HopeSpeechEDI_BERT_Multi_Malayalam.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "HopeSpeechEDI_BERT_Multi_Malayalam.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "evYV0yrQ2u_b",
        "s9n3_5jI2ywo",
        "sWPDqogJrjIZ"
      ],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "fa35075a0c3b4ac797b447ed0cbdfb5e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_3782bf5eb65b49909015511146b467d0",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_c78ee957ff6b48b7ac56bbc7ad36401d",
              "IPY_MODEL_996c25d462424bbf90f0dff2b92fc816"
            ]
          }
        },
        "3782bf5eb65b49909015511146b467d0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c78ee957ff6b48b7ac56bbc7ad36401d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_9d3409c0ec024c4f93dfc46446cb87f5",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 714314041,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 714314041,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_0250d973b87a4a37af7c14c8a5382793"
          }
        },
        "996c25d462424bbf90f0dff2b92fc816": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_fa578d2e60d141a8a3f2a86d2ea84a5c",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 714M/714M [00:09&lt;00:00, 71.6MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_80cd0c340dd248b1ab47f4c7e844b20a"
          }
        },
        "9d3409c0ec024c4f93dfc46446cb87f5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "0250d973b87a4a37af7c14c8a5382793": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "fa578d2e60d141a8a3f2a86d2ea84a5c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "80cd0c340dd248b1ab47f4c7e844b20a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "elqe9PQrVH6P"
      },
      "source": [
        "### Performing checks for the resources available"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fSELLChxa5su",
        "outputId": "50b656fd-c725-4011-cacf-1c549ac1c76b"
      },
      "source": [
        "import torch\r\n",
        "\r\n",
        "# If there's a GPU available...\r\n",
        "if torch.cuda.is_available():    \r\n",
        "\r\n",
        "    # Tell PyTorch to use the GPU.    \r\n",
        "    device = torch.device(\"cuda\")\r\n",
        "\r\n",
        "    print('There are %d GPU(s) available.' % torch.cuda.device_count())\r\n",
        "\r\n",
        "    print('We will use the GPU:', torch.cuda.get_device_name(0))\r\n",
        "\r\n",
        "# If not...\r\n",
        "else:\r\n",
        "    print('No GPU available, using the CPU instead.')\r\n",
        "    device = torch.device(\"cpu\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "There are 1 GPU(s) available.\n",
            "We will use the GPU: Tesla T4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8SokVowWo3cc",
        "outputId": "e91b2959-9171-41e1-88e3-5396f5eacaff"
      },
      "source": [
        "!nvidia-smi"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fri Feb  5 04:13:30 2021       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.39       Driver Version: 418.67       CUDA Version: 10.1     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   38C    P8    10W /  70W |     10MiB / 15079MiB |      0%      Default |\n",
            "|                               |                      |                 ERR! |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K-gbOgflVRxg"
      },
      "source": [
        "### Installing huggingface transformers library"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DbDuxKy0a9Zl",
        "outputId": "763ab7b1-06f7-4ff8-8e7a-425c667136d6"
      },
      "source": [
        "!pip install transformers"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: transformers in /usr/local/lib/python3.6/dist-packages (4.2.2)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers) (4.41.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers) (2.23.0)\n",
            "Requirement already satisfied: sacremoses in /usr/local/lib/python3.6/dist-packages (from transformers) (0.0.43)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers) (3.0.12)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from transformers) (1.19.5)\n",
            "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from transformers) (3.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from transformers) (20.9)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers) (2019.12.20)\n",
            "Requirement already satisfied: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers) (0.8)\n",
            "Requirement already satisfied: tokenizers==0.9.4 in /usr/local/lib/python3.6/dist-packages (from transformers) (0.9.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2020.12.5)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2.10)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (3.0.4)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.15.0)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.0.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (7.1.2)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.7.4.3)\n",
            "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->transformers) (2.4.7)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bPwaYLiRSNPC"
      },
      "source": [
        "## Importing necessary packages"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0XdFrhr8SRG0"
      },
      "source": [
        "import pandas as pd\r\n",
        "import numpy as np \r\n",
        "import random\r\n",
        "from sklearn.preprocessing import LabelEncoder\r\n",
        "from sklearn.utils.class_weight import compute_class_weight\r\n",
        "import time\r\n",
        "import datetime\r\n",
        "from sklearn.metrics import classification_report,confusion_matrix\r\n",
        "import random\r\n",
        "import time\r\n",
        "import torch.nn as nn\r\n",
        "from transformers import AutoModel , AutoModelForSequenceClassification, AutoConfig , AutoTokenizer , AdamW ,get_linear_schedule_with_warmup \r\n",
        "import torch\r\n",
        "import matplotlib.pyplot as plt\r\n",
        "import seaborn as sns\r\n",
        "from matplotlib import rc\r\n",
        "from matplotlib.ticker import MaxNLocator"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dROX3juhVCxC"
      },
      "source": [
        "## Setting some configuration values"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Kzafv4BzVCC9"
      },
      "source": [
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (16,12)\r\n",
        "\r\n",
        "# Set the seed value all over the place to make this reproducible.\r\n",
        "seed_val = 42\r\n",
        "\r\n",
        "random.seed(seed_val)\r\n",
        "np.random.seed(seed_val)\r\n",
        "torch.manual_seed(seed_val)\r\n",
        "torch.cuda.manual_seed_all(seed_val)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2v1AIN_OVX4t"
      },
      "source": [
        "## Importing drive into the colaboratory"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Lofimyh2a_tp",
        "outputId": "628355f4-be1a-49e8-bed1-28ec83ac33a1"
      },
      "source": [
        "from google.colab import drive \r\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yOK-M00dVeW2"
      },
      "source": [
        "## Importing dataset directories"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-y-JRPKBbCTv"
      },
      "source": [
        "from os import getcwd , listdir \r\n",
        "from os.path import join\r\n",
        "curr_dir = getcwd()\r\n",
        "drive_dir = join(curr_dir , 'drive','MyDrive')\r\n",
        "dataset_dir = join(drive_dir,'Codalab','HopeSpeech Detection For Equality,DiversityAnd Inclusion','Dataset')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7YU1h8WhmqvK",
        "outputId": "c289e863-5c07-4b4d-bcb5-69769906c5e5"
      },
      "source": [
        "listdir(dataset_dir)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['english_hope_dev.csv',\n",
              " 'english_hope_train.csv',\n",
              " 'malayalam_hope_dev.csv',\n",
              " 'malayalam_hope_train.csv',\n",
              " 'tamil_hope_first_dev.csv',\n",
              " 'tamil_hope_first_train.csv',\n",
              " 'tamil_hope_test.csv',\n",
              " 'malayalam_hope_test.csv',\n",
              " 'english_hope_test.csv',\n",
              " 'english_hope_test _labels.csv',\n",
              " 'malayalam_hope_test _labels.csv',\n",
              " 'tamil_hope_test _labels.csv',\n",
              " 'malayalam_hope_test_labels.csv']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FUPkZxjLVjLK"
      },
      "source": [
        "## Loading training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "joone3H4bINR",
        "outputId": "ae6ef7ed-e7dd-46c4-b135-a1b8d849fce7"
      },
      "source": [
        "train_df_path = join(dataset_dir,'malayalam_hope_train.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "train_df = pd.read_csv(train_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of training sentences: {:,}\\n'.format(train_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "train_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 8,564\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>7913</th>\n",
              "      <td>Iniyippo ningal pubg kalichalum kuzhappamilla ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6065</th>\n",
              "      <td>ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1649</th>\n",
              "      <td>Suryammaa ishanikkaaaa happy wedding anniversa...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>Ente bayi ittekkana shoe muthal jaddy vare ava...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1918</th>\n",
              "      <td>Ayaal entha parayunath ennu ayaalkk tahnne ari...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3617</th>\n",
              "      <td>ചക്ക കുരു പൊട്ടിയോ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>233</th>\n",
              "      <td>പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6927</th>\n",
              "      <td>Helo  iku പകരം എന്തുണ്ട് ?</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2094</th>\n",
              "      <td>Kevin mandane kaanumbhaz santhosh pandittine o...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3114</th>\n",
              "      <td>പൊളിച്ചു bro</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text            label\n",
              "7913  Iniyippo ningal pubg kalichalum kuzhappamilla ...  Non_hope_speech\n",
              "6065  ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...  Non_hope_speech\n",
              "1649  Suryammaa ishanikkaaaa happy wedding anniversa...      Hope_speech\n",
              "710   Ente bayi ittekkana shoe muthal jaddy vare ava...  Non_hope_speech\n",
              "1918  Ayaal entha parayunath ennu ayaalkk tahnne ari...  Non_hope_speech\n",
              "3617                                 ചക്ക കുരു പൊട്ടിയോ  Non_hope_speech\n",
              "233          പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം      Hope_speech\n",
              "6927                         Helo  iku പകരം എന്തുണ്ട് ?  Non_hope_speech\n",
              "2094  Kevin mandane kaanumbhaz santhosh pandittine o...  Non_hope_speech\n",
              "3114                                       പൊളിച്ചു bro      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w4VW351225YK",
        "outputId": "4b438daf-9cc4-4777-a240-0a85f6991562"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    6205\n",
              "Hope_speech        1668\n",
              "not-malayalam       691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ooOv9QZtnLIF"
      },
      "source": [
        "\r\n",
        "le = LabelEncoder()\r\n",
        "train_df['label'] = le.fit_transform(train_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a89Bf4LpnigU",
        "outputId": "38010f74-88a4-404a-a4b8-cf430de1da98"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    6205\n",
              "0    1668\n",
              "2     691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bvNeR4lTVnK0"
      },
      "source": [
        "### Loading `train_sentences` and `train_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EufQZx2dbKMT"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "train_sentences = train_df['text'].values\r\n",
        "train_labels = train_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wnZSg5f7ZWs_"
      },
      "source": [
        "## Saving Class Names"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "83tTT-wbZa1o",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d1d04af2-4586-4551-bc09-72b137868844"
      },
      "source": [
        "class_names = le.inverse_transform(range(0,len(train_df['label'].unique())))\r\n",
        "class_names"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Hope_speech', 'Non_hope_speech', 'not-malayalam'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ToUbAgZ9ap63"
      },
      "source": [
        "## Loading the validation data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "Dle8VzoAjOLS",
        "outputId": "676b6fe2-fe7d-45c4-b225-25772feebba6"
      },
      "source": [
        "val_df_path = join(dataset_dir,'malayalam_hope_dev.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "val_df = pd.read_csv(val_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of validation sentences: {:,}\\n'.format(val_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "val_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of validation sentences: 1,070\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>424</th>\n",
              "      <td>ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>722</th>\n",
              "      <td>@Mallu crafts thanik or gay aya kutti ondavath...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>306</th>\n",
              "      <td>Helo. Lesbiann.. chodichal. Vanno</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>116</th>\n",
              "      <td>Nikesh  nte  kada  kettapol  sangadam  തോന്നി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>551</th>\n",
              "      <td>Ithil parenjekana korey app onnum njan kettit ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>263</th>\n",
              "      <td>Gay enn kandappo nice aayitt kaanan vanirikkka</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>333</th>\n",
              "      <td>Public reactions kalakki but kurach koodi leng...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>575</th>\n",
              "      <td>പോയി ചതൂ ഡേ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>597</th>\n",
              "      <td>Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>634</th>\n",
              "      <td>Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                  text            label\n",
              "424                  ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്  Non_hope_speech\n",
              "722  @Mallu crafts thanik or gay aya kutti ondavath...  Non_hope_speech\n",
              "306                  Helo. Lesbiann.. chodichal. Vanno  Non_hope_speech\n",
              "116   Nikesh  nte  kada  kettapol  sangadam  തോന്നി...  Non_hope_speech\n",
              "551  Ithil parenjekana korey app onnum njan kettit ...  Non_hope_speech\n",
              "263     Gay enn kandappo nice aayitt kaanan vanirikkka  Non_hope_speech\n",
              "333  Public reactions kalakki but kurach koodi leng...  Non_hope_speech\n",
              "575                                        പോയി ചതൂ ഡേ  Non_hope_speech\n",
              "597  Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...  Non_hope_speech\n",
              "634  Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AypCmtBcDV6v",
        "outputId": "379e1736-8029-45ad-d10f-c46eaa34d2ec"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    784\n",
              "Hope_speech        190\n",
              "not-malayalam       96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-CgK81lGDPKC"
      },
      "source": [
        "val_df['label'] = le.transform(val_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Yfgn-E6JDZQZ",
        "outputId": "f1f61b6e-9b8d-4e15-d36d-675b484dd3ff"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    784\n",
              "0    190\n",
              "2     96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DMdNNVqrDCuN"
      },
      "source": [
        "### Loading `val_sentences` and `val_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LvGhjUkaDCuO"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "val_sentences = val_df['text'].values\r\n",
        "val_labels = val_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4mgM6b0yL0NM"
      },
      "source": [
        "## Loading the test data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "d7tVWiIeL0NN",
        "outputId": "541fb498-fd40-478b-e9ea-d2fce69674cf"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test_labels.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "test_df = pd.read_csv(test_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of test sentences: {:,}\\n'.format(test_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "test_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of test sentences: 1,071\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "      <th>Unnamed: 2</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>673</th>\n",
              "      <td>Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>180</th>\n",
              "      <td>Kundanmar Ennanu Nchangal Vilikkua</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>474</th>\n",
              "      <td>നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>834</th>\n",
              "      <td>ഇതൊക്കെ രാജ്യം നിരോധിക്കണം</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>668</th>\n",
              "      <td>നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1055</th>\n",
              "      <td>@Vyas Deep brother swarganuragam thettanu yoji...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>448</th>\n",
              "      <td>ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>629</th>\n",
              "      <td>@Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>488</th>\n",
              "      <td>@rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text  ... Unnamed: 2\n",
              "673   Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...  ...        NaN\n",
              "180                  Kundanmar Ennanu Nchangal Vilikkua  ...        NaN\n",
              "474   നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...  ...        NaN\n",
              "834                          ഇതൊക്കെ രാജ്യം നിരോധിക്കണം  ...        NaN\n",
              "668   നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...  ...        NaN\n",
              "1055  @Vyas Deep brother swarganuragam thettanu yoji...  ...        NaN\n",
              "4                                       I respect you..  ...        NaN\n",
              "448   ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...  ...        NaN\n",
              "629   @Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...  ...        NaN\n",
              "488   @rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...  ...        NaN\n",
              "\n",
              "[10 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wkt73boTL0NO",
        "outputId": "e6807c93-bef4-429b-b80e-82450552410b"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    776\n",
              "Hope_speech        194\n",
              "not-malayalam      101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ProewaglL0NP"
      },
      "source": [
        "test_df['label'] = le.transform(test_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GYR2XokSL0NP",
        "outputId": "67cf00b1-1a3b-4f99-c83b-5c1986fbe75a"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    776\n",
              "0    194\n",
              "2    101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eCCNrKNmL0NQ"
      },
      "source": [
        "### Loading `test_sentences` and `test_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NvBSOGdkL0NR"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "test_sentences = test_df['text'].values\r\n",
        "test_labels = test_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fS2UcOiEVuhm"
      },
      "source": [
        "## Handling class imbalance using `sklearn's compute_class_weight`\r\n",
        "\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WL4tP_YkI1mY"
      },
      "source": [
        "\r\n",
        "# #compute the class weights\r\n",
        "# class_wts = compute_class_weight('balanced', np.unique(train_labels), train_labels)\r\n",
        "\r\n",
        "# print(class_wts)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "z_WjMTuibsrf"
      },
      "source": [
        "## Helper Functions"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bef28eHNV-_d"
      },
      "source": [
        "#### 1) Update Interval Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lBK0ujfEbMir"
      },
      "source": [
        "def good_update_interval(total_iters, num_desired_updates):\r\n",
        "    '''\r\n",
        "    This function will try to pick an intelligent progress update interval \r\n",
        "    based on the magnitude of the total iterations.\r\n",
        "\r\n",
        "    Parameters:\r\n",
        "      `total_iters` - The number of iterations in the for-loop.\r\n",
        "      `num_desired_updates` - How many times we want to see an update over the \r\n",
        "                              course of the for-loop.\r\n",
        "    '''\r\n",
        "    # Divide the total iterations by the desired number of updates. Most likely\r\n",
        "    # this will be some ugly number.\r\n",
        "    exact_interval = total_iters / num_desired_updates\r\n",
        "\r\n",
        "    # The `round` function has the ability to round down a number to, e.g., the\r\n",
        "    # nearest thousandth: round(exact_interval, -3)\r\n",
        "    #\r\n",
        "    # To determine the magnitude to round to, find the magnitude of the total,\r\n",
        "    # and then go one magnitude below that.\r\n",
        "\r\n",
        "    # Get the order of magnitude of the total.\r\n",
        "    order_of_mag = len(str(total_iters)) - 1\r\n",
        "\r\n",
        "    # Our update interval should be rounded to an order of magnitude smaller. \r\n",
        "    round_mag = order_of_mag - 1\r\n",
        "\r\n",
        "    # Round down and cast to an int.\r\n",
        "    update_interval = int(round(exact_interval, -round_mag))\r\n",
        "\r\n",
        "    # Don't allow the interval to be zero!\r\n",
        "    if update_interval == 0:\r\n",
        "        update_interval = 1\r\n",
        "\r\n",
        "    return update_interval"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eMGycwGAWFyO"
      },
      "source": [
        "#### 2) Format time function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9zVyNQLm-3q"
      },
      "source": [
        "def format_time(elapsed):\r\n",
        "    '''\r\n",
        "    Takes a time in seconds and returns a string hh:mm:ss\r\n",
        "    '''\r\n",
        "    # Round to the nearest second.\r\n",
        "    elapsed_rounded = int(round((elapsed)))\r\n",
        "    \r\n",
        "    # Format as hh:mm:ss\r\n",
        "    return str(datetime.timedelta(seconds=elapsed_rounded))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EBAo04ENWw3n"
      },
      "source": [
        "#### 3) Make Smart Batches function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nof-AUeoiZc2"
      },
      "source": [
        "def make_smart_batches(text_samples, labels, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(labels)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(labels), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, labels), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_labels = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_labels = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_labels.append(torch.tensor(batch_labels))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6EIVfH5-mo_f"
      },
      "source": [
        "### 4) Make Smart Batches ( On Test Set)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ggH8AkAEaV9N"
      },
      "source": [
        "def make_smart_batches_on_test(text_samples, text_ids, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(text_samples)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(text_samples), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, text_ids), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_ids = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_ids.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_ids = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_ids) in zip(batch_ordered_sentences, batch_ordered_ids):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_ids.append(torch.tensor(batch_ids))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "x6EHYpUbz8fo"
      },
      "source": [
        "### 5) Function for calculating accuracy per class"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Knuw_DOei8RO"
      },
      "source": [
        "def accuracy_per_class(preds, labels , label_dict):\r\n",
        "    \r\n",
        "    preds_flat = np.argmax(preds, axis=1).flatten()\r\n",
        "    labels_flat = labels.flatten()\r\n",
        "\r\n",
        "    for label in np.unique(labels_flat):\r\n",
        "        y_preds = preds_flat[labels_flat==label]\r\n",
        "        y_true = labels_flat[labels_flat==label]\r\n",
        "        print(f'Class: {label_dict[label]}')\r\n",
        "        print(f'Accuracy: {round(100*len(y_preds[y_preds==label])/len(y_true) , 2)}\\n')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sOWk_8lpWO17"
      },
      "source": [
        "### 6) Function for plotting training history"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R7-FAyfnWM65"
      },
      "source": [
        "def plot_training_history(history):\r\n",
        "  fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(18, 6))\r\n",
        "\r\n",
        "  ax1.plot(history['train_loss'], label='train loss')\r\n",
        "  ax1.plot(history['val_loss'], label='validation loss')\r\n",
        "\r\n",
        "  ax1.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "  ax1.set_ylim([-0.05, 1.05])\r\n",
        "  ax1.legend()\r\n",
        "  ax1.set_ylabel('Loss')\r\n",
        "  ax1.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  ax2.plot(history['train_acc'], label='train accuracy')\r\n",
        "  ax2.plot(history['val_acc'], label='validation accuracy')\r\n",
        "\r\n",
        "  ax2.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "  ax2.set_ylim([-0.05, 1.05])\r\n",
        "  ax2.legend()\r\n",
        "\r\n",
        "  ax2.set_ylabel('Accuracy')\r\n",
        "  ax2.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  fig.suptitle('Training history')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "A7QOTORh_JHa"
      },
      "source": [
        "### 7) Function to check accuracy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yzRDobQ6MwaR"
      },
      "source": [
        "def check_accuracy(predictions,true_labels):\r\n",
        "  # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  # Calculate simple flat accuracy -- number correct over total number.\r\n",
        "  accuracy = (preds == true_labels).mean()\r\n",
        "\r\n",
        "  return accuracy"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "D7TtFkV5_Olz"
      },
      "source": [
        "### 8) Function to evaluate model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TSBNdYHYMA7Q"
      },
      "source": [
        "def eval_model(model,py_inputs, py_attn_masks, py_labels):\r\n",
        "# Prediction on test set\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  print('Doing validation on {:,} sentences...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "  total_val_loss = 0\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "\r\n",
        "      logits = output.logits \r\n",
        "      loss = output.loss\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "\r\n",
        "      total_val_loss += loss.item()\r\n",
        "  \r\n",
        "  val_accuracy = check_accuracy(predictions,true_labels)\r\n",
        "\r\n",
        "  validation_time = format_time(time.time() - t0)\r\n",
        "  \r\n",
        "  # Calculate the average loss over all of the batches.\r\n",
        "  avg_val_loss = total_val_loss / len(py_inputs)     \r\n",
        "    \r\n",
        "\r\n",
        "  # print('Accuracy: {:.3f}'.format(val_accuracy))\r\n",
        "  return (avg_val_loss,val_accuracy,validation_time)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Lrt_FyJIbC8j"
      },
      "source": [
        "### 9) Function for making predictions on our test dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eylCkH2Zipq5"
      },
      "source": [
        "def get_predictions(py_inputs, py_attn_masks, py_labels):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "      # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return (preds,true_labels)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eiRNCS-EbZmy"
      },
      "source": [
        "### 10) Function for making predictions on test dataset(without labels)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RIuwhVSmZvkd"
      },
      "source": [
        "def get_predictions_test(py_inputs, py_attn_masks,py_ids):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels ,ids = [], [] , []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_ids = py_ids[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      b_ids = b_ids.detach().cpu().numpy()\r\n",
        "      # Store predictions\r\n",
        "      predictions.append(logits)\r\n",
        "      ids.append(b_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  ids = np.concatenate(ids,axis=0)\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return ids,preds"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4IM8r_ddYZZS"
      },
      "source": [
        "### 11) Confusion Matrix Helper Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DqNaS8SrBox5"
      },
      "source": [
        "def show_confusion_matrix(confusion_matrix, class_names):\r\n",
        "\r\n",
        "  cm = confusion_matrix.copy()\r\n",
        "\r\n",
        "  cell_counts = cm.flatten()\r\n",
        "\r\n",
        "  cm_row_norm = cm / cm.sum(axis=1)[:, np.newaxis]\r\n",
        "\r\n",
        "  row_percentages = [\"{0:.2f}\".format(value) for value in cm_row_norm.flatten()]\r\n",
        "\r\n",
        "  cell_labels = [f\"{cnt}\\n{per}\" for cnt, per in zip(cell_counts, row_percentages)]\r\n",
        "  cell_labels = np.asarray(cell_labels).reshape(cm.shape[0], cm.shape[1])\r\n",
        "\r\n",
        "  df_cm = pd.DataFrame(cm_row_norm, index=class_names, columns=class_names)\r\n",
        "\r\n",
        "  hmap = sns.heatmap(df_cm, annot=cell_labels, fmt=\"\", cmap=\"Blues\")\r\n",
        "  hmap.yaxis.set_ticklabels(hmap.yaxis.get_ticklabels(), rotation=0, ha='right')\r\n",
        "  hmap.xaxis.set_ticklabels(hmap.xaxis.get_ticklabels(), rotation=30, ha='right')\r\n",
        "  plt.ylabel('True Sign')\r\n",
        "  plt.xlabel('Predicted Sign');"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MBxHY4rMojd-"
      },
      "source": [
        "## Loading the tokenizer using AutoTokenizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fIlwEvcMb4pb",
        "outputId": "84a2d1d7-c3ec-4436-ef76-094796c3933e"
      },
      "source": [
        "model_name = 'bert-base-multilingual-cased'\r\n",
        "# Load the BERT tokenizer.\r\n",
        "print(f'Loading {model_name} tokenizer...')\r\n",
        "tokenizer = AutoTokenizer.from_pretrained(model_name, do_lower_case=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Loading bert-base-multilingual-cased tokenizer...\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OVs3Jb3Vb89i"
      },
      "source": [
        "## Smart Batching of the training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cWNt4eOLofmF"
      },
      "source": [
        "lengths = []\r\n",
        "for text in train_sentences:\r\n",
        "  lengths.append(len(text))       "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "hbdGRA3Bo02O",
        "outputId": "fde104d7-56dc-401e-9a94-4e75bde4bc4f"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(lengths)), lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Tokenizing')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAusAAAGaCAYAAAC2bw3EAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdeXwN5/4H8M8RSWwhllhu7C0JIiFVLVWtPdKqSAlaca2luLeWtqRXb3cpQrVo7fRG0NJEqFa56lLLT2triqCoJVUSKREJCXF+f7jn3LOfmXNmzsyc83m/Xn1VZubMfGfmmZnvPPPMMzq9Xq8HERERERGpTjmlAyAiIiIiItuYrBMRERERqRSTdSIiIiIilWKyTkRERESkUkzWiYiIiIhUisk6EREREZFKMVknIhIgMTERXbt2VToMUkhYWBimTZum2PKnTZuGsLAw0b/LyclBWFgY5s+fL0NUROQJ5ZUOgIi816VLl7BkyRL89NNP+OOPPxAQEIBatWohMjIS/fr1w+OPP650iJqQnp6OpKQks2EVK1ZEnTp18OSTT2LkyJGoV6+ecVxOTg66devmcJ67du1C3bp1AQBdu3bF77//bnO6gQMH4t133zUbdvLkSaxcuRI//vgj8vLyUKlSJYSFhSEuLg5xcXHw8/Mzm37+/PlYsGCB8W+dToeqVauiRYsWGDp0qM1YnSWmaWlpaNeunc1xiYmJ+PHHHx3+3iA5ORnx8fGCpiUiUgKTdSKSxS+//ILExESUL18ecXFxePjhh3Hnzh1cuHABe/fuReXKlZmsi5SYmIjWrVsDAIqKivDLL78gLS0N27dvx5YtW1ClShWz6Z944gn07dvX5ryqVatm9nfdunUxefJkq+maNGli9veaNWvw/vvvo2rVqujXrx+aNm2KmzdvYtu2bXjjjTewZcsWLFiwAJUqVbKa19///nfUr18fZWVluHjxIr744guMGzcOKSkp6NOnj9X0LVq0wPDhw23G37RpU5vDAWDs2LHo37+/8e/r168jOTkZ7dq1Q0JCgtm00dHRduejJu+99x7eeecd0b8LDQ1FVlaW1Q0UEWkHk3UiksXChQtx+/ZtZGZmIjw83Gp8Xl6eAlFpW7t27RATE2M2rGrVqli1ahX279+PHj16mI1r3Lix3WTdUlBQkNNp9+7di3fffRfNmzfHqlWrUKNGDeO4kSNH4qOPPsKiRYvw9ttvY9asWVa/79y5s/FmAwBiYmLQt29fLFmyxGayXqdOHcHxm3riiSfM/s7JyUFycjIaNGjg0vzUwN/f36Xf6XQ6BAYGShwNEXkS26wTkSzOnz+P4OBgm4k6AISEhJj9/c0332Ds2LF4+umnERERgcceewzjxo3DyZMnrX7btWtXJCYm4uTJkxg2bBjatm2LDh064MMPP8S9e/dQUlKCmTNn4sknn0Tr1q3x4osv4uzZs2bzSE9PR1hYGPbt24f58+ejS5cuiIiIQJ8+fbBlyxZR6/naa6+hU6dOiIiIQNeuXTFz5kwUFxebTffHH38gKSnJuJwOHTpg0KBByMjIELwsW2rXrg3A9WROjDlz5hj/b5qoG0ycOBFRUVHIzMzEqVOnnM4vPDwc1atXx/nz56UOVbD169ejX79+iIyMxCOPPIIRI0bg4MGDgn57/PhxPPHEE4iNjcXly5cBAHq9HmvWrEF8fDyioqLQtm1bJCYm4v/+7//Mfmvalnznzp14/vnn0bp1a3Tq1AkzZ87EvXv3zKa3bLN+4MABhIWF2f0vPT3dajmuLhsAvvvuOzz33HNo3bo1nn76aSxYsAD79u0zWxYRyYM160Qki4YNG+K3337Dtm3b0LNnT6fTr169GsHBwUhISEBISAguXryIL7/8EoMHD0ZGRgYaN25sNv2VK1cwfPhwxMbGolevXti7dy9WrlwJPz8/nDlzBnfu3MFLL72E69evY8WKFRg3bhy+/fZblCtnXkeRkpKC4uJiDB48GMCDJH7y5MkoKSlx2pb52LFj+Otf/4qqVati4MCBqFOnDk6ePInU1FQcOXIEqamp8Pf3x7179zB8+HBcvXoVL7zwAho3boxbt27h1KlTOHjwIPr16ydomxYVFeHPP/8EABQXF+PYsWNYvnw5GjVqZLNJUUlJiXF6U+XLl0fVqlXNhpWVldmc1pCUX7p0CcePH0d0dDSaNWtmMz6dTof+/fvj559/xvbt2522Oy8oKEBBQQFq1qxpc/y9e/dsxqTT6VC9enWH8xZi9uzZWLZsGSIjIzF58mTcunULX375Jf7617/i008/xVNPPWX3tz/88AP+/ve/IywsDIsWLUJwcDAA4LXXXsOWLVvQq1cvxMfHo7S0FJs3b8aIESMwf/58q/b5u3btwpo1azBo0CA8//zz2LFjB1asWIFq1aph7Nixdpf/0EMP2Xx6sWLFCpw8edLuNnVl2d988w0mT56Mhg0bYsKECfDz88PGjRvx/fffO10GEbmPyToRyeLll1/Gvn378Le//Q2NGzdGdHQ0WrdujcceewwPPfSQ1fTLli2zauccFxeHvn37YtWqVXj77bfNxl28eBHz5s1D7969AQCDBw9GfHw8li9fji5dumDVqlXQ6XQAgODgYHzwwQfYu3cvnnzySbP5XL9+HZs2bUJQUJBxPs899xw+/PBDxMbGokKFCnbX8Y033kBISAg2bNhg1l68Q4cOmDBhAjZv3oz4+HicOXMGv/32G1599VWMHj1a+Ea0sTxL0dHR+OSTT2zGuWHDBmzYsMFqeLNmzfD111+bDTt37hw6dOhgNW1WVhYCAwPx66+/AgBatWrlMEbD+NOnT1uNu3XrFv78809jm/V58+bh/v37eO6552zOa8+ePTZjqlSpEo4cOeIwDmfOnTuH5cuXIzo6Gp9//jkCAgIAAAMGDMAzzzyDd955B9u3b7fZ1nvjxo2YPn06OnfujLlz5xq3/fbt27F582a8++67GDhwoHH6oUOHIiEhAR988AG6du1qLJcAcObMGXz99deoX78+gAflr0+fPli9erXDZL1WrVpWTXrWrFmDkydPYujQoQ5vNMQs+969e0hOTkaNGjWwfv1647sOhuOEiOTHZJ2IZNG2bVt89dVXWLlyJXbv3o309HTj4/J27drhww8/RIMGDYzTGxJ1vV6PoqIilJaWonr16mjSpAmysrKs5l+nTh1jom4QHR2N48ePIzEx0SwhMvQacuHCBatkffDgwcZEHXjQdnvQoEGYO3cuDhw4YDfpOXXqFE6dOoW//e1vKC0tNasBfuSRR1CpUiXs3bsX8fHxxvkfOHAA8fHxgmo9bRk/frxxXYqLi3HixAmsWrUKY8aMwcqVK61eGu3WrRuGDBliNR9bL3+Ghobi/ffftxpuaF5z69YtALB6idWSYXxhYaHVuGHDhpn9HRAQgNGjR2PixIk25xUVFWVznBQvS+7YsQN6vR6jRo0yJurAg3IVHx+Pzz//HCdOnDBrYw8AS5Yswdy5c5GQkIC33nrLLJZNmzahcuXK6N69u9UTga5du2L+/Pk4f/682Uu73bp1MybLwIOnBo899hhWr16NoqIiVK5cWdD67N69G++//z66dOli1XOQPUKWffz4ceTm5mLUqFFm5aty5coYNGgQUlJSBC2LiFzHZJ2IZBMWFoYPP/wQAPD777/jp59+wvr163Hw4EGMGzcOX331lTFROnHiBD7++GP8+OOPVu29TRMKR8MMyYTlOEOTjxs3blj9xlavIoaa/5ycHLvrZmgDP3/+fLt9WF+7dg3Ag0R47NixWLJkCTp16oQWLVrg8ccfR0xMDCIjI+0uw1Lz5s3RsWNH49/du3fHww8/jEmTJmHp0qV49dVXzaavW7eu2fSOVKpUyeG0hiTckLTbYxhvegNk8M9//hNNmjTB7du3ceDAAaSmpuLmzZsoX972pah69eqC4xfLsG9tNekxDLt06ZJZsr5t2zYUFRUhISHBqjtL4EGZKCoqchhzfn6+WbJuesNqYGhSc+PGDUHJ+qlTpzBp0iQ0a9YMc+bMsWrqZY+QZRu2k2WvQPaGEZH0mKwTkUeEhoYiNDQUffv2xQsvvIDDhw8jKysL7dq1w+XLl/Hiiy+iSpUqePnll9G0aVNUrFgROp0OM2bMsEreAce1q/aSFb1eL9n6GIwYMcKqtt7AtF34pEmT0L9/f/znP//BwYMHsWHDBixfvhyjRo3Ca6+95vLyO3XqBABWLzBKzZDAHj9+3OF0J06cAPDgxsJSZGSkMfnt1q0batWqhTlz5qBFixbGdwbULDIyEr///ju+++47JCQkWNW66/V61KhRw/giri2WNweOyrGQ8pqXl4exY8eiYsWKWLx4seCaeCmWTUSewWSdiDxKp9MhKioKhw8fRm5uLoAHbX2Li4vx2WefWb0oeePGDbNmClI7d+6c1TBDrbmt2nuDRo0aAXhwYyC09rdBgwZITExEYmIiSkpKMHLkSCxbtgwjRoxwuWmMoeeOoqIil34vVIMGDdCiRQscOXIEZ8+etfnegV6vN7aR7969u9N5Dh8+HBs2bMC8efPQp08fp01spGSoVf7111/RsGFDs3Fnzpwxm8agbt26mDlzJoYOHYrhw4dj2bJlaNOmjXF8o0aNcP78eURFRYlKml11+/ZtjB07FtevX8fq1auNH7mSUmhoKADgt99+sxpnaxgRSY9dNxKRLPbu3WuzC7g7d+5g7969AP7X3MRQw2dZm/fll1/K3h/72rVrzdpXFxYWYt26dahatSrat29v93ctW7ZE8+bNsW7dOly6dMlq/L1794zNbgoLC3H37l2z8YGBgcYmOAUFBS7H/+9//xuA8xc/pWD4aNKrr76K69evW42fP38+jh49ir59+9rtstOUv78/xowZgxs3buBf//qX5PE6YnjRc/ny5Wb7Jjc3F+np6QgNDUXLli2tflenTh2sXr0atWvXxogRI3Do0CHjuLi4ONy/fx9z5861uUxDsygp6PV6vPbaazh+/Dhmz56NiIgIyeZtKiIiAiEhIcjIyDArp0VFRVi3bp0syyQic6xZJyJZJCcn48aNG+jatSuaN2+OChUq4MqVK9i8eTPOnz+PuLg4Y9d+nTt3RsWKFfH6669jyJAhqFq1Kg4fPozdu3ejYcOGKCsrky3O6tWrY8CAAcZuGtPT03H58mW8//77qFixot3f6XQ6zJo1C3/961/x3HPP4fnnnzf7Suv27dsxefJkxMfH48CBA3jzzTfRs2dPNGnSBJUrV8axY8ewYcMGREVFOfwap6mDBw+ipKQEwIObnuPHjyM9Pd3YfMjS+fPnkZmZaXNeHTt2tOrr3pnOnTtj+vTp+OCDDxAbG4v4+Hg0adLE+AXTI0eO4IknnrDquceRvn37YuHChVi1ahWGDh1qVrt+9epVu/G3bdvWqkZcjKZNmxqfbAwZMgS9e/dGUVERvvzySxQXFyMlJcVuM5GQkBCkpqZi2LBhGDVqFBYvXoz27dsjJiYG8fHxWL16NY4fP44uXbqgevXquHLlCo4ePYoLFy5gx44dLsdsau3atdi+fTvat2+P4uJiq+0UHR1ts026WOXLl8fUqVPx6quvYsCAAejfvz/8/PyQkZGB4OBg5OTkmL3MTUTSY7JORLKYNm0aduzYgUOHDuG7775DYWEhgoKC0Lx5c4wePdqsD/OGDRti6dKlmDt3LhYtWgQ/Pz9ER0cjNTUV7733Hn7//XfZ4nz11Vdx8OBBrFmzBteuXUOTJk2QkpJi84uallq0aIGMjAwsXrwY33//PdatW4fKlSsjNDQU/fr1M3Y7GBYWhh49euDHH3/E5s2bcf/+fdSrVw9jxozBiBEjBMeamppq/Lefnx9q1qyJ3r17Y9y4cTZf9tu7d6/xKYallStXik7WAWDIkCGIjo7GypUr8fXXXyM/Px8VK1ZEeHg4ZsyYgbi4OFG9tZQvXx4vvfQS3nrrLaxatQoTJkwwjsvOzsbrr79u83fvv/++W8k68KBP9EaNGmHNmjWYM2cO/P39ERUVhTlz5hh73bGnZs2a+Ne//oXhw4fjpZdewmeffYYOHTogOTkZjz32GL788kssXrwYd+/eRUhICFq2bIkpU6a4Fa+p/Px8AMCPP/6IH3/80Wq84YutUujTpw/Kly+PTz/9FJ988glq1aqF/v37IywsDBMmTOAXUolkptPzLRIi8kHp6elISkrCv/71Lzz22GNKh0OkOStWrMDMmTPxxRdfmLXdJyJpsc06ERER2VVaWmrVFK2oqAhpaWkIDg622bafiKTDZjBERERk16VLlzB69Gg888wzqF+/PvLy8pCRkYGcnBy8/fbbsvbWRERM1omIiMiBGjVqoE2bNti8eTPy8/NRvnx5NG/eHFOmTEFsbKzS4RF5PbZZJyIiIiJSKbZZJyIiIiJSKSbrREREREQqxTbrDly/XoT79z3fSqhmzSrIz7/l8eWStrHckCtYbsgVLDfkCpYb28qV06F69cp2xzNZd+D+fb0iybph2URisdyQK1huyBUsN+QKlhvx2AyGiIiIiEilmKwTEREREakUk3UiIiIiIpVisk5EREREpFJM1omIiIiIVIrJOhERERGRSjFZJyIiIiJSKSbrREREREQqxWSdiIiIiEilmKwTEZFmzEw7jJlph5UOg4jIY5isExERERGpFJN1IiIiIiKVYrJORERERKRSTNaJiIiIiFSKyToRERERkUqVVzoAIiIioaa+GK10CEREHsWadSIiIiIilWKyTkRERESkUkzWicin8KM6RESkJUzWiYiIiIhUism6l2GtIREREZH3YLJORERERKRSTNaJiIiIiFSKyToRERERkUrxo0hE5FP4UR0iItIS1qwTEREREakUa9a9DGsNiYiIiLwHa9aJiIiIiFRK0WT9/PnzmDhxIjp37ow2bdogNjYWS5YsQWlpqdl0hw8fxuDBgxEVFYUnnngC77//Pm7fvm01v9LSUsyePRudOnVCZGQkEhISsH//fk+tDsmI/ccTERGRL1KsGczVq1cxYMAABAUFYciQIahWrRoOHjyIOXPm4Ndff8Xs2bMBANnZ2Rg2bBgefvhhTJs2DVeuXMGKFSuQk5ODRYsWmc1z2rRp2LZtG4YOHYpGjRohIyMDo0ePRmpqKtq2bavEahIRERERuUyxZD0zMxM3b97EmjVr0KxZMwDAwIEDUVJSgm+++QYzZsyAv78/5s6di+DgYKSmpqJy5coAgPr162P69OnYv38/OnToAADIysrCli1bkJSUhGHDhgEA4uLi8OyzzyIlJQVpaWmKrCcRERERkasUawZTVFQEAKhZs6bZ8Fq1aqF8+fLw8/PDrVu3sG/fPsTFxRkTdQDo27cvKlWqhG+//dY4bOvWrfD398eAAQOMwwIDA9G/f38cOnQIubm5Mq8REREREZG0FEvWH330UQDAP/7xD5w8eRJ//PEHNm3aZGy6Uq5cOZw6dQr37t1DRESE2W8DAgLQokULZGdnG4dlZ2ejSZMmZkk9AERGRkKv15tNS0RERESkBYo1g+nUqRNeeeUVLF68GN9//71x+N///neMHz8eAJCXlwcACAkJsfp9SEgIjh49avw7Ly8PderUsTkdANasExEREZHmKNrPev369dG+fXv06NEDwcHB+M9//oP58+ejRo0aGDx4MO7cuQPgQU26pcDAQON4ALhz5w78/f1tTgcAJSUlouOrWbOK6N9IJSQkSLFlq1HKxKeUDkETWG7IFSw35AqWG3IFy414iiXrW7ZswVtvvYWtW7caa8R79uwJvV6PWbNmITY2FhUqVAAAq64cgQfJt2E8AFSoUAF37961OR3wv6RdjPz8W7h/Xy/6d+4KCQlCXl6hx5dL2sZyQ65guSFXsNyQK1hubCtXTuewglixNutr1qxBq1atrJqudO3aFcXFxTh58qSxCYuhOYypvLw81K5d2/h3SEiIzaYuht+aTktEREREpAWKJevXrl1DWVmZ1XBD7XhZWRmaN2+O8uXL49ixY2bTlJaWIjs7Gy1atDAOCw8Px2+//WbsZcbg559/No4nIiIiItISxZL1Jk2a4NixY7h48aLZ8C1btsDPzw9hYWEICgpChw4dkJmZaZaEZ2Zmori4GDExMcZhMTExuHv3LtavX28cVlpaivT0dERHR9t8+ZSIiIge4JeiidRJsTbrI0eOxO7duzF48GC8+OKLqFatGv7zn/9g9+7dGDRokLH/9UmTJmHQoEFITEzEgAEDcOXKFaxcuRKdO3dGx44djfOLiopCTEwMUlJSkJeXh4YNGyIjIwOXL19GcnKyUqtJREREROQynV6v9/wblP+VlZWF+fPnIzs7Gzdu3EBoaCief/55jBw5En5+fsbpDh48iJSUFJw4cQJVqlRBbGwsJk+ejEqVKpnNr6SkBPPmzcPmzZtRUFCAsLAwTJ482SypF4MvmJKWsNyQK1huyMBQqz71xWin07LckCtYbmxz9oKposm62jFZJy1huSFXsNyQAZN1khvLjW2q7Q2GiIiIiIgcY7JORERERKRSin7BlIiIiNRBSPMXIvI81qwTEREREakUk3UiIiIiIpVisk5EREQkEX5ciqTGZJ2IiIiI3MKbFPkwWSciIiIiUikm60REREREKsVknYhIAD7iJSIiJTBZJyIiIiJSKX4UiYiIiEgi/LgUSY3JOhERERG5hTcp8mEzGCIiIiIilWKyTkRERESkUmwGQ0QkAB/xEhGRElizTkRERESkUkzWiYiIiIhUisk6EREZ8eNPRETqwmSdiIiIiEilmKwTEREREakUk3UiIiIiIpVisk5EREREpFJM1omIJMKXM4mISGr8KBIRERnx40+OGW7GuJ2IyFNYs05eiTWcRERE5A2YrJPPsZfIM8G3j9uGiIjUzJuvU0zWiYjI63nzhZyIvBuTdSIiIiIileILpkREEuFLh8rhi58kJ5YvUhKTdSIiIoGYrBGRpzFZJ6/ECyoR+RrW/hJ5Jybr5HPsXch4gbOP20YaTKaIiOThzedVJutEROT1vPlCTkTejb3BEBERERGpFGvWiUhSbOpBSmB5UwdvPf61vj7eul98BWvWiYiIiIhUijXrRERECpGyxpO1pkTeick6EZGHMJlSPzYXICK1YTMYIiIiIiKVYrJORERERKRSbAZDRJJi8wEi38XjX524X7RNVLJ+5MgRrF69GhcuXMCNGzeg1+vNxut0Ovz73/+WNEAiIiIiIl8lOFnfuHEjkpKSUL58eTRu3Bj16tWTMy4iIiKvxxpPInJGcLL+2WefoUmTJli5ciXq1KkjZ0xERESKYPJMRGoj+AXTy5cvY/DgwUzUiYiIiIg8RHCyXrduXZSWlsoZCxERERERmRCcrA8aNAibN29GWVmZnPEQEREREdF/2W2z/tNPP5n9HRERgW3btmHAgAF44YUXUL9+ffj5+Vn97tFHH5U+SpINv9ZHREREpF52k/XExETodDqzYYauGqdPn25znE6nQ3Z2tgxhEhERERH5HrvJenJysifjICIiIiIiC3aT9X79+nkyDiKfwuZHREREJITgF0yTkpLw888/2x2flZWFpKQkSYIiIiIiIiIRyXpGRgYuXrxod3xOTg42btwoSVBERES+bmbaYeNTOCLyXYK/YOpMcXExypeXbHbkIWyGQUREpC1sSulbHGbXly9fxu+//278+9y5c1ZdOgJAQUEB1q5di0aNGokOICsrCwsWLMCRI0dw7949NGjQAMOGDUN8fLxxmh07dmDBggU4c+YMatasif79+2Ps2LFWNwc3b97E7NmzsX37dty5cweRkZFISkpCixYtRMdFRERERKQ0h8l6eno6FixYAJ1OB51Oh0WLFmHRokVW0+n1epQrVw4zZswQtfBdu3Zh/PjxaN++PV555RWUL18e58+fxx9//GE1zeOPP44333wTp0+fxsKFC3H9+nW8+eabxunu37+Pl156CadPn8aIESNQvXp1rFmzBomJiUhPT0fDhg1FxUZEROTLWHtLpA4Ok/Xu3bsjNDQUer0eb7zxBhISEtC2bVuzaXQ6HSpVqoTWrVujXr16ghdcWFiIpKQkDBo0CNOnT7c73axZs9CyZUssX77c+BGmypUrY8mSJUhMTETjxo0BAFu3bsWRI0ewcOFCdO/eHQDQu3dv9OrVCwsWLMCsWbMEx0YkN178iIiISAiHyXp4eDjCw8MBPGgS07NnTzRv3lySBW/evBk3b97EK6+8AgC4desWKleubPaxpTNnzuDMmTN49913zb6W+sILL2DRokXYtm0bXnrpJQDAd999h9q1a6Nbt27G6WrUqIHevXvj66+/xt27d+Hv7y9J7EREpD2sKSYiLRLcG8yECRMkS9QBYP/+/WjatCl27dqFp556Co888gjat2+PlJQUlJWVAQBOnDgBAIiIiDD7bZ06dVC3bl3jeADIzs5Gq1atrL6s2rp1axQVFTnsyYaIiEhtpr4YbffGgj3FEPkOwd23COmWsUKFCvjLX/6Cli1bOu0Z5sKFC7hy5QqmTZuGUaNGoWXLlti5cyeWLl2KkpIS/OMf/0BeXh4AICQkxOr3ISEhyM3NNf6dl5eHxx9/3Gq62rVrAwByc3Px0EMPOV0HX8UaJyIiIm3gtdq3CE7Wp02bZlZrrdfrAcBqmE6nQ3BwMCZNmoSEhAS78ysuLkZBQQGmTJlibMrSs2dPFBcXY+3atXj55Zdx584dAEBAQIDV7wMDA3H79m3j33fu3LE5nWGYYV5i1KxZRfRvpBISEmQ1LOnTPQCA5HGdJF+ef4Cf3eWSdnD/kSt8pdy4e56T8xwslifO2c6W4SvlhqTFciOe4GR95cqVSElJQUFBAQYNGoQmTZoAeNCd4xdffIHq1atjzJgxuHjxItLS0vDWW2+hWrVq6NWrl835VahQAQDw7LPPmg3v06cPtm7dil9++cU4TWlpqdXvS0pKjOMN87M1nWGY6bRC5effwv37etG/c1dISBDy8gqtht8tfdA8yNY4d8k5b7JPyica9soNkSO+VG7cPc+p6TzpiVgmD4iyuwxfKjckHZYb28qV0zmsIBbcZv3QoUMoLS3F5kLPD9QAACAASURBVM2bMWrUKHTr1g3dunXD6NGjkZmZiTt37hi7Tdy0aRNCQ0OxcuVKu/MzNG2pVauW2XDD3wUFBcZpDM1hTOXl5RmbuBjmZ9osxsAwzHRaImdmph3G+I92sU0oERERKUpwsv7VV1+hX79+qFixotW4ypUro1+/ftiwYYPx77i4OJw+fdru/Fq1agUAuHr1qtnwK1euAHjQk4vhY0bHjh0zm+bq1au4cuWK2ceOwsPDcfz4cWPzHIOsrCxUqlSJ/awTEfk4Ry9sEhGpleBkPT8/39hLiy337t3DtWvXjH/Xrl3b4fQxMTEAYEzwgQdt3tevX49KlSqhTZs2aNasGZo2bYovvvjCbF5r165FuXLl0LNnT7P55ebmYseOHcZhf/75J7Zu3Ypu3bqx20YiIvIavPFwH3vU8U1a3O+C26w3btwYGzZswODBg1Glinm7msLCQnz11VfGduwAkJOTg5o1a9qdX0REBOLi4rB48WLk5+ejZcuW2LVrF/bs2YPXXnvNuIzXX38dL7/8MkaOHInY2FicPn0aaWlpGDhwoNnyevXqhTZt2uD11183fsF07dq1uH//Pv72t78J3iC+iid9IiIiIvURnKyPHz8eEydORExMDOLj441fDv3tt9+QkZGB/Px8zJs3DwBw//59bNmyxeprp5bee+891KtXDxs3bsTGjRtRv359vPPOOxg0aJBxmi5dumDBggVYsGAB3nvvPdSoUQMvv/wyxo0bZzYvPz8/LFmyBLNmzUJqaipKSkrQunVrzJw5E40aNRK6mqrGhJp8EbsVJbVgGSQiJQhO1nv16oU5c+YgOTkZS5YsMRsXEhKC2bNnG3t+KSsrw9KlS1GjRg2H8wwICMDEiRMxceJEh9N1794d3bt3dxpjtWrV8MEHH+CDDz5wOi2RGvDiTyQOb96IyNcITtYBIDY2Fr169cLx48eRk5MDAAgNDUVERAT8/PyM0/n7+6Np06bSRkrkQUwEiIiIpGG4yU6Z+JTCkWiTqGQdeNDcJDIyEpGRkXLEQ0RERERE/yU6WQeA27dv48aNG1bdJALAX/7yF7eDIiLfwCYNRKQUnnd8kxb3u+Bk/f79+1i2bBlSU1PNumi0lJ2dLUlgRERERES+TnCynpKSghUrVqBZs2bo1asXgoOD5YyLiDxACzXbao6NiIjUTQvXOWcEJ+ubNm3Ck08+iaVLl8oZDxERkV1avuASEblCcLJ+8+ZNdOvWTc5YiIi8mlZqeLQSJxFJS65jn+cS95QTOmHz5s2Rl5cnZyxERERERC6ZmXbYeMPhTQQn6xMmTMC6devwxx9/yBkPkap564lAKVNfjGaNC5FIPA8R+RbBzWCOHTuGv/zlL4iNjUWPHj1Qv359lCtnnuvrdDqMHz9e8iCJiIiIiGyxvHn1tqZ8gpP1BQsWGP+9adMmm9MwWSdfpsWTg5ZiJVIjLR73RL7EG45Nwcn6jh075IyDiIiIiIgsCE7WQ0ND5YyDiAiAd9dUamWdtBInEUmLx746CX7B1NSFCxdw6NAhFBYWSh0PkepdzC3ky11EREQq462dFohK1nfu3Inu3bsjJiYGQ4YMwbFjxwAA+fn56NGjB7Zu3SpLkERqMfXFaDSsHaR0GFZmph1G0qd7lA6DiDzAWxMSIrJNcLJ+4MABTJgwAdWqVcP48eOh1+uN42rWrImGDRvim2++kSVIIiIi8i3e0kWlt6yHmlnewHrbDa3gNusLFy5EWFgY1q9fj4KCArPeYQCgTZs22Lhxo+QBEmmFN50YiEgYHvdEJDfBNeu//PILnnvuOau+1Q3q1q2La9euSRYYERH5DtY+EhHZJrhmXa/Xw9/f3+7469evOxxP2uHNvXGQ+rHcERER/Y/gmvWmTZvi0KFDdsfv3LkT4eHhkgRFpGZabgvH2ksiIiJtEZys9+/fH9999x3Wr19vfLlUp9Ph9u3beP/993H06FEkJCTIFigR2Tf1xWgkj+ukdBhEREQkMcHNYF544QUcPnwYb775JmbOnAmdTocpU6bgxo0bKCsrQ3x8PJ577jk5YyUiIrKJzfe8j7fsS29ZD1KO4GQdAFJSUtCrVy9s2rQJ586dg16vR2RkJOLi4tCrVy+5YiQiIiIi8kmiknUA6NGjB3r06GE1/OzZszh16hRiY2MlCYyIiHwHax+JvAOfcklPdLJuz7Zt2/DJJ58wWfcCPMCIiIiI1EGyZJ2I1I83YkREymCNM7lKcG8wRCQOu0kkIiIid7FmnYhIRVj75hpuLyLyVqxZJyIiIiJSKdasExEREZEk+JRLeg6T9bZt20Kn0wma0b179yQJiIiIrLF5DBFZ4nnBNzhM1iMiIjwVBxEREZHXYkJNrnKYrKempnoqDiKvwxMzEakRa2OJtIVt1omIVMQ0gWJSRURE7A2GyAPY5zoRERG5gjXrRDJigk5ERFrHp3zKYrJORKQBvEgSkSWeF3wDm8EQ+Sg2zSEiIl+jxWsfa9ZVjI+dtLUN5IhVS+tPRNrA8wmRtjBZJyJSKSZVREQkKlkvKyvD5s2bsWfPHuTn5+O1115Dy5YtUVBQgJ07d6JDhw6oU6eOXLH6NNawahv3G3kazxlERN5BcLJ++/ZtjBgxAkeOHEHFihVx584dFBQUAACqVKmClJQUPP/885g0aZJswRJpDRMlIiLSOl7LlCX4BdP58+fj2LFjWLBgAXbs2AG9Xm8c5+fnh549e2LPnj2yBEnS0OJLFUTejMckEYnBc4ZvElyzvnXrVgwcOBDdu3fH9evXrcY3bNgQ33zzjaTBEZF8PFlTwiYZRATwXEDK02LZE5ys5+bmIiwszO74ihUroqioSJKg6AEtFiipaWkbyBGrltZfCbzwE8ByIAduU+3gvvJ+gpvBBAcH4+rVq3bH//rrr6hdu7YkQRHZw0eA8uL2JSIiUhfBNesdOnRAeno6Ro4caTXu0qVL+Oqrr9C3b19Jg6P/cXbHrNY7a7XGReTthBxzM9MOwz/AD5MHRHkgIiL14rWK1ExwzfqECRNw8+ZN9O/fH2vXroVOp8MPP/yAOXPmID4+HgEBARgzZoycsZIPYM0u+Sqly77SyyciItsE16w3atQIq1atwhtvvIFPPvkEALBixQoAQLNmzTB79mzUq1dPnihJEpY1BqxJIFIWjz33zUw7jIu5hWhYO0jpUHhOJdlJUbZYTrVH1EeRIiIisGnTJpw+fRpnz56FXq9H48aN0bJlS7niIyIN40VBvQxJ7kP1g43/Ngzn/iK5sGwRiScqWTdo3rw5mjdvLnUsZAOTHSL7eFz8jy+fKxrWDtLEemtpH2khRnqA+8r7CU7W9+/fj3379mHKlCk2x8+ZMwdPPPEEHn/8ccmCI22S84LEk5K81LJ9tZTUEJFn8fxAvkZwsr506VJUqVLF7vicnBwsXbqUybpC1HrSUmtcRPSgRjp5XCe8Om+X0qG4zRcTOF9cZ7lwG5KaCU7WT548iVGjRtkdHxUVhWXLlkkSFPkud06YvHCRlildbtXwgiYREVkTnKwXFhaiYsWKdscHBgaioKBAkqDIM5RODtSEib734r71bob9qoZuJ1nGSAtYTrVHcLJep04dHD9+3O7448ePIyQkxK1gli5dipSUFISHhyMzM9Ns3OHDhzF79mycOHECVapUQe/evTFlyhSrG4jS0lJ8/PHHyMzMxM2bNxEeHo5JkyahQ4cObsVGROLxouA6uW8yTOfL/UTehjfp5E0EJ+tPP/001q1bh9jYWHTs2NFs3P79+7Fx40b079/f5UDy8vLw2WefoVKlSlbjsrOzMWzYMDz88MOYNm0arly5ghUrViAnJweLFi0ym3batGnYtm0bhg4dikaNGiEjIwOjR49Gamoq2rZt63J8SuGJhoiEUOpcYS8pYrJkjduCiFwhOFkfO3YsvvvuO4wcORKdO3dGeHg4gAdt2Xfv3o1atWph3LhxLgcyZ84cREREQK/X4+bNm2bj5s6di+DgYKSmpqJy5coAgPr162P69OnYv3+/sdY8KysLW7ZsQVJSEoYNGwYAiIuLw7PPPouUlBSkpaW5HB8JxwsSuYtliJTi7TcZrq6fmraLGmKQkpq2rZS8db2UUE7ohLVq1cK6devQqVMn7N69G4sXL8bixYuxe/dudO7cGWvXrkXt2rVdCiIrKwubNm1CUlKS1bhbt25h3759iIuLMybqANC3b19UqlQJ3377rXHY1q1b4e/vjwEDBhiHBQYGon///jh06BByc3Ndis8b8dPiRORNpr4Y7XNJgZh1Hv/RLoz/SPu9/pB3Yk7imKiPIoWGhmLp0qUoKCjAhQsXAACNGjVCtWrVXA5Ar9fjvffeQ1xcHFq0aGE1/tSpU7h37x4iIiLMhgcEBKBFixbIzs42DsvOzkaTJk3MknoAiIyMhF6vR3Z2tss3FKR+vnahVhvWohAREUnPpS+YVqtWDZGRkZIEsHHjRpw5cwYLFy60OT4vLw8AbL68GhISgqNHj5pNW6dOHZvTAWDNOtlNKJlgei9v3rdK3SDxxswxbh8ikpLoZP327dv4/fffcePGDej1eqvxjz76qOB53bp1C3PmzMFLL71kt8b7zp07AB7UpFsKDAw0jjdM6+/vb3M6ACgpKREcGwDUrGn/I1ByCwmRt89j/wA/jyxHCUmf7gEAJI/rZDXOm9cbkGe9HG1PU96+be0Run3ESpn4lNNpbG1zV+IRu89Ml2tvvytVHtzdH1LErcZjQafTAXA9Nlu/EzMPuY4Te4QcP2qhxvIiBXvrZWs9vXUbSEVwsn779m0kJycjPT0dZWVlVuP1ej10Op1ZsxRnPvvsM/j7+2P48OF2p6lQoQKAB10yWiopKTGON0x79+5dm9MB/0vahcrPv4X7961vSOQWEhKEvLxCWZdxt/TBPpR7OUpwtG7evN5ylRuh28ybt60jSq63rWWLjceVcmO6jMkDomwuz95wubm7P6TYn2o8FgyVa67GZvk7seVGjdtELbx129haL3vlxlu3gVDlyukcVhALTtY/+OADbNiwAU899RQef/xxBAcHuxVYbm4uPv/8c7zyyiu4du2acXhJSQnu3r2LnJwcBAUFGZuwGJrDmMrLyzOrkQ8JCbHZ1MXwW7ZXJ+IjenLfxVzPX1A9VW69/bhwdf28fbsoSQ3bVo7ja+qL0cYXR9WwjlomOFnfvn07nnnmGcyZM0eSBefn5+Pu3btISUlBSkqK1fhu3bph9OjRGDNmDMqXL49jx46hZ8+exvGlpaXIzs5Gnz59jMPCw8ORmpqKoqIis5dMf/75Z+N4eoAHjndTS0KuljiIfN3CSdppFkLyMvQKpKYywWuEY4KT9dLSUjz22GOSLbh+/fo2XyqdN28eiouL8cYbb6Bx48YICgpChw4dkJmZiTFjxhiT8MzMTBQXFyMmJsb425iYGKxYsQLr16839rNeWlqK9PR0REdH23z5lEhNtJzcajFm8j1aPsakxO1ApB2Ck/WIiAicP39esgUHBQWhe/fuVsM///xz+Pn5mY2bNGkSBg0ahMTERAwYMABXrlzBypUr0blzZ7OvqUZFRSEmJgYpKSnIy8tDw4YNkZGRgcuXLyM5OVmy2Em7eGGyjRdubVJqfzWszZfAHNHyB4eISH0EJ+tTpkzB2LFj0bt3b7Ru3VrOmKy0atUKK1euREpKCpKTk1GlShUkJCRg8uTJVtPOmjUL8+bNQ2ZmJgoKChAWFoYlS5bgkUce8WjM3kINFxGxMZhOp4b4tY7bzjFPbR+hZdnX95dW1t/T5yaxy5M6Pmfz4bnaOynxfos3Epysf/HFF6hbty4GDhyINm3aoEGDBihXzvwDqDqdDjNmzHAroNTUVJvD27Vrh3Xr1jn9fWBgIKZOnYqpU6e6FQepl6+f1H19/YmE4HHiGn5Fkkh9BCfrGRkZxn8fPnwYhw9bH9BSJOtEJC8mL+QuJcqQ2sotbwbIm8hVjtlkThqCk/WTJ0/KGQeRV1H6Qu7LCYTS256kxy+1EklHTb3AkDCiv2BK3oEXIXXi/iCSl68fY9567vfW9dICbnv5iU7Wi4uLcfToUVy7dg0dO3ZErVq15IiLZKCGA0oNMZA1b98frpY7llff5qmX41i+5MXjmExpsTyIStbXrFmDuXPn4tatW9DpdFixYgVq1aqF/Px8PP3003jzzTeRkJAgV6ykADUUZndiUDp+rZ0UtBavFrm6jb2tNw2txSs1T6+3YXlCXyD1ZHy+WhbkWm81bU81xOANBCfr3333Hd59911069YNXbp0wfTp043jatasiSeffBL//ve/mayT7LR88EtxEpVz/ZXuZktNFxm5KL2NfYU3lyE5ubPdPHn8Wi7LE8eVL5yfSJ0EJ+vLly/HY489hoULF+L69etmyTrw4KNJ69evlzxAIiLSJm9Obry5NlQoNcTMribdp4b9SI4JTtZPnz6NV1991e74kJAQ5OfnSxIUqR8PbsfEPnL2Vuzij6TAL7WS1vGaSe4QnKyXK1cO9+/ftzs+NzcXFStWlCQoco2Yk4GvnTCUfMHwYm4hZqYdlnSbK3ni50WHnPH1m1Q1c+W41cIxzxsr98n1Pg25T3CyHh4ejj179mDo0KFW4+7fv4+tW7eidevWkgZHws1MO4yLuYUOT1hSHFDuXoTtxaD2i4Ha45OTN6y7q7HLuc7esF1doaVEXivtt4VQWzye5IvrTPZpsTwITtaHDBmCyZMnY968eYiLiwMA6PV6nDt3Dh999BHOnDnjsJkMkS+a+mK0ppIT1k7JT65trLULkNbiVZK3J9reul7OyLXevro9vZngZD02NhanTp3CokWLsGTJEgDAqFGjoNfrodfrMWHCBDz1FL+KRZ6jxQuY2mNVulmN2rePFPg+g2do8fygdZZlW85t78llWS6TyNNE9bM+adIk9OzZE5s3b8a5c+eg1+vRqFEj9O3bl01gVIgXKxKLZYakxHIknBa3lasxS3me0eJ2UxtWIKif6C+YtmrVCq1atZIjFtIQbzlBMjl1zNm7ENx+3sGV/ch9rww5tjv3pfy4bckdopN1Uq+GtYM0d0Lw1J28uy8YuhOnHPtEyf2stTJGnscy4l3UsD95QyE/V7bt+I92AQAWTmIzaDkJTtaTkpKcTqPT6TBjxgy3AiLXeOoE5qsvxKg9Pjmp+SZQyxdwLcYsBbnWW22fblfb/lVbPL5Ey+cpe9hkxrMEJ+sZGRlOp2GyLh1vPLiJSNvUdF5SUyxy84V1VAtn5UpIufOGsukN6yCG2tdXcLJ+8uRJq2FlZWW4dOkSVqxYgdOnT2PZsmWSBkfkiFoPKld5+mShlpOT0ssn78RypRxue1IjtVzzXOFWm3U/Pz80btwY7777LsaOHYvZs2fjnXfekSo2skNogdNigfRFanqcyDKjfVq+IElBzvVXatt62z71lvUgdfC248MWyV4wffLJJ7FgwQIm66Qp3nxwS8Gbbgh94YTuKle2CbejMrzthXUick6yZP3GjRsoLi6WanYkA3eTFTmSHV4kiBxz5bi7mFuImWmHeXy5QU1PvIjXCrViLzCe4XayfvPmTezbtw+ff/45+18n8hBfecnJGS2smy/sBzWQ68MuWtlvLGeeI/Zm2Bv3iTetk7PviaiB4GQ9PDwcOp3O5ji9Xo9q1aph2rRpkgXm6/hxEu/hzfvHdN28eT1d5emPShmWJxc17Vs1xeLr7JVjLZ4ThDT9c3ZDqKX1tccb1kEMNXdRDIhI1uPi4mwm68HBwWjcuDGeeeYZVKlSRdLgyDO0eEL1Rp7e/u4uT47aCJZF8gVaKOdaiJHk5cky4IllabksC07WP/zwQznjIBG0XODImtj9KdcjO16c1U3o/lHzo1y5udtHtrPxSjU7k2KeYuJzdI4xzCdlojRtlXneIXe5Una0Vu4ke8GUiLTJ0SNdqU5oajgxauWkTCQnNRyLclFy3bx5u5LyBCfrP/30k0sLePTRR136Hf2PVCcBd+8+lTwJecOJUOw6eMM6k/tceXFSaO0p8KCGlGXNGreFe5R8ac902dyP2sPzkTXByXpiYqLdF0xt0ev10Ol0yM7OdikwEkbsCZEHgXcQchFSeh+zrD3AhEGdvK18Sr0eJaVldl9WvphbiKRP92DygCiX56FlcpUZbyuTzqhlfZVevhCCk/UZM2Zg9erV+O2339CnTx88/PDDAIAzZ87g66+/RuPGjTFkyBBRCT1Jw91kwBtPplJy94QiV5dyamBa9iy3j9rKlRIXBkdto4XW/Eldo26L2vaV1mih6zc52St3gQF+PrtNiKQkOFkvLCzEn3/+ia1bt6JOnTpm48aNG4eBAweiqKgIiYmJkgfp6+S+kPJkSq5Q64t0aqWWWiQSTq59poUywETbPssbaC3sT1dIvV4z0w7DP8DP5hMZb92GUhGcrKelpWHgwIFWiToA1K1bFwMHDsTq1auZrBPBcz1DSLkcniytqSnBNvTvrMSXSdW0HRxxt2mYO+sn5imJKz1A2fqdmPmJecLnqC9xIf2MiyHVtiDf5Gp50Fr5EZys//HHH6hYsaLd8ZUqVcIff/whSVBkn1ZOVFqJ01c42h+O9pFUXdX5Qtda5D28scmagTd/9VjJJoda3WamtL7/vZngZL1+/frYtGkTBg8ejMDAQLNxJSUl2LhxI0JDQyUPkJRtpuJqkiV1+01X+0VWEynv/L05mfAVSr98Z1q+1NjcQe5j2xfa6dvahp46Z0pdAy922WIocR1R6trlieVK9Z4X/Y/gZH348OH45z//if79++OFF15AkyZNAADnzp3DmjVrcPbsWbzzzjuyBUq2iSnUjg6gi7mFijxel4orJwctJfpaZJkAcnuTu6QsQ2q8QVETZ0/cQkKCkJfn+IZHLce6Vs49crQRdzRfodvFl9/dUAvByXpCQgKKi4vx8ccf45133jH2+qLX61GhQgW8/vrrSEhIkC1Qko+SNSBykPrEokStlBSUjlVt3ZupaZ+JOeY8Ebdab3JdqURQU68/Yih9vHorX++px1NYfuUl6gumw4YNw/PPP48ffvgBOTk5AIAGDRrgiSeeQNWqVWUJkMwLvy88unWEJwQSSq6y4g03CySMmpsKkHL4YTvXCH0iQ9ZEJesAEBQUhNjYWDliIRJM7U8CPHVydnc5vn4xcbb+atsuSr27obbtYI/QWlSlalttfYtAyJMDrZRPT9DiOvv6edaSJ3ox87ZtLjpZz8nJwf79+3Ht2jX06dMH9evXR2lpKa5du4ZatWohICBAjjjpv2xdXNRYKPnVRnXRYp/oUr4kpsZjRElSbA9v3qbeuE5CaOllR28pf2paDzXEICWtv4tnSlSyPnv2bKxatQplZWXQ6XRo06aNMVl/5pln8Morr2DYsGEyhUpaoURbUbXWtI//aBcAYOGkpySdr1qadsi9TDVdyKTmjeskJTHt+l05/n2hQsFRV62ePLbUfhwrEZehfLv7hEfstpV7XbVQrtReHm0RnKyvW7cOy5cvR2JiIrp06YIRI0YYx1WpUgVdu3bFzp07may7ydEXvtzlan/aWuBK/GpbZ7lPIEqfoNS2vS0pvX3k5C3rpvX4PcVb9rdQpkmvrXVW8sbM8J6ZkIRczs4RXBkvZjox60niCU7W16xZgx49euAf//gHrl+/bjU+LCwMP/30k6TBkXt87YRtIOf6Kr0tHfWbnDLRvPZejbFKQen18gQ19DFuLwZ3nmaJWS9Xt4FWa8x9pe2tp6ntaaE3MV1fLSXpWuyoQ3Cyfv78eQwePNju+OrVq9tM4klaan605Alqb/ZC6iH3y5ZqPU6kjkvt7YodNSVQ6z4CvK/LXF9lr4wZhjesHSR5cujqd0UcPX1wJQZ2iek5gpP1wMBA3L592+74y5cvs/tG8hi+RCgNX7n5sXex9PWyImezOzExANJ0h6eWdruAsPXy9fJnyVvP4Vp92uMKITcmrm4LMeXD226GBSfrkZGR2L59u1lbdYOSkhJkZmYiOto3CqPa2Luj9xSpTrCeOlF76wXB1znan558gUsJYmvupKgNU/qG2ZsuxL7KnXKi1uPR0AOJUGpP5LVw/rNHzuZ2niY4WR85ciRGjhyJ1157Dc8//zwA4Nq1a/jhhx8wf/58XL16FXPmzJEtUCJ7TE+MauuqSWwvMErFr0SPLEJrR4TQyglXKKHJt+FRdElpGQID/GSOSpzxH+0yxiV3mVZ7wqNGzraXJ/rCloPazwWm8dmKUew1QMkXZ0tKy6yGe7JZjKvrrsWmO4KT9Y4dO+Ltt9/GBx98gK+//hoA8PrrrwMA/P398d5776Ft27byROlDpr7IL3xZUvvJVypyP7aTIyFX476R8gujamqXablehtiE8NYehmxx9BK2muKUk6+sp4Gtfa0WYvaFUk03pDg+fKVJpVJE9bM+cOBAdO3aFVu3bsW5c+eg1+vRuHFj9O7dG3Xq1JErRnKRt1+sfOGkYLnf3Gmn6+oyXaX2sqbmY0LMzUFJaRnu68XNX8iFVejFV0xNoNjEhZw3c1T7dlLzceaMK32YC7kuqe0JsIHY9Q0M8FPdOgihxZhFf8E0JCQEiYmJcsRCEnLnZGA44ajxZKIWWroAaSlWLZGzttqd2nxPN1cqKS0znm8s4w4M8JPlqYRpn86WlRKmMShR2zcz7TB+zbkBAGhWP1jU7wDvOk7FlmU1dqnn7FoqdrhQUrxI7cpvhOYOanja6EtEJ+sG9+7dQ1ZWFq5evYqHH34YzZo1kzIucoO9tmRqIseFydve/vYkMW2kAe0lFFqLV6xyOtcuns6a3bnTPEpoO3pXmiuJaQKkFK3UOqrpmHY1AVS6cwI1bUOpiT3O5NwG3rh9hXKYrB84cADbt2/Hyy+/jJo1axqHX7p0CePHj8evv/5qHBYXF4fk5GT5IiXB7PXrKtejN6nmJ+eB9pCuqgAAIABJREFU6OylHiJ7tPDyopSJoTuJh2FbeeKmWQv7hYST8v0QJZuZeFuZ9PYadK3sL4fJekZGBo4cOYLp06ebDU9KSsLp06cRHR2NqKgo7NmzBxs3bkT79u3Rr18/WQMmsmR6sKm1/bZQjh7pK0ULJzMtxCiG0ETUXtlQQ7vmZvWDvW6/+BKt7jtnN4vuPC2S4nzsLD6tvKip1fKhVQ6T9aysLHTq1Mls2NmzZ3Hw4EE8+uijSE1NBQC88soriIuLw8aNG5msS8ibH62Jofb11+J+soxZyvbRSm8PRy9Wu/LCmDNSrK8rH9BRw0V96ovRGP/RLsWWb4utduyAOo9PNcSmhuZEWmjW5M3UcC7xFDUcc65wmKxfu3YNjRo1Mhv2448/QqfToX///sZhFSpUwLPPPovVq1fLE6WPSfp0D+7aaXPuTrd03nYgunKwae1AlfpRv5AyoMbtKtc7DmqJxR324jB9CdOUq58qt/cbKZ/8qG3biiU26XQlQVVi20jRNEqL5LpueqrJp1hSra/YJ3tqOO7VEIMjDpP10tJSVKhQwWzYL7/8AgBo37692fB69erh1q1bEodHrhJzgrRVSNVaYNVCikTPUycHKefP2i95qf2CYYua2gXbqlH3NFeTU298aVFs7EK2ndQ3m844q3WWq7miGva7WppiGmIxZW/7eMNxY4vDZL1evXpmL5ECwKFDh1CzZk3Uq1fPbPidO3cQFKT8DiVt3J1624EkhtjPUbvLlSYW9hheXvbky1tquWCo5cmUJy9Grj4e9/bj2919oJayBEjz5EVpcsRqazvYu5nQ8tMDZ+ReNznO75bXKC2WaUsOk/V27dohMzMTAwYMQPPmzbF9+3ZcuHDBZrv0U6dOifowUlZWFjIyMnDgwAFcvnwZwcHBaNu2LSZOnGjV9Obw4cOYPXs2Tpw4gSpVqqB3796YMmUKKlasaDZdaWkpPv74Y2RmZuLmzZsIDw/HpEmT0KFDB8FxeTNPFdSLuYUY/9EuyQ5ytX5dzXRejhJYW/Hba6KgFmo4uakpoRFCDS91SsFTtdPulDGpu9DzdHn35SdU9ra1lEmhVo89e9RwPhZLzDXO8K0GKefpbRwm6y+99BI2b96Mvn37Ijg4GDdu3IC/vz9GjBhhNl1ZWRm+//579OrVS/CCly1bhsOHDyMmJgZhYWHIy8tDWloa4uLisGHDBjz00EMAgOzsbAwbNgwPP/wwpk2bhitXrmDFihXIycnBokWLzOY5bdo0bNu2DUOHDkWjRo2QkZGB0aNHIzU1FW3bthUcG7lG7peElDhhKXlylKNnGyE1GGqpyfYEKcqUEhcQezeHQptZmT7duZR3Cw1CqmgqEVADsU+YtJhwSUktN9+ubn9395uv73+1Uku5dMZhst6gQQOkpqZi4cKFuHDhAiIjI/Hyyy9bfQDpwIEDqF69Orp16yZ4wcOGDUNKSgoCAgKMw2JjY9GnTx8sXboUH374IQBg7ty5CA4ORmpqKipXrgwAqF+/PqZPn479+/cba82zsrKwZcsWJCUlYdiwYQAe9P3+7LPPIiUlBWlpaYJjUwtHL45p8euiWngJ0ZV5iHkpx/DBKiEfi5GTnI8H1VQu7fWg4gp7SbkUSbqYJz9a+OiZmniqbbMr1HBDrIbjVQ0x+CJPlnfDslImPmU2/GJuIe7rZV+8kVbLmtMvmLZu3dqqBttSx44dsXnzZlELjo623mCNGzdGs2bNcPbsWQDArVu3sG/fPowcOdKYqANA3759MWPGDHz77bfGZH3r1q3w9/fHgAEDjNMFBgaif//++Oijj5Cbm4vatWuLilGNvLFXF0/ypjZsrhDzqFnMTaHcPcioqU2o2N5XbPFE+XP0EqZa26CrqfmKqzfuYqilTDujlThJHftKbAcKhi8wK3HzYKCG7eaI02Tdk/R6Pa5du4bw8HAAD9rB37t3DxEREWbTBQQEoEWLFsjOzjYOy87ORpMmTcySegCIjIyEXq9Hdna2VyTrclB7IdUyyyYlpl+XFZqAqunGwjLRUzI2octW0/ZzRgsxyt0uXKr95ervPf0CuD1C33/xNa5UuChxUywVd5olunvDKcWTSKkIvQHw1gpNVSXrmzZtwtWrVzFp0iQAQF5eHgAgJCTEatqQkBAcPXrU+HdeXp7NF1wNv83NzZUjZMUp0RWgPaZJqJQHqhpfKnHnBCrVeojteUeqE5iny5e9dtlys9y+SpU/W3E4Or6kfsHbU9RygTW87Obu/vZE3/Te3oxNCMttoERzSKl6B9LatpeC1PmCLd6wXVWTrJ89exbvvvsuHnnkEfTt2xfAg+4gAZi1azcIDAw0jjdM6+/vb3M6ACgpKREdU82aVUT/Rir+AX4ICbF9Qvf/b3vnkJAg+Af44dzvBZi7/mez4WIlfboHAJA8rpOTKe3T6XQArNukGbgan2G+zn4vZv72phU6D/8APzxUP9i4vRyt80P1gwHAbB8Zfidku4uJ1VHctqa3N8wQs615msZ8Ke+W0+WKicd0/s7W2158QpcjdpyzeAzbTMgx5E5Z9Q/wg06ns3mOMIwz/NvZsWL6t9DtYzlM6LnD8neWx4y9/Wpr/obfGsbZm6cle7Fazs+wfU3nbRmrvX1guT62yo+jOB1tT6Fl0nIeUpzfbRFz3Fue+9xluPYBQNPQak63idh5C51H0qd7cCnvllkMtra3O+ch02uNGM6OVSm2lT2G86HlfrFcnun6WR7PljE7O75N5wk8uOYafmtvGlsxqZEqkvW8vDyMGTMG1apVw8cff4xy5coBgPGDTKWlpVa/KSkpMftgU4UKFXD37l2b0wH/S9rFyM+/hfuefPMBD+6wDb0z5OUVmg0HHtwhGr5umpdXiLulZdDr9TibcwPAg7tU098JZZjnq/N2GZcjVoOQKsa4HC3DUXy2ahj0+gf7YPKAKOPvbU0nZP6m017MLTSur2FeQuchdHvZ+xKtYf5ClmdvGsvhc9f/jLulZXafsphuP0fzNkxnmIej5Rr2jTtlzt78DcSOF7ocwPY2sfc7e/Nxtr3ExiQkjgYhVTB5QJTNWMZ/tAslpWW4W1pmd/6GmIEHF6m8vEK728BwnBjKktDtImRettbTwDA/w7lNyD5yxtG8TOen1+sdztvRPrAXm9Dzn6FW33I6W+OEnhvEbichDOVGKEOZc+caY2DZ85hpWXdnXS2f7gg9Pg3lxVEMYs41QscJic30t+6Wi/EfPdh3Cyc5T5rtLctyeabT2To+XVl/IdcIwzSGcijlseGKcuV0DiuIFU/WCwsLMXr0aBQWFmLt2rVmTV4M/zY0hzGVl5dn1gY9JCTEZlMXw2+12l7d1qNh08d9WuqvV0hbVXceP0vRFlbux2WefhznbJ0Nib3UvQt5+rGuUi9s+lp3ogae7JFKip5vnDWxMT33KN1Tk2Wf045id/X8r+ZmF558adjWthXb7NKydyYh1zF7397wdC9vci/LdJ0cXYM8TYvdEyuarJeUlGDs2LE4f/48Vq1ahaZNm5qNb968OcqXL49jx46hZ8+exuGlpaXIzs5Gnz59jMPCw8ORmpqKoqIis5dMf/75Z+N4rWgaWs2s5stAq102qpEUL6Eo2ZZeypONvQu+veRUquV66sUswP4+ElNTZDlvW38LXSdvPoY9mQiq9cVBMceJFhMHrXPl3C937yG3S8rw639rloXEIdXylb5xM12+J48Brb3To1iyXlZWhokTJ+Lo0aP49NNP0aZNG6tpgoKC0KFDB2RmZmLMmDHGJDwzMxPFxcWIiYkxThsTE4MVK1Zg/fr1xn7WS0tLkZ6ejujoaFFfV/UGStRsGhIjNd9QiP3SqLukeLlTrdsSsJ0Eeyr5ELpdtHZSlouUvay4Up5t/c5WTErvK3fKrTvHueVNs615qbUsS33uFFIxZdhPptcdLXL2hNzRNhDy5NSduITMw9503tori1IUS9Y//PBDfP/99+jSpQtu3LiBzMxM47jKlSuje/fuAIBJkyZh0KBBSExMxIABA3DlyhWsXLkSnTt3RseOHY2/iYqKQkxMDFJSUpCXl4eGDRsiIyMDly9fRnJyssfXTw62PslresJS+kQuV3Kmln6rTRlOREIfQ9t6rG2vlxN3k1BvqKlzVCPuqV4elDyWTOMUG4dhmwm9yAp9aUtujuK9r/dcJYBUZcMT52Opj3Fnx4fStbC2GLazO7FZnm/E7rvAAD+3tknD2kGCatXd4ep1Qcx2tZxWima6juZhKzbTYYYnp95AsWT95MmTAICdO3di586dZuNCQ0ONyXqrVq2wcuVKpKSkIDk5GVWqVEFCQgImT55sNc9Zs2Zh3rx5yMzMREFBAcLCwrBkyRI88sgj8q+QgqS4g3W1BljqO2dbNyS2DkRn8UjZjZcY9pZn7wQpRVyGZVq+3e5KMx0hXYGaXsjk2q6Gr7yqKSnQOlcunELOLZbH5685NyRt9x0Y4CfZF1udHQtyNTUUkygFBvi5nYSr8bgRcq0Q+x6Wu+spRTJpa18pXXFmj1rjcsSdY8H0t45yATXehFpSLFlPTU0VPG27du2wbt06p9MFBgZi6tSpmDp1qjuhKWrqi9E237J3dpfozqMyIfMROg93T35SXKhMiXm86MqNh5pOfsnjOhl7yrF8RAyYJwxyxezoYquFE6LYcq7GpxdSb185moWJ4awfZq08LbE87uw1c7HHU+94qKX5mrN5yPFivDsVX3I0+VDbOdPwbo+QuGamHTZWugil9HqqbXubUrw3GHLMUaFRw2N6Kcndxk1om1lvIiQxF3NxNvR8IKQ9qZRPDSxr+oU8AQBsP6mRkmlzKCk/dOOpZkwXcwuR9Okemy+0OyJHUyRX274K2b/OkjsxTxblPmeIeSroagxyxG76VMLd9s5STW/JctuaHmNin6o4eorr7EbC1nCleyES69ecG8aPr9kjdeWbgZDOAwxsfZFYi9d7Jusa4mqhlzNZEVvDKMWFTspaTXe2jdwXPE8tW8wFVcjX5uRKkMXM0xBzM5OPO9kithcYA8uy5+zmRE03hXI//bB1gVbT+nuCmPV0tQkiuc6VbS7Fk1hHhF7PTGOXoschpY9JV98xMNTaC71maqmba1uYrHsRd15Kc5dWLjhqflIh5CVUT7BVEyGGXLUpnmLv5O9KLaCYGnLLbS51+2kx/Uar6WVOd9jaB3IeW/baw9qKwVYvJqa/11LbWqmfirryZE6qbSL3Nracv71rp2m5sRWTofwIidOyL3ghnF3T7+sfVMyopSw6K39SvfeiFCbrKmXr4JTyoJCqhttWmzQlP+4g5QVDaLs8Z9NYjrc1rb1tKZRpcwbLbaH0DZQryzck/FLXhkhR3j2xPT1xs2NrGa5c1D1B6nOJ5TlK6WPEU2w1BxC67mKatgi5STV8adfZ0y93CWkCIXcTTDWw9cK+s30qNk+wnM70psu0I4S7NpJ8R83g7HH2pMB0v3r4Y/SSY7LuA6S8+Fqe0FypRXWUzAtJeh09xrfXtaUlZydmMbWiQr7SJhV7N3G21sfVdrj22mLa2u5yvJBpOi/DBd1WrbNchH6cRGs8kZiqpZbNVXLFr+SL6LaObVuE3Ki5UhFj7xxRUlpmlUA5ilHIOdnd5FLMfIW+v+PN7HWparmvZqb9r5conU4HvV76zNnZNaGczv44Ldy0M1lXmZlph6264Pv/9s49yqrqyMM/aKABbWlNaMwAPQGlW+MDgo/EaETBGCSiEh8EG6IxaHwkS2ViGse4YkYn2oZoDEHjK+ogUXTE1xDfOLgiZpxIAjogEXxAaxDUAI1AN9B3/mDVpW7d2o9z7r3dF1LfWi7pc8/ZZz9r166qvU+hFGPjiq8zS2W1VB2epxs7+aURolwpXbmmJbuJphgCOa1HI0mdprFQFAtf+3eGwpJUqW9sGI7JTfPyrjfNWpijyBS7HLzPkYelVGdo+9jcmmxhX6iHLulGRILf3xkhV7FKq0/BLGa+i+EpLYUnq1hohoKkfaYQYjcxy2e0PqKl5eon8jsqpYbnIxQyOrlpHtoz7nImkfdpvCz07pgNprsDpqzvRhSzU4aEv7Rwp4nzjRUMpaRQAdjZYQMdbQmQbs20k4jWL7RrXIHg7+H/lgvJxobhnXq0oqtNYhU8WlwXK9ba10caG/SjYl1pFGOc+mRKMdNz3Zd0zGgxxr744iTl8PXTkOzkv8XI/lKFnWieOF89yLCEpGEPmvevGCTtH1w2ad4L1yZrCVmdXfA5Rpa7GJZ939ztk+9DBlR3qCIsy961S24dx8zDHflxtWJjyvpuiE/YFEO54xsQtfO8S01aZSVN2E1sOsVCTkZpKea+gaSTmOudheYp1nIF+JX0kBLUnnG7TNszO44sS1oOvrgtpA6K0a6+Z7t2yY3tpDzL/RRaX6DvQGhfUKV/0z2uU3iSjjGfxd1nTGht256qHV152F2sd4VQjLmlI2RsZ+NSKkMfgdO+shrb70rhxSk2ZCmPgZed6kzziHKK+XG1zsCU9V2AWAEmz4yV1+RvlHbSFXUsxUpHSxfIVYBCFq1infAhny3G4Kc8cGWoWJNVmjYo5UTJF3qdsRE5hq5d8kPHVq5pyYuvDcX/1tZURR0NKduIrGxDBlQXVDdpJ9WuXcpHWQqF3YXQQooaG4ZnrcxJ3x1C5s11YofmDYohduHcEUrvlbf+AVtLrPzwDwG62qvYZY1J55Kb52Nz63ZvHLQG9QeSL76FHl/gahvuY+P7KTy12EjveikoVttSWyU56rHcMGW9TCl1RyqGAu2aOIq1WcOllHcUMV6DYn3IglvUpSCJcV/7whlcC5mYOi2GsIwV6trvpdwDQcSEG5Ci0KtyZ3t3ZqhNqSj1h1m4wpVmTBcr7ExTfHzv5BQqi0LjuZT9XbPexspr31hMMxb4WJLplILYGPddTYkrhJB8LWaIKi046DQYiQxriSV2vND732pe5zwooZwxZX0XQ4sP5H9rSIt7IZNdMZSnUobOzLh8hKrwSkITVJJwlGLFUXIlwJVWseJhJTHpaiEGrk+oa/nWFHbNyuGKEe4oawgJ9VIsEOmDUa56Igu+z2KXxDLEQ1jSlkM7tSP0zqTsCpPlroS2EOFWaoL3wxh5p/W50LGzrn6q9Uff3BQKE/G9C3DLJq3M8l4tr1277PR+lbr/8g/NhWRmyDBS6DwVY933zVsxe2Ri8iD7yq72BdikmLJeZmgWUtfu8ULQFLkYoaUhB2whefO9jxRDbdIpBq6FEIUyFCPm2DXZATvKR0JZTg4xExV/hyawi7GYKOT5Qkh7lGIxrUI0OfCJ09VeQDKlmi/4kii7Sdok5p6kYTuF1m/sopgrnK7Y1qRjM7RwkvA8xpY9JF8Bd+hMksVVKb07Ls/p2++vL8kRfPydNOaSboqVyisR6iO8P3CkYhxj8HIZGaQxgF+TeQdKc0qPqx60BUCIYshYMrIlOX2N5sRQPsmaTrRn8k+9ovpN+0XrjsCU9d2IGHdmrJVMTqKhCc1nPUnzWzHoCGudVoaYsAr5G1cAk+B7ptSbadKcfEF5KnW8YyhfbzWvwyU3zw8KZ1e78LqV9eCKiebXQxZ7rW6TeCc40qqeZtGV1kUt6ewPk7hi4H3ElNslL13QgoOUFAkfJxppPG5aX5enmbgWQYC7HmKVydAir2lW7uZun5cpVN5QfkoZ587nYT7OXeM35uQcqmPZBnLOl+nLPUKhjwjxtGK894XUY9JFP79HlsPXR7mBr7FhOM67wb8RtVzp2tkZMMK0tm1PpHg1NgxHbU1VzuYS6uiVPSqCLvaQoOPpAchaD2LztnJNS4d+dIbqo1homyRdNM1aiEtuno9Lbp6f531Iupjg6cRYIuXpHSHXaMjylxSZZm1NVWJXpS9fMUJee17WjfwtpEQPGVCd2uWapg44sX3ZN2knfd+QAdV5m121up9x+QjMuHxEVvbwvFC/7VVZocYq8/fFTvwyhIMUGn6d6lqmS+Vy1WWShWRsnqVsLdbmdFe7+r62K5/zyf3NrduzlkhfP6I+wdNKKue0zd0dTSH5d6WXxisjKYVxi5cvtqxyfBcLn2wrRjtQOtq1XeGUGLOs7wKQCz5JZ3WtgrX4VWmVk0Ih7UY6n2DxubJ9cEtD6B0xeUkq/GK+8EfEtldSN6e8l/rGtMvyLWexrsIk79ZCnqQLX1qVNCuKlq8Yq3OhNM1aqJ7k4Ksjvs+CxpCmVEhLmBbiION7ZR8sdFKWdS9jXfm/k3iFSom08PK+IfPisvJrcawua7I8ZlJDC9EJycIYa6TMYym8S5pMkeVIM8bSegB9ix+XDAB2bEKNsTxrYSqlVPppDk06TrR51dfXZX+TY9tFsY4AlsS+Xz4DpJMpMdECNO59p2fxUFbAvyeoXDFlvcxomrXjC6ZTzhzqvCdGeQ5NFjTg+CRZbp9Y1ya+WOET2vTEKXW4DE3Orn0CfBLTNgIm2ZCbRDCmiU8MvTvNJEmKo2/REgqf4P03tizyAxnac3JS5vslfMeiyk3dvjCVNKS1lJcCV2iJVmZ5hCI9z8eIr7/zPlJsJdc1dmT/CIW++RQaGh++cSLlspanQtte7rsAdNnjCtGR13mdpFkE8NjtYuMa33IMlTo0z0fMO+U+mdC9IUNIUiNcR9eNZgjSQnp8C1NN5mrem1J8MbrYWBjMLgJZoqnz8ZjGJEoAWQRp4IZCbPg9ckBQWIbrbw2yagLxQiImNIdD9dGe8buCi43PjUd5cUG/SY9BKMRGs9JxIVwMAaRtqJTvvOTm+Vi5piVP6PmUSuklITRlqGuXXGtITL9P2m9k2rEhJ7KMrsmU7uELAOnejSkXn7w0a7K8l0JTQrgm46QyRqu3kIIhPRXl4prm7ROqa7q/M5Q9SbFD/0LvKtZCtFQhFkCyOnEtyKQsc4VnpO0HvjEIIGeR55IboTostG8U6vm78tY/ZOcLIC6UNEmcP6VZDuOwmJhlfReAdjNzxTPJ6SAaNOD5Bh7NqkGr1qQx8xqFTmRaKEXIkpxkQ5tmaZbpanWU1HIqLRrcMpC0Tal8K9e04Mpb/xC02MWk77IM8o06HG6ZKxVJToOQccFp+xzvr7x9+YKEW+M0a6PMT5J3c1ztVoqTItLgstKlHfMr17TkfUkVyLfG8z7nqgvXWOYLJprca2vcR3b60neF9PF+43peG2chA4MWHhH7bBroQ1l84/Tg/n3yzst2hWBpyqFcBMm2JFxhIj4PBj9xhT8n+498Xqs/akcqy4zLR+Qomz54PUjl2rdhNySnfXItxmKexIuQxgJP73DhmjP4MzGhaklxlaUU+wGKjSnruzFavCzBY3ZjPvNbDm4i36LBF9+q/V7K2NxQHCyQbwGPQRNwvSrdn1BOWrZShVbwcvryJCfKpPGRSRYL1C9cp8KE3h2qWyorV25iYislsQpBKKYX2DnBu04gSYJrgSpd1fRe8iyl2SOSVOH3LZ41JaWjwx+kF00jFE7DcYVe0TVfW/MFhNaPihmeEhr/Ms5ai+9O+i5X2V2Gh7SEYs5dhGRuoXNumlBHX+ha6N4kVPaoUGVRGtmk9a3Wtu05Cj/3uL/VvK7ooYmlxpT1MqaYcYmx93OLPSkaIUGtxfMCbgHmOw1Cez6EZpkhaCHiii92vcPlipQWLJcg44rZkAHVefsB6Lm3mtfhreZ16hFlchIOtcPb7693htuEvAauiU1aOJN4WEKWZV4+CqWhv6UXhfJG98Seh1uKRSYpkCE3bDEU4lJvlIuh0IVtKEab09q2PXrvjG9/RyyaFZXSkV4Tao+knjSCFMT2zA4ZmLY+6VP3lIZroeFTWGXd+RTpXpUV2fEW48mR7/V5W9K2V9q6i3neJxfThFWG5giedszijC9+tX4YCmud3DQv2/683WO8FoV4KgshqVXfdUQ1RSlwpP5SrmetW8x6GfL2++uDAmFz63anZUAT3i7BKWOBNWhQF9PyKt239G+XoKHjw7Twn6RfWCwEPrDJOr5yTUvWQkvU1uw4oi9N7JwrDpL2DsiYxFJ6PULKeWPD8Dz3NY/55mloE6QU/vS8nMjS1KNrP0Zjw/BsWE3SfQ0zLh/hDcmhdnf97Qpfc7V5CF4vlIbLxS7Dd1yTsxZLXwh8fDbNWph3jCmwU8bw2PWkx/jFxE7Te2dcPiJa4eN9lPJTiMIiT7OR3r5CkYsK6iO8vK6wlFAeXH0r9KxsG34cpCtUJKY+tP6q9YNC+zPVKTf+uGRurJeGywYpJ4Cdcwwvi+sUKp7PmLkwrdItP94k20urY9m/pVGJ+mdMG2nzgG/ca3u6OvtbD2kxZb3MaGwYjsH9+wBwKyi1NVVRCrYvdpnHqdMA1M4djgmRcSHz/1bzurwvh73VvA6Tm+Z5rRcx5ZXwZ1ybItNu0k2LpqhpG+tihZErLMjV7i5h6BOSsdbQtGEOQNymMnmPzHNjw3D1nG/qvy7roqtf+UKuaHHmmphc1t5ibpjkZUyy2OCTIn9GK2/s4pzKzPPki8kltDbk7QbEHa2YFjnWYvqhtgD0WYllHcbsY+D14lKqkn6kSvaRkMyjPGjjjp6XcONFEsXYV3+X3Dwfk5vm5Sl2/FnXu5pm7TghihtUtPaWaWrysNgGIempiRkvcozJPR085E6ba7TxxRXppAs1aSiI0ROaZi3EltZt6m/kZSZk3+NyJjTu+Z683QVT1sscGsxcqZPWzDRwJV0TWARNCjRQuHAkxYj/DSBrOaOJjQuBYn0JEcgXEPxdVEdcYefECl+XJTApIes3/2qfD4q3A/QFWUz98ra+5Ob5wbADSpPqgCYCEpiUB61PSus6kKsIpPE+SAVGtpFMT7Y97zftmdxNur6QHUp/c2tu36Eycu9KrKKaZKEorYdEmqMy+SR75a1/yKYjrZ+hvkF5CrUh75cxVj05HqSSnMbTkgYua30GEMKl8EtAQDBmAAAgAElEQVRlSFtgFcNzyb2Tsp5dVskYeRxz0lcoX64wu1KjLbBkKE7aOcn1LF2jMUTv4gsaKRO5Z0uDywryiMs+E5rTuGWZ+mCsos3zz0nyPAD0rOyW9Zq5PP78PbEy0hVetblVlze87nxe/XLBlPUyh7uLfAOZW8vkBMevkYWBwiko5GBzqx4yELKsx06a0oqnvSPkotIUUT6BSiuqZoGIpRABDvgts9SGvB640sgJWU1ra6qyLn3ukfEROq6T0o0JKSCl2+f5cJUtlEf5DPVT7Tovj2w73of5pBhqX6mY+eo1RpEj+Hh0Kbt8M5TMQ1KFrhiKLX+v1n9dFuMk9ULPU3y7DB+S4UW+9pP5dfVlUqb4PUkt9tzaJ0NNYmSIlM/837HjRobqVPaoyJk7tL0smgId6l8hZa1QuSnfJeUAL0PMQkMLG9Gs89xT5vKc8ZBRHuoX01e4wSu2T/g8e1Q23/sonclN87wLLW7hd3kL5SKe0tMW3nS/XODxeifjFZfdcp7QQpwKlWW1NVXoVan3idDxyp2NKeu7ILGrQBlfyeNC+YkUXNniA5ZbaOi3pJ3Z96XSQhYBrtV8bCyeFgIREmwu65CcUGLriQtu6QHQ0vBNOk2zFuLt99cH30nQB4FcyBj8JMh6itkXIZ+nDbexShNfqLnan9zivF57VVaoG559FlIixgVME5e0+MT005hTQ0JpcYVGhs746kkqM3Iylx45uocrulR2CrGjtDihca4pOa765t6KWEU+BtfiNkmMbVIlwyVDNNkf8rSmCSPkaQNhJaa1bXvWghkj2/lzvrRJrvo8k6RcawvgtMpX0vBPTWl3KYb8He0Zd/iUtlCT7U8bskNldRl9+HOucFHNs0ztVoowk9D4jQ37o3mH5DuXXa5vT4Tmxc7ElPUyhoQsX4WSEPINErmrnFvNl63KjRvnE58UiK6NdNpkJ+MsyX2eZpKgFW7IwhWze94Xl6x9XILgSlaswOf3aZZAXhaa0CjWesiA6px88thDnkfqD9rmwMH9++TsO+BtItuZXKgxFna+sKP8xJ4zDLgt61Io8zpybS50KddA7mTjGyNJJ2JXPclJgysecvJOM7H5+q4rn5qFFnBv3A0hrU1pLPv82dj+5nOLp0XGCQP60a5kzaOFO43lYm3Q1BbdVC984yUh+xmdMEXvpFjlpJsG09QpKeWynLJvcwVw2ap1Ue+RSrdGzGZ6rVxSMZb9MFYmJHn/yjX5Huu3mtdh2aqdBgM+vrX5TlNMeQgr9SUuX6SRg8vf2poq1A+sDp7IRvOS5sl2IftfjAeX8pekH8r7+bjjci6pR5cr9uWIKetlxiU3z8fb76/3bg4B/LHJ2okFST+ipFmvXC5tPki50NAGiwzrkQptr0pdQeETFJVNbpLh+XFNmnJREWMd5WE6XMGm/0ipIqXW1S7y3VQP8t2uetauUxla27bnWNZlmtrm3hgFMq1rn5PUsg7kT4q+etXK1dq2PW/xQ0dkyjSTuqgJvn+AX0ujVNK7fQqfy8LNY6pl/mPjSeWzrnpIohBqcfnk1StWqESMgkz30cKej6HQhE7KFs+vS5bGKL8ur6imBLryFbLWU1vyhT3vI3IRSWlo4U0SnqfrLz4me3/S8S1lAlc+XUqrj5g9Qfx9MSEPfB4JncIiFUYZhifx9TnqI70qK7wnT5E8kH2YYsFD4ZNJw9O0RYPWhlQGni8uvwf375MN3eS6gGyjtIYBX+RBRx0mUQrsnPVdBD7ZcCVLc8vT7z4BGjPhkhLEB7Urrl27Lt9P5y1z6GtwMv2QYAy5Tt9qXpdVCmLObU5qcZTxuz5o8qFykiDj6RDcUuLKH9+Yw+P1aZe9DGGgs535VwjlO8maGIL3McK3j0K7pnlDuBIaq1zGnAjA+7B0H/PySPgpCUmt4i5rWCgG1efmL5Y1mzx0/Pf9HB9p6tplpzLLP6CWNLRAeh+o/WWf4/+m35KUncpFlmZufZYWP3rHeTfMC6Yr42jpHXTWOd9Yz/PO75eGE15mitHXICMAL6N2P9806FLgXX2dtwV9LM81tqhPuH6j8ros5HI8Sc8x3wworc9vNa/Lk1W8n/jKzBcB1E78GEZu7dbmDK2/JoXLfarHkOzVwlK09ufjMwaqa3o26SZ1Hp4E7Kxr7tnjcLl//cXHYO3a/HJxZZ8bJvgHHJOihboCpfkYYqkxy3qZE7IY+Kw5fGWruS6TvIffJ63hJHhWrmnBkAHV2Tg9rnjKycr3LqkQuFbDmneB581XN7GWBbL2Uzli0paQwhxSEOkdrrAkADkLkLTxmLzsXNmQR2dJQrGELmsO7wvSfSnzE5t/rkxz+ILGF6urWaN5CIS2uYzuk94fKhOFMrnCHLhFVqsPDZ8nyjUuYve00D1kIZXI0CwNqr8kbShjz30LJi3eXrME+2QbTfgxp9vwfKVBfv+Cyqd5Lri7npdHy39sfrjMkPKD1zuQf/697x1DBlQX9LEYubimkIPYPkNzWWvb9kQhePRuKbfSePs4Lll33g3zcsJ+qJzyFBdplXbJM/lOajMu52Q5aA7R6kjKDL5YiqGxYbiz3mLDXqgsTbMW5uWf5kqeJrAzltyXviYPK3tUOOPT5abypAuWjsaU9TJkS+s2r2WG4KENLjc+DQT5fynEfR8JIfc85YFPeq7NTXLg8gmdv1sKJ01BoF3lmgCiwU1CkdLmce90MkIoHlKibUiUZSTBwmPLtcnZBbequo4+JHdhyGoSa1WRSjfFvUqlIeS9iHkfLx8XtrwttRAdzXJO4Ud8YnO1J01YlT0qcvpFzCTN8ybzQNe1snPFi1+T9Uj1z5VwzSKpLTZ88kDmHdA/SKVNqiG3ufQMaCET3HLpOgVCIvPCJ1Devq40qO9w2SQ/nsbTp35L7UQLL1L4eVy7LwxF7vvhi3GtjL6wFb4Q5O0tF34uZYVCvlz92mVN5IoSldlnZeX7ZgDgylv/oIYWud7hIuQl86Uh9yFIGaPVl7bo5QuHxobhORuiY0Mn0izwXCGb2jzJ5YtW367f+D4f2ovB+6+sf7pnctO8bB3yeiSDHD3L51y5QbNrl1yjjNy3xeuBpyW9L/y7MBoxHriQYcCl1JcLpqyXKb6ORcKLuz5dJN2kJk+vSPJZbFcspk8Jpefks3Ky1X7n6fJ/a5YGeY+W9/aM34LEN1dqC5FC0SY9nxJFAl1a/GPQFBk+UctNbD43LZ0WkMQC6CMmxKVp1sK8zdLUJ3yKg1R+QvnlsZfaIoxv3OLIutBi8EkBdilyVAd8z4QG5cmlnMSWlyY8zfqm9U2+yHItpHkbaWnwhbSG3A/TNGthnoWYfpOLG1+/TRq/7Aq3cI17qkNuoOBeArkBUB4VyBdyvB5CsdP8eV/Ylba44IsYqjuu6JOyqO3LqK3ZuRHdZcCh+uNl8MWn88WSPL6RL9Do3dKjEGst1RZBVIbNrdvzPtpHxCiIWt+ia5p3zTXO+WJKbkqVce2y7fnf0qDA51ltHpN1KOPyY/Y5rFyzc+Nw06yd33WgvCXdeO/ar+drDzJ4Ub+h+6SMKOeYdlPWdyFocMgBJFezMkxlyIDq7LW7GkeiV2VFTodN2jld1hcugPk75YQbUpBi3XKxSjJf1EjBya0ChaANci1sRJ724Ppgg6wDX9iE3FMgJ3pt7wH9ncb1p1l8fYoi9Vva4KlNXnRfKBSHWz9d7wJy64/6HNWN1r98H32RE6RUZPm7XQvj0AIk5EIO/c5Dp4D8RafcYMnDCmjybG3bnlUaSTbQoo3n3dVnXFZCwhdGxcefpmSHPApaXrS0tfbR5Bl5ZHieKB+8DNyi79onpMk8Xka5SJYnUlCb8T5A/+aGCNmvNaWaj9M04196MAnXRvQZl4/AXY0jnZvUuUdD1kUaNI+YvBYK53OlK/eHSSOJZsDhFntaqNQPrM4ro8uLm8YQlOQUFFkGl/dZ9qUYwwxvS9eCWHoDZD3yssjfpCeMw8eRlCdaPkj+hzyMnYkp62VGbU0VelZ2U4/wAnInXU1h4gMo1qLOOyj9W6ZPrl+alPjEzO+VcWC1NVV5MXZAbmgLoE8s2sChic+n/HAB4bJSyDR8bmRuqZEuP0pPCg4u3EMLApd1KUYxoYlHs7jw3fYUm86VUrLKh+J4SYhrQkwKPs1SrFk8SNHgMZDytJYkglOWnVsxqT/I2HmeP9dHwULw8BBu6eNljEUeL+fCN4FLqyPhWky1Z4Alb3+s3s8/1c6tjz6FmxSOmHKHPAGUJpeD1F+pjEkUO9dmM+7hoHdQvmhcUT2EFpO+hUxonwnvk9yCzcNyeP/gp25p4WX0Xh+a7PH1P5KFK9e0BL/rwOViGgXIJY9dm2mTjGMqM4V0StnM80v16wuJkQY0l9Lb2rY9u5k1jTeWL7KB/EU6QdZnaUl3EbvPJQaaW+WpTyQfuLxxzbuuPMcsMLlXiy8KXaGLvJ1C47szMWW9zFm2ase5rICuZBJvNa/LUSh9m3dCq3V6D7fOycmLu25dbk9KC9hxv7RocEsnV/al5YoEFF8oaJDglQsNTRjIOiQhIBVvgg9iXheyrD6Bx/cNJN3cRG2qWY4lciOjdBvSQovXrZZv/mEkUhx8bm6evoxB5MKSL6akRyjGshaj5FEf5vHhXNnkyrysR6lsSiW/adbCnDbki0LuTXLBY5x9MaiEq064EqS5vmkDlys/fCxzZdCF6zceDuNKg+o45Gbm4VRSEfPB65GfoMKf4yfbcC+g9MBwNOWA0ujaZafyxaG6v+Tm+TkTv1Y3mtXc56HxndQi+znhsoJyowKXado+jdiz3KlPcjnO309yV5PzAPLCWXwyM2ah5vPIyHBSANlY7Rho3MduSI4Jy6F5zmeFpn8nNQZIucnHgTbPSrghJuQFBHaGTmnhOzLv3Ljkk0FkMJR9Wi7qfcg24HlJ4pXoaExZ303QJgG+GY/HeZLiKVeR3BXnOjnB15k1N7hvUcDTktZ634QuLeYuoeWKbXPl3SeAuDLPJ3zfc3KSCi1oaJMLlVFOjNy6E1MufnoAKd5SoeMUeuKDC62OuFfCtfdi5ZodMc9aeIoMbZDx31xwx1qXgNzj1ehZX7/g8dgyf/QfXzzFTuwEVxZdniL5XnoOyFfCuUXLZ6WSk2aSPLvgXh0tnE/LgwZX4rSFs7RI0++0mdS34HcpC7GKEX3gTObf1f/kWJZGBK5EELKP0u9c4dLyTx5T7mnS+i33eMYsjHm+YvqJy9JO41caCbjySG3P2z/mndrclBS+CCMFlEOygAxlsSGa3EukGYBoTpa/ufoUV8J5/9GU8CT1oo0bbizQcI0nKdfI8Mfbl5eX6lO2fZpT0eQcWM4KOseU9TLDJXjIasJd3NrJKVzxA/ItVVxxkZO4fDe3fPJJVX5F0rVBR5ZHLgYkcuKmicL1VTEeV8ufpd38/Bq3tmlKoXStapYeDanw0N++yZ3epVnPfO5In5JR2aMCPSu7BScJl2CSccl8A6T2zpD3hgSwZoXn5/tyq0tI0XDFdVJ+ONpCzVd/9Ds9q5WLrLCu0Crt39TG0lsjlcyQpYrqjPdP8rqRG1/2K58s0WK0fWhKsaZcaGVylVFrSxrzcpJ3Kfb8qFhgh7LMj1qVlnTKjwyH4nH8UtmREzrJEi30gNJctmpdjoJZTDQjSiiEj/LF4YpuTB6lAji4f5+sZ4G8CJQm/U3tKUOzuBFDQoql9DBoso2u8XBAyicPdeFWcB7qycvNlVm5SOF9kfcH154juYgILWRCCifNKyGPrOZ9kF7mkLwFgPqBOw8YcLWRy0AG7Kxr7r2QdcjlgzQuUN75/VoeNLkn4dZ9eg7IX/QmVfo7GlPWyxRNCaeORTvUAeTtBOf4BITPehjq/JQHbsGi5+jfmmJFE5jmBSDFTcb6+fIiFxg06GW5pULtslDK+1xWGzn5031cqaLJP6kA0MJFQsRu3JPviU3fFUpBf9ORV770QuEVod/lQjMtvO2pzrjyI9ubyuUKmyoWPC3pTUlaZtf9XEH1hcKFLJU0EXMrsvb+yh4VzgUdnyhdXy3mUKgJ3yPAF05aKBMQH26m9W15TVvEybpumrUwxxARIwO4cYEUXU1RSRLbKzeq8nyQ19WlDPGyuxZ2Mm5es9rK0AQtfJNbjukewhVux+VFrGWdv0/e77NY++Zh/rtmrXWFs/Aw0lBcPhEKXeXGE7mooXHo8qaFvCeu03o4mlJO6fIFQ3sG6Fmpf4tTGhJ9RjUNku1yPxz9xq325Xriiw9T1suQLa3bVHeVBm3Qcw16UiDpP27JlGnHKgY8L7FxYj602DPfucU8Dy5hLSccF9ySzeuI4LF0ofzwCcR1L7dqADtPVnBtpuXpSGWBBBM9t6V1m6pgxMaB8/f7LPwhKxHvQ/SlR8qLVCAkZBHX6oJ+l67w9kz+UZSaUh6Da18Erx+tX/G2igl/0MrG80DtGvN8rDIvFSGCxwUT1F/4pnKeX21BLfPU2rZz3wJNtNLtroXt8L9l/mWcs8/LQmnz8C5SJmTb8TLQPT6vkdb/fYYTKZ9dsfskr3k/lnUklUWX7Kcyyph6YOeiwmUZBnIVW9m/fUYgl/zTQtpoMUBl4wtnee/m1vz9ARLN+s73F2iLMs0g5FJIpTym8vr6CpcXvn1GcgGVJASJb6h0fTOFL55ci05uGaf/fGEy2uIHyJXDWv3IMRbaGEzpkPzn9Sj7vxxD3END75Nl4p73csWU9TKjtmbHaTCu0A8JTeg02DTXv/xbu0adWBP+pDhT+EuhFkXtHTJf8gQISYzFimKFSejxlTkphNpJADFogpcrxqRQkrVs5ZqWrCWST74u4R2jYLvgAlYqQS4rJu1RIKsErxey2gD5G0I1t7Sc9FwKhXaNW39dC0E5wfaqrMgZBz73LD0PpLOu+Kw7LmXKhbQQclx7RmL6hHa0HqCXt7amCl8Y/Jk85VUSu+iTaKF1rgmeh/Pw/kpQyA//BgC/lxavWtpy8elbbGjWUio7D7OJKS/B643HZEu4bKgfWJ0dr7SI1cJ5XNbSJCSVgbU1Vc4v33JcXkjfIkG+R0tTq4+Yj6aRwkohevI3Qgtxil30c0u2LH9jw/Ds8ckhjyLlie6h8SEX1a5vAABxG+jl+zhUVzKEREvLVRYpk2f/+zf0GyMIzfuu31zeYSmfZYhvOWHK+i5EjLuY3IpJN9OErOouxVLbZMNPGgm5MX3wiYvi833l54peKHb7reZ1OXGlMh0Z58kVBBKQrvenCX2h/6RlkdylrkUFhQ4RvnolwUrlk9YJbnlJGorD0WIrNYVC6weadVpLn+dRg0+uUsHm7tLQme6UF25N1GLCpRIloTakcnErDoVMSWIVKO19WmgUfbmQrNsy5MxVrzx9fnoJKcZSLoVklPatAf5+7nmS/cBXT9p452M1ti+76l16BSiv9H8ZGyvTC8kvDldmaZy4FrC83NQW5M2QXh4uayhP3PLIQxm4p5EvCsgAwT9uw+tD9mfX6TZccZd1FQPf31DI5lHp8eN5TWPI0eBWahkq5coT/78cp6RUapuTuZfWtTCmtPl7qB5cXgi6jxuigPxwJ8ojxzemQsYPei+wI39yf5V8Dw+l0UIK+ZzK006zWbUjMWV9N4N3ft8gdbl8eHjGkAHVOQI/TVhBDEmOXJLxbzw/JGCkcsV/J0JKLXfbE1r5pcud/u3yDPhCdni4AQ9ZkulzJZK3tabguI7hkoqnqz40Cy9NsFyh4Mf3SbTFgQ9eFi1/PCSGtxF3dfKvr2oCmOo8NBnzuNmYUCj5u9wrAezsM5oFN4R08fJ0CfIa0aKVn4KipffGio+xbNW6vH4tLXjaJjCtnDJ93jdilFWfhZPgSh4pyqGwAa3/+bwwNLH7+ghXDLT+T0oQedW08lxy8/zs2dsyv9QOmrWPW4lln6C60BbDcrHEZYGMdXd5U1rbtjvPWddCyHg98fxz5Hta27Z7lTIeXiHlKv/mhfZuno7PIsyRMfSuttdCbXxhHiEDlOYp4+Fl/BAJbmGnBbs2l0hjTNJFiSyzK7Q2tEDlcl7rZ9QX+QJSeqZCedfkAqVHcwUtMIu1OCsFpqyXGY0NwzG4fx/1t9qaqqyFuT2TewY7Qcos76CalVMqYFIIScsOV4Jj0VyHfCXPXYWu5wH38XiUby6U+X8xVrkk8EXA5KZ5eZsetff5FiJ8UeCbMKTiSu3OJwutXaSrn4RTksVWSKEkCytfZAC5ngjKS4zb2xdLSf1fu4en7Qohkc+ElDDyUHF3O1e4XSFnPH/Saux6J40D38QmJzRuDePIenYtSmQd8Oe0/iVDybgCwmWNLxzItyiMVehdoQ20MOULVBnjLnF5/jikxHJZ45OFJIN5qIMrTMG3N0TKX5knl7XaJ3d8CjKNI99Y5+/Y0rot7x7pQaO887xqXpUkSCVZGjLI4yMXtHLxyeGhfu0ZPZyUt5UWLsHbhGSGphjLfjBkQHVWjvKQErn44uXke3S4RdhnNJHQXOBSZOW9vrlA3u9blI2/aq76vOaV4u2i3Ruz+Ofy2/VMsQ2QpcCU9TKjadZC1WLBB/qQAdWoH6hbxjVhHaOkuqxO8mMnUtGXFg6eHrmrXANKs0qncUEmsdrFIAUlj23nyq72lVmuoHIFhYRx0nz48uV7zuXSo0WYDJ/huISxVIqB/E1XhAyxCFnWNauMhPYfbG7dnucdci1WZH61kA3f5jDXtwY0hZh+C7WRXORpE7pGTBgHXyD7vAc+r5sLrWxy8actBpNarDQvCieJl8ZFzIKOe2qo38V45zRPHlceZT26LL/cO6hBClSMJ8IFyTBKSyq/Wp58luq0aLKUFGQNqXTRCWmagYL/ze/n8jjGkECeKh+0WKH4ea5oUntKpVQe88kX4C4ZzvcVceOUXLj49maErnP4RmDNu6ClEzohjNA8ooSvXajcMmSIQ3WuGVyAnZuWy/WrpRxT1ssY2flo1ezrXHLwuCZfObC0QaENYi48XJsxKC1tJzkXSnRkGcfn9vbdIwUzlVs7J96Fa6EgreeuTYZ8IeMLO/CVw5cnmS8g103In/EpSNwLEbIsynTkhOr60AZfMFKduWJuSfEOuYO1WE9f/9Zcz5oi6VOuuYWWW2eAHf1Ce7+sD5kPaZUNLTKpjeUpIQRZn+TCI6mSDOj7Dfimcq2t6TmCL9C5ZyQtSWK9JW81r8PkpnlqKI5s+9BYo2u+cduegboXht7N+y8ZASQ8f9ygwZ91LYqSWKrlAtnn9UjSX9Mu1khJdXlcYzb+aWE+LpJa9eX3ITSLNF2neUdbVPrqwxW2KNHayzffaOMayJ/3NSNfewbZE9FCp7ZolnF5bdOWXI8MhfrINEJtKfuIa06W3odiGfU6GlPWy4yVa1py3IvUIfng1BTBrl300x7kINUEIKVfCkixle8lgaZZKF0rZO3fIYHL48xDg9Q1OWsxiBpc0GqClP9OdR7Kf0hwF+JGBkrT7j5l33V/yLLR2pZ/bJtcNPks5ITrSLMQPstoTBqxbmKXJdn1nPybPCchi5SGNjGGZIP0MpDVL0aR0NAUZl5OvlCKQT4v8yL7jyYjtA2xofJoHhuSg7Q41TaNx562RQqIKx8+jxHPj8xb6P4YeeQ6XjFWSeILFNeCOG3+Yt5b6HtowSY9qSHDgIYrbDHUXvLr5PRMWiY3zYvq89z4Ru+XRg4JXwBwmR5aFNP/fQYBbpiKJc2c2hGYsl6GcAtJyPXESRpmAeyceJKclMCtzIRPgZWDmAhtCNPu9w0kucqWyktaYZVU+UyTbjFJkq7vFJNiWyBkW/OQlJgJkCPDb1zPyuv0VT0NV3mTbpAM4cur9ltoIaNZx0LjyrfZLeQRkvfzRWfShX/MCVcdhc+6zInZXxBqY9/pTpw0i67Qb0SMJ4HK6VrgFAtuTZX7ImgRJcd7MfMRCjni93FkHcoFnxY26CO0Z4UTan8+r7s8kjEyVEtbQytb7BzPvRKxaAYBXx2RHhWz6ChHTFnfBUjaieWzvHMOGVDtPds7KaTsywEgB6lrU1ghFjht44krj+W4gSSNm7fYcE9GjPCjZwqFYqs1AZ/2iL2YfPkU31iFn7+vVAuuGLjXLWmbJJlwfYqR/C1mMuTU1lRFeUf4+5atit9EpxEbGujLQ6Ht7lKMJaGNoj6ZUYxxWiylWNuMqb0nacy9D21Bpc0bGq6vi2rKH0+b92dtXPr6rTwNjOZI6u9p2iF0wEGhCrpMj3suSQGneSRmbGtexiR6iS+f1B7lqoyHMGW9zNAGV4zA5NZ4eZ3jsh6kEQax7nRX3jR8Ayn2bFqNWLd5R6DFmQOlc7+FJqgYd2MMIcVBO3lCEhtvqsHz6lPIfFbiUpL2gxsxbSAtemkVLPKEAbn1EVs3SdvOtVHX996Q9TFUx766SRIfHxMSUmpi9lsAO+pEHkrQUQtNzRjgWwC7SDM/kaLIZa6rXeR1GlO+8A0A2Y9X0UJSvt9HEpkTc2+xFNs0tGd2hMsU6x081CVETLmpPbT0OtPoEosp62VGKRQGvmkHSKa4FpKfNAMgxrrpUy5dwrVUMflp6sdn0YhNr5hCuVhW2RmXjwhu+OQUopiHSBMiELMgDikcro+rAMmUN186Mj9JJrUYeHq+tIshq0IfWpNjPeadoQ1woTRC8iVJXmKhWPU0m847m0LbhNJwpVOIB4vSDHlWtf0FSTbVpqUUn7gvVR+NIa1sLdV7NQoZ/52JKetlRik6dWtb+jCQYuZHs+4QaZVejZizk4tFsVb9RKyikLQ8rW3bnR9WKSSOkpNmz0RaSm21TLMZGcjNl3bCTUy+Y2OJk6ZbbIoxpuRmxELDLkJ9eciA6uBCTp541VHQmdehfTmhk5N8hJ5Lo+jFtFdIKeXtrh3hmBaebqzXVu6jcfVJCkErJCwrieEsph6KFbZULiTxdMWyq9aPKetlhnr4dPgAACAASURBVE8hSztxtGd2fn2tlNbMEL6zjX0WS7kJTTu+jv5OEnLT0ZA71icstEmDKMS65DoPXb5TI9bSkDausiNIKvCL4b72ndYRSoMfx+h6rhiTmG+DZ9KJstiTaq/KClVxk3Wa5L0x5ynLkCIud11yqhhKfcwmeAq14B6PWMt2TH/kZS+WtVL7CJ+LUsmPJAcMyHC6kGerEEo9V7nGSrHCGynNmD6YxlAR621Ki5bvGZePKNn7CsGU9V2IQkI5+NfRYiiVRSmNcJOb0AqdsItNMS1Qhdzfu2c350auQhTpct6U01n5irVyJYEmPRnP79qMl6Y9Zf/whRiUqr/GtllsGELo41hJkWMlJs1Cla6km4STetl4/LYLqsdihi8CHb8RO8lG3RAuz2Ox5E4pLMc+0oSQxhwvXEj7uhbD9O5SLGgoNFirD9eHuDobU9bLHLlRs35gOheoS1nzxQmWC2m/LtZRQjCJoIq1LqTJ+5bWbQV/PVLDl0ZHTzZp8eW/M07hAdyeIcD9AaRCkQuvkAJXjHcXw0PkOgMdyD25I+bEiST9VW6MLhWFjtPYceh7R5JP1Seh0P05xXhfaFNyMd5R7nTt4p9/YvpgMRcppSb0js6MMkiDKetlhoztk8pEEsU1dJJCr8r8z/t2BOWoRBOumPq0kKVUu+66vxDK6dSbjqKQTbkyRrmcKEX8qUzT1T/T4GoHqezGLo74cyHPkC+MrlDKsX/IMiZdULjGQiEkDZnqyI18rrKFwhLTImP/Zd2QZTfNGE87R8hxX2jahRg5irkhVKN+YHXZbhRNiynrZU6xlQk+SMrx7PG0FGvwd7ayS+dUd7TbmMcuF3sxlTa9mMmgGBbJQp/XFnhpyhxaXKfFF5dezH7mSiut9Sr2Of7eYlvKkvQvrpR1dKx/seaIQvKSpC+ViyIV01+0DwolsdRr57EnSW93RNuD5iJmkSF/6+x5vBTsdsp6W1sbfv7zn+OYY47BoYceirPOOguvvPJKZ2crmsaG4epgd6EN9NjB7/sseSmFqS9tl4LmK1Ohwq6UwtLnvk8DKdbyaD96R9JJm+eN57WYcfh3NY5MlCeitqYqldVceo98ympM+8g0ZP3zD4HwdJOi1WXacajJEE1OxKZVyILL1TZJ8hGapJPkT9ZFsRZEQwbo1jzZH5PI944giYVU1nUp5CbVkTQguOa6Qkjbt31yz6eYAzu85zMuH5FjLCu0DxSrHULyXJ49X4iVP+mzSUOZeP3KvrQrGip3O2V96tSpuO+++3DKKafgqquuQteuXXH++efjz3/+c2dnLTWus4i1CcI3adDvWloaSQaHT+jxd/omhl6VFUEFzSX8KnvEf3DGJUyTDuKQwKLrrq90aptBtbPKed1SWrU1Vdn9C0l2zEvFs7JHBe5qHJndAU9pFWvySDu5Ut3wySH0aXq6Rypj9KXUNEfe8T7hU+x5W9YPrPaeOV+MyU6mJ//m7VdbU+X8WqwrX5LY885jx65rkag9U4hLW6sbXhdUV8VSdmZcPiLbF2IUwdiFiqbwS/mhLUJkX9MU4Bj42JLvTArJuRmXj8jzStEcQAwZUK3KyWIaWOgdMW1VqFEI2Gn1bWwY7tzkqD1H/9ZOK7qrcWSOnPThe2dMGUmWxsgUmbb8t5RVoff6fpMyj9Lnc10xF/0dzW6lrC9evBhz587FD3/4Q/zoRz/C+PHjcd999+Fzn/scpk2b1tnZi+YLgz/jPNVDU6S4gkudtLamKjuAeRp0LxeKpDhKgcUFpRQCrgWCNkFw4UuKA39W3udSbklI8PLwPPmOu6P7fzt1ZLYOunbZUUbKu08hkeUiASnbiepRCkSfkkf/yf0D9GU8yhvV0YzLR6jW3BD0fGhBQhNpKO+y/n0CmH5z7ZFIqjj47q2tqXIq5ryv82uuNCt7VKCxYXhO39TqUKtTbVKV/SLtZMfRlI0YrwTVBZ0ixPtZEuoHVmf/o7zQf3zS1PqEtqDlSkdoTw1/3mW11pQ7khUuS7hUaH1fn+1VWZEzJqn/aXJF9k3qTzI9WQd8caHl1TXeSGbWD6zGXY0js++/q3GkatSJkVm8TqkeZd3zMsh8ufqBVNQJmsvS7K+KUV4Jqid6Rh7mwNuTzwMkp0OKIfVRVxm1etTqi9qQxlwaKzG9j7+Hl9PVdhquEEo5ZqScorrk8zHVpZY+LQ5k+/DFH39/Y8PwbJvRvEnjUs6fZBAgeV+O7FbK+tNPP43u3bvjzDPPzF6rrKzEGWecgddeew1r1qzpxNzFc/3Fx+QMXiDfwkAdsLFhePYMdZeyAexULikt7SxREgJSoNCEIZVuGljSEkJCld7Z2DA8K1gov/xZyjf9JgevDKOgtAiuTPE806D+7dSRWUWC7ucTlXxeUyzpfhKSfFEkFUASDKTUceGq3Uf/kZDgbUnPz7h8RLYuebmpXWprqtCzsltOGaTg54KoskdF1gLM21S2O7dUuxQXrgzQ/WRhpDp2hWGElDLNeiMnTFp0affRGKH65fXN25Fb3l2TBuXHJcw1hZC3u3R70zXeV/nEz3+XdSTzxscu1QOXGXxc0fPSFc8nNHonjRs+3vkCm8Y0QXXsUki4RY5P1jTRxljauFLD5Q1vB/lOrqDy+qB3U3+ifizrktKKsUyTHON1Kn/ni28e+kjtIpVTajuqL/o/3ce9J3SfVo88bzJtUnq4/NP6Gb2H5I3PcyMVWzmPaHC5xvNL9cb/cymWAHLqS17nnjv5bj4v8EUS7zM0rkmu8H6mwecEF7we+Zjn49anTNL7pSJO+ecyhcsDbnjisoOuSTmgGd+onbnsoN/kfE3l4PUh+yuXw7KOpLGjUK+bnGvLlW7hW3Ydli5dikGDBmGPPfbIuX7ooYcik8lg6dKlqKmp6aTcJaOxYTiaZi3McZmF0AZybU2V9wQZ3jnpWTpnVPvb9xvRNGth3upV5ounpQ02+Tzlk79XE8S1NVVYuaYl8aDT8tPYMByTm+ap+ZfvlO0l0yboHp/Sl5bB/ftgq4hZ5/mSQlZrEw4pGfLcWUqT+pWrHPx9My4fkU2nfmB1tp54PugLqLKtNUJfS42pW9mHAeQpSL5n+XPa2NDyQPfIcS3HmKuP8Puob3JC/UpTJgb374MpZw7NK4vsy1p9ueB5cI0hWV807qivyDqib0VQu/D88WuaTHP9zZ/n6fGyam2hyT0J/40vmnh+ednll6Zlnwq90zXWY+D9gss/QB//AHDTw4uwtW17sK5C8EV1CJdsIHmkhUIAuUoqkCs/5FguRGFLWhdyIdc0a2HOfELIOtLaRvZPks+8bWVe+BzqWmC73qeVV0M+27OyGwb23TPnHq0eeHqk28j3yzzTOJLv1v6mvhIz35QDXTKZzC54YqjOySefjH79+uHuu+/Oub58+XJ84xvfwHXXXZdjdQ/x8ccb0d4JB6r27VuFtWuT7WZ2CfLYiX9XxLVQkNeSPC+vd3YdJXl/375V+OEv5wfvT1omn4BOkk4sMelyYc77diF5Cj0bs1BNS2f2s6TyxtUfCiVUB6RgcWW+mIveUrZBbJ/23ZM2fzFzA5Ek7TTzlJa3Uhkv5HuA4smFYrdFofcW4/lSyk5+36q1GzGw756p37MrjfskdO3aBZ/5zJ7O33crZf2EE07A/vvvj9/85jc511etWoUTTjgBV199NSZOnNhJuSstV976BwA7QmhirhtxdHb9dfb7DcPYfTH50rFYfRtp2a2U9X9ky7phWL8x0mD9xkiD9RsjDdZvdEKW9d1qg2nfvn3VTaRr164FgF0mXt0wDMMwDMMwgN1MWT/ggAPwzjvv4NNPP825vmjRouzvhmEYhmEYhrGrsFsp66NHj8bWrVvx8MMPZ6+1tbVhzpw5GD58OPr169eJuTMMwzAMwzCMZOxWRzcOHToUo0ePxrRp07B27VrU1tbi0UcfxQcffIDrr7++s7NnGIZhGIZhGInYrZR1ALjxxhvxy1/+Eo8//jjWr1+P+vp63HHHHTjssMM6O2uGYRiGYRiGkYjd6jSYYmOnwRi7EtZvjDRYvzHSYP3GSIP1G51/qNNgDMMwDMMwDGN3wpR1wzAMwzAMwyhTTFk3DMMwDMMwjDLFlHXDMAzDMAzDKFN2u9NgiknXrl3+Id9t7LpYvzHSYP3GSIP1GyMN1m/yCdWJnQZjGIZhGIZhGGWKhcEYhmEYhmEYRpliyrphGIZhGIZhlCmmrBuGYRiGYRhGmWLKumEYhmEYhmGUKaasG4ZhGIZhGEaZYsq6YRiGYRiGYZQppqwbhmEYhmEYRpliyrphGIZhGIZhlCmmrBuGYRiGYRhGmWLKumEYhmEYhmGUKaaslwltbW34+c9/jmOOOQaHHnoozjrrLLzyyiudnS2jhCxevBg//elPMWbMGAwbNgzHHXccLr/8crz33nt59y5cuBATJkzA0KFDcfTRR+O6667D5s2b8+5L0o9i0zTKnzvvvBP19fU49dRT836zvmNwFi9ejAsuuABHHHEEvvjFL+KUU07BnDlzcu554YUXMG7cOBxyyCE47rjj8Otf/xrbtm3LS2vDhg24+uqr8eUvfxnDhg3Dt7/9bSxdulR9b2yaRvnx7rvv4rLLLsOxxx6LYcOGYcyYMbjjjjvQ1taWc5/JmtJRcc0111zT2ZkwgCuuuAJz5szBWWedhbFjx2LZsmW4++67cdRRR+Fzn/tcZ2fPKAH//u//jpdffhnHH388xo0bh0GDBuHpp5/GzJkz8bWvfQ377LMPAGDp0qWYOHEi+vTpg+9973uora3F/fffjyVLluDkk0/OSTO2HyVJ0yhv1q5di0svvRTdu3dHnz59MGHChOxv1ncMzvz58/Hd734Xn/vc5zBhwgQce+yxqKqqQltbG4488sjsPRdddBH2339/TJ48GX369MHdd9+N9evXY8SIEdm02tvbce655+KPf/wjzjnnHIwaNQqvvvoqZs6cidGjR6NPnz45741J0yg/PvzwQ4wbNw7r1q3D2WefjRNOOAHbtm3Dvffei/fffx8nnngiAJM1JSdjdDqLFi3K1NXVZe65557stS1btmROOOGEzNlnn915GTNKymuvvZZpbW3NufbOO+9kDj744ExjY2P22uTJkzNf/epXMxs3bsxee+ihhzJ1dXWZBQsWZK8l6UexaRrlT2NjY2bSpEmZiRMnZk455ZSc36zvGMSGDRsyRx11VObaa6/13jdmzJjMuHHjMtu2bcteu+mmmzIHHHBA5p133slemzt3bqauri7z3HPPZa99/PHHmcMPPzxzxRVXpErTKD9uv/32TF1dXeavf/1rzvUf/OAHmS984QuZtra2TCZjsqbUWBhMGfD000+je/fuOPPMM7PXKisrccYZZ+C1117DmjVrOjF3RqkYPnw4evTokXPt85//PIYMGYIVK1YAADZu3IgFCxbgtNNOwx577JG979RTT0Xv3r3x1FNPZa/F9qMkaRrlzeLFi/HEE0/gyiuvzPvN+o7BefLJJ7FhwwZceumlAHa0ZSaTybln+fLlWL58OcaPH4+Kiors9bPPPhvt7e149tlns9eeeeYZ1NTUYNSoUdlr++yzD0466SQ8//zz2Lp1a+I0jfLj008/BQB85jOfybn+2c9+Ft26dUNFRYXJmg7AlPUyYOnSpRg0aFBOhwSAQw89FJlMxhkDaOx+ZDIZfPTRR9h7770BAMuWLcO2bdtw8MEH59zXo0cPHHjggTl9I7YfJUnTKF8ymQyuvfZanHbaaTjwwAPzfre+Y3BeeeUVDB48GPPnz8eIESNw2GGH4cgjj8S0adOwfft2AMCSJUsAIK99+/Xrh3333Tf7O7Cjzxx00EHo0qVLzr2HHHIIPv30U6xcuTJxmkb5ccQRRwAArrrqKrz55pv429/+hieeeAKPPvoozj//fHTt2tVkTQdgynoZsHbtWtTU1ORd79u3LwCYZf0fiCeeeAIffvghTjrpJAA7+gawsy9w+vbtm9M3YvtRkjSN8uWxxx7D8uXLcdlll6m/W98xOO+99x5Wr16NqVOnYty4cZg+fTpOOOEE3HnnnbjhhhsAFKfP0DXrM7sHxxxzDC699FIsWLAAp556Ko477jhcccUVmDx5Mr7//e8DMFnTEXTr7AwYwJYtW9C9e/e865WVlQCA1tbWjs6S0QmsWLEC//Zv/4bDDjsse6rHli1bACAvXAbY0T/od7o3ph8lSdMoTzZu3Ihf/OIXuOCCC9SJD7C+Y+SyadMmrF+/Hv/yL/+CCy64AABw4oknYtOmTXjggQdw0UUXBduXn8KxZcsW9T66RmklSdMoTwYMGIAjjzwSX/va11BdXY3//u//xvTp07HPPvtgwoQJJms6AFPWy4CePXtm4/s41GmpExu7L2vXrsX3vvc99OnTB7fccgu6dt3h9OrZsycA5B2RBezoH/Q73RvTj5KkaZQnt912G7p3747vfOc7znus7xgcaht5isbYsWPx9NNP4/XXX0/cZ7T76Brda31m12bu3Ln4yU9+gqeffhr9+vUDsGORl8lkcOONN2LMmDEmazoAC4MpA1wuHXIDuSxnxu5BS0sLzj//fLS0tOCuu+7KcfvRv6kvcKQ7MbYfJUnTKD/WrFmD++67D2effTY++ugjNDc3o7m5Ga2trdi6dSuam5uxfv166ztGDtR2n/3sZ3Ou09/F6jN0zfrM7sHvfvc7HHTQQVlFnRg5ciQ2bdqEN99802RNB2DKehlwwAEH4J133snuuiYWLVqU/d3YPWltbcWFF16Id999F7fffjsGDx6c83tdXR26deuGN954I+d6W1sbli5dmrOxMLYfJUnTKD8+/vhjbN26FdOmTcOoUaOy/y1atAgrVqzAqFGjcOedd1rfMXI46KCDAOw4N5uzevVqADtOcqH2k+374YcfYvXq1Xl95v/+7//yTpRZvHgxevfujdraWgBIlKZRfnz00UfZDcgcso5v377dZE0HYMp6GTB69Ghs3boVDz/8cPZaW1sb5syZg+HDh+etaI3dg+3bt+Oyyy7DX/7yF9xyyy0YNmxY3j1VVVU46qij8Pjjj+cIt8cffxybNm3C6NGjs9di+1GSNI3yY8CAAZgxY0bef0OGDEH//v0xY8YMnHbaadZ3jByobf7zP/8zey2TyeDhhx9G7969MWzYMAwZMgSDBw/G7NmzcxS0Bx54AF27ds1+AIfSW7NmDV544YXstU8++QRPP/00Ro0alY1LTpKmUX4MGjQIb7zxRvZ0H2Lu3LmoqKhAfX29yZoOwL5gWgbsu+++WL58OWbNmoVPP/0Uzc3NuP7667FixQr8/Oc/xz/90z91dhaNEnD99dfjsccew4gRIzBw4EAsW7Ys+19zc3PWyr7ffvth5syZmD9/Ptrb2/H888/jlltuwdFHH41LLrkkm16SfhSbplF+VFZWYvDgwXn/0bnDV111Vfbrt9Z3DKKmpgbNzc2YNWsWVq9ejdWrV2PGjBl46aWXcNlll+HLX/4yAKB///649957sXDhQrS1teHRRx/FPffcg/Hjx2PcuHHZ9AYPHoyXX34Zs2fPxtatW/HWW2/h2muvRUtLC2666SZUV1dn741N0yg/+vXrhzlz5mDu3LlobW3FX//6V0yfPh0vvvgixo8fjzFjxgAwWVNqumSkD8voFFpbW/HLX/4STz75JNavX4/6+npMmTIFX/nKVzo7a0aJmDRpEl599VX1t/79+2PevHnZv//0pz9h2rRpWLJkCfbcc0+MGTMGU6ZMQe/evXOeS9KPYtM0dg0mTZqEDRs24PHHH8+5bn3HINra2nDrrbfisccew0cffYQBAwbg3HPPxbe+9a2c+55//nn8+te/xooVK7DPPvvg9NNPx8UXX4xu3XLPpFi/fj1uvPFGPP/882htbcUhhxyCqVOnZkNu0qRplB+LFy/G9OnTsXTpUqxbtw79+/fH6aefju9+97s5H7oyWVM6TFk3DMMwDMMwjDLFYtYNwzAMwzAMo0wxZd0wDMMwDMMwyhRT1g3DMAzDMAyjTDFl3TAMwzAMwzDKFFPWDcMwDMMwDKNMMWXdMAzDMAzDMMoUU9YNwzAMwzAMo0wxZd0wDOMfmEmTJmHkyJGdnY1OY/r06aivr0dzc3NnZ8UwDEPFlHXDMIyErFq1CldffTVGjx6NoUOH4ogjjsBJJ52ExsZG/PGPf+zs7JUFkyZNQn19PUaNGoW2tra830lJfv311zshd4ZhGLsO9p1fwzCMBLz++uuYNGkSunXrhtNOOw37778/tmzZgvfeew8vv/wy9thjD3z5y1/u7GyWDc3NzXjggQdwzjnndHZWDMMwdklMWTcMw0jAjBkzsHnzZjz++OM44IAD8n5fu3ZtJ+SqPOnZsycGDBiA2267Daeffjr23HPPzs5Sp7Nx40arB8MwEmFhMIZhGAl49913UV1drSrqANC3b9+cv3//+9/jwgsvxHHHHYeDDz4YX/rSl3DxxRfjzTffzHt25MiRmDRpEt58802ce+65+OIXv4ijjjoKN9xwA7Zt24bW1lY0NTXhq1/9Kg455BA0NDRgxYoVOWnMmTMH9fX1WLBgAaZPn47jjz8eBx98MMaOHYu5c+cmKucVV1yBY445BgcffDBGjhyJpqYmbNq0KTqNrl27YsqUKfj73/+Ou+66K3i/L36c6oZTX1+PqVOn4pVXXsH48eMxdOhQHHvssbjjjjsAAOvXr8e//uu/4qijjsLQoUPxve99Dx9++KH67s2bN+O6667D0UcfjUMPPRRnnnkmXnnlFfXeBQsW4LzzzsPhhx+OQw45BGPHjsUDDzzgzPOSJUvw3e9+F4cddhhOOeWUYD0YhmFwzLJuGIaRgNraWrzzzjt49tlnceKJJwbvv//++1FdXY2zzjoLffv2xcqVK/HQQw9hwoQJePTRR/H5z38+5/7Vq1fjO9/5DsaMGYOvf/3rePnll3HPPfegoqICy5cvx5YtW3DBBRfg73//O37729/i4osvxlNPPYWuXXNtL9OmTcOmTZswYcIEADuU+ClTpqC1tRXf/OY3vXl+4403cM4552CvvfbC+PHj0a9fP7z55puYOXMm/vznP2PmzJno3r17VH2NGjUKhx12GO677z40NDTkLWYKZcmSJXjxxRdx1lln4dRTT8VTTz2FX/ziF6isrMRjjz2G/v374/vf/z5WrlyJmTNnorGxEffee29eOo2NjejatSvOP/98bNy4EbNnz8bkyZNx55134itf+Ur2vtmzZ+MnP/kJhg0bhgsvvBC9evXCggULcM0112DlypVobGzMSfeDDz7AOeecg9GjR+PEE09MtNgxDMMAAGQMwzCMaBYuXJg56KCDMnV1dZkTTzwxM3Xq1MysWbMyy5cvV+//9NNP864tX748c9BBB2V+8pOf5Fw//vjjM3V1dZnf//73OdfHjRuXqa+vz1x44YWZ9vb27PX77rsvU1dXl3nppZey1x555JFMXV1d5rjjjsts2LAhe33Dhg2Z4447LnPEEUdkNm/enL0+ceLEzPHHH5/zvrFjx2a+/vWvZ1paWnKuP/vss5m6urrMI4884qidnUycODEzbNiwTCaTybz22muZurq6zNVXX539/Ve/+lWmrq4us3jx4rxrq1atykvv+OOPz0ycODHnWl1dXaa+vj7zl7/8JXuttbU1c/TRR2fq6+sz1157bc79P/vZzzJ1dXWZFStW5L3zjDPOyLS2tmav/+1vf8sMGzYsM3r06Oy1Dz/8MHPwwQdnpkyZkpe/a6+9NnPAAQdkVq5cmZPnurq6zEMPPeSuKMMwjAAWBmMYhpGAL37xi3jkkUcwbtw4tLS0YM6cOfjpT3+KMWPGoKGhAatWrcq5v3fv3gCATCaDjRs34pNPPsHee++NQYMGYfHixXnp9+vXDyeddFLOteHDhyOTyWDSpEno0qVL9vrhhx8OAHjvvffy0pkwYQKqqqqyf1dVVeFb3/oW1q9fj//5n/9xlm/ZsmVYtmwZTj75ZLS1teGTTz7J/nfYYYehd+/eePnllyNqKjf/J5xwAh555BG88847iZ4NMWzYMAwdOjT7d48ePXDIIYdk64vjq69zzz0XPXr0yP697777YuzYsXj77bezoUbPPPMM2tracMYZZ+TUyyeffIKRI0eivb0dCxYsyEm3uro66MkwDMPwYWEwhmEYCamvr8cNN9wAAHj//ffxv//7v3j44Yfxpz/9CRdffDEeeeSRrOK3ZMkS3HLLLXj11VfzQiAGDBiQl7Z2rU+fPupve+21FwBg3bp1ec8MHjw479p+++0HAN4zxUkxnT59OqZPn67e89FHHzmfdzFlyhS8+OKLuOmmm5zppmHgwIF519LUF9WNdm3VqlXYb7/9snVz7rnnOvMj62bgwIGoqKjwlMAwDMOPKeuGYRgF0L9/f/Tv3x+nnnoqzj77bCxcuBCLFy/G4Ycfjg8++AANDQ3Yc889cdFFF2Hw4MHo1asXunTpgp/97Gdq/LJPsZNx6UQmkylaeYjzzjsPX/3qV9XfSOlNwn777YdvfvObePjhh7Fo0SL1Hu41kGzbtk297qsv129p64uea2pqQk1NjXqPXDz06tUr1bsMwzAIU9YNwzCKQJcuXTB06FAsXLgQa9asAQA899xz2LRpE2677ba8s9fXrVuXE3ZRbN5+++28a2QZ1qz3xD//8z8D2LEw4Bsri8EPfvAD/Nd//RemTZuGI488Mu93soivX78+J4+tra1Yu3ZtNm+lYMWKFXkn/FB9kQJOm4H33nvvoteNYRiGC4tZNwzDSMDLL7+sWnm3bNmSjeWm8Amy7EpL7kMPPVTy89gfeOABtLS0ZP9uaWnBgw8+iL322ktVlIkvfOELqKurw4MPPpgXfw/ssHBrYSQx9OvXD9/+9rfx6quvYv78+Xm/kzIs477vvfdetLe3muroNQAAAthJREFUp3pnLPfee2/Ol1ZXr16NJ598EoMGDcq250knnYQePXpg+vTp2LJlS14aLS0t6tdaDcMwCsEs64ZhGAm4/vrrsW7dOowcORJ1dXXo2bNnVrF79913cdppp6G+vh4AcOyxx6JXr1740Y9+hIkTJ2KvvfbCwoUL8dJLL6G2thbbt28vWT733ntvnHnmmdnNjXPmzMEHH3yA6667zhua0aVLF9x4440455xzcMopp+D000/P+Urrc889hylTpqTeNHn++edj9uzZeP311/N++8pXvoJBgwbhV7/6FdatW4cBAwbgtddew6JFi7D33nunel8s27dvR0NDA77xjW/g008/xYMPPojW1lb8+Mc/zt6z77774pprrsGPf/xjjBkzBqeccgr69++PTz75BH/961/x/PPPY+7cuV7PhWEYRlJMWTcMw0jA1KlT8cILL+C1117DM888g5aWFlRVVaGurg7nn39+jhJbW1uLO++8EzfddBN+85vfoKKiAsOHD8fMmTNx7bXX4v333y9ZPn/4wx/iT3/6E373u9/ho48+wqBBgzBt2jSMHTs2+OyBBx6IRx99FLfffjvmzZuHBx98EHvssQf69++PcePG4aijjkqdr6qqKlx00UW4/vrr836rqKjAbbfdhuuuuw73338/unfvjqOPPhr3339/9rz4UtHU1IQHH3wQd955JzZs2JDdRHz00Ufn3Hf66afj85//PH77299i9uzZaGlpQXV1NQYNGoRLL7206OfIG4ZhdMmUYmeSYRiG0SnMmTMHV155Jf7jP/4DX/rSlzo7O4ZhGEaBWMy6YRiGYRiGYZQppqwbhmEYhmEYRpliyrphGIZhGIZhlCkWs24YhmEYhmEYZYpZ1g3DMAzDMAyjTDFl3TAMwzAMwzDKFFPWDcMwDMMwDKNMMWXdMAzDMAzDMMoUU9YNwzAMwzAMo0wxZd0wDMMwDMMwypT/B663YzeUJCjCAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9rMhLNhPcZjU"
      },
      "source": [
        "### Tokenizing the sequences"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "t7JsLi3EdEje"
      },
      "source": [
        "max_input_length = 400"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J968o8RJcUEd",
        "outputId": "7c9721e4-881b-4ae3-b006-e7e4119c1227"
      },
      "source": [
        "full_input_ids = []\r\n",
        "labels = []\r\n",
        "\r\n",
        "# Tokenize all training examples\r\n",
        "print('Tokenizing {:,} training samples...'.format(len(train_sentences)))\r\n",
        "\r\n",
        "# Choose an interval on which to print progress updates.\r\n",
        "update_interval = good_update_interval(total_iters=len(train_sentences), num_desired_updates=10)\r\n",
        "\r\n",
        "# For each training example...\r\n",
        "for text in train_sentences:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "        print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # Tokenize the sentence.\r\n",
        "    input_ids = tokenizer.encode(text=text,           \r\n",
        "                                 add_special_tokens=True, \r\n",
        "                                 max_length=max_input_length,  \r\n",
        "                                 truncation=True,     \r\n",
        "                                 padding=False)       \r\n",
        "                                 \r\n",
        "    # Add the tokenized result to our list.\r\n",
        "    full_input_ids.append(input_ids)\r\n",
        "    \r\n",
        "print('DONE.')\r\n",
        "print('{:>10,} samples'.format(len(full_input_ids)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Tokenizing 8,564 training samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rZzhO2tZeXur"
      },
      "source": [
        "# Get all of the lengths.\r\n",
        "unsorted_lengths = [len(x) for x in full_input_ids]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "x7c_mYuVed_H",
        "outputId": "ad994f8d-2de6-4f96-c59d-514b52cad9bd"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(unsorted_lengths)), unsorted_lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7PaeohUVegmv"
      },
      "source": [
        "# Sort the two lists together by the length of the input sequence.\r\n",
        "train_samples = sorted(zip(full_input_ids, train_labels), key=lambda x: len(x[0]))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_9nyx-BtepE4",
        "outputId": "b89a46c9-ea96-4729-e261-60f5f2c85b77"
      },
      "source": [
        "train_samples[0:5]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[([101, 13073, 102], 2),\n",
              " ([101, 22678, 37157, 102], 2),\n",
              " ([101, 13073, 30514, 102], 2),\n",
              " ([101, 32470, 91929, 102], 0),\n",
              " ([101, 22678, 37157, 102], 2)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rBxJhEieetFh",
        "outputId": "a61cf45a-4691-4351-cc84-f8b51ec2c85e"
      },
      "source": [
        "print('Shortest sample:', len(train_samples[0][0]))\r\n",
        "print('Longest sample:', len(train_samples[-1][0]))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shortest sample: 3\n",
            "Longest sample: 400\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "P44bFOI-e7hW"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "sorted_lengths = [len(s[0]) for s in train_samples]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "9P5ZX99le_G1",
        "outputId": "c93f88b1-7991-46dd-d3bc-c0a41cdf84d8"
      },
      "source": [
        "\r\n",
        "plt.plot(range(0, len(sorted_lengths)), sorted_lengths)\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples after Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Eh1z0xugfF2t"
      },
      "source": [
        "### Random Batch Selections"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gPrYkFMcgm5H",
        "outputId": "12b7ffb8-1c31-4aad-9894-6187809e327e"
      },
      "source": [
        "train_samples[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "([101, 13073, 102], 2)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "isMxwgezfAvO"
      },
      "source": [
        "batch_size = 16"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s0tjD8pIfJ0S",
        "outputId": "950c802e-a663-4517-d8d6-0c9b1fd98ddf"
      },
      "source": [
        "# List of batches that we'll construct.\r\n",
        "batch_ordered_sentences = []\r\n",
        "batch_ordered_labels = []\r\n",
        "\r\n",
        "print('Creating training batches of size {:}'.format(batch_size))\r\n",
        "\r\n",
        "# Loop over all of the input samples...    \r\n",
        "while len(train_samples) > 0:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(batch_ordered_sentences) % 100) == 0):\r\n",
        "        print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "    # we get to the last batch, which may be smaller. \r\n",
        "    to_take = min(batch_size, len(train_samples))\r\n",
        "\r\n",
        "    # Pick a random index in the list of remaining samples to start\r\n",
        "    # our batch at.\r\n",
        "    select = random.randint(0, len(train_samples) - to_take)\r\n",
        "\r\n",
        "    # Select a contiguous batch of samples starting at `select`.\r\n",
        "    batch = train_samples[select:(select + to_take)]\r\n",
        "\r\n",
        "    # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "    # sequences and a list of labels for this batch.\r\n",
        "    batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "    batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "    # Remove these samples from the list.\r\n",
        "    del train_samples[select:select + to_take]\r\n",
        "\r\n",
        "print('\\n  DONE - {:,} batches.'.format(len(batch_ordered_sentences)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating training batches of size 16\n",
            "  Selected 0 batches.\n",
            "  Selected 100 batches.\n",
            "  Selected 200 batches.\n",
            "  Selected 300 batches.\n",
            "  Selected 400 batches.\n",
            "  Selected 500 batches.\n",
            "\n",
            "  DONE - 536 batches.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rf91Dd3LhBaP",
        "outputId": "d7dfb50e-2200-49e2-bb19-86d6b6cb8d1d"
      },
      "source": [
        "print(batch_ordered_sentences[0])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[101, 1352, 52388, 29400, 66985, 16471, 24458, 1353, 111402, 79960, 18395, 24458, 102], [101, 137, 23080, 10676, 139, 20578, 15190, 10824, 32037, 17094, 10727, 10133, 102], [101, 56326, 40799, 15292, 75301, 13622, 1353, 27921, 34590, 17896, 29400, 119, 102], [101, 24625, 10192, 10114, 67742, 19962, 10731, 13998, 11023, 10107, 10114, 59411, 102], [101, 1328, 43877, 75301, 1334, 59009, 17878, 69203, 1331, 96696, 1323, 37591, 102], [101, 12404, 54047, 11008, 51428, 10174, 33705, 10112, 16642, 10537, 21427, 35397, 102], [101, 13672, 41493, 10107, 119, 31119, 11759, 15688, 12177, 1367, 17676, 21403, 102], [101, 17376, 119, 119, 119, 25460, 11591, 48765, 12078, 119, 119, 119, 102], [101, 158, 10350, 69191, 40300, 18995, 18643, 91189, 10133, 119, 119, 119, 102], [101, 100, 182, 19998, 10271, 13723, 14325, 11534, 87600, 13998, 13061, 11147, 102], [101, 17376, 119, 119, 119, 25460, 11591, 48765, 12078, 119, 119, 119, 102], [101, 109499, 69857, 54047, 19172, 10144, 44082, 61972, 10284, 119, 119, 119, 102], [101, 138, 139, 89696, 21318, 11369, 65729, 11259, 119, 119, 119, 119, 102], [101, 16777, 25230, 10105, 11083, 55352, 41549, 12443, 15914, 10853, 59731, 13660, 102], [101, 137, 77603, 23315, 77603, 23315, 182, 11565, 39041, 19314, 16200, 22659, 102], [101, 85581, 11147, 15694, 55170, 13723, 10799, 30771, 10116, 18028, 21533, 10112, 102]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qmkQK_gVgiTu",
        "outputId": "b45361b6-9d1c-4067-e04c-ff40913d74f0"
      },
      "source": [
        "batch_ordered_labels[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 2, 1, 1, 1]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 53
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xZ0TFA8Mfn6m"
      },
      "source": [
        "### Padding"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9rdswcpfTip"
      },
      "source": [
        "py_inputs = []\r\n",
        "py_attn_masks = []\r\n",
        "py_labels = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "    # New version of the batch, this time with padded sequences and now with\r\n",
        "    # attention masks defined.\r\n",
        "    batch_padded_inputs = []\r\n",
        "    batch_attn_masks = []\r\n",
        "    \r\n",
        "    # First, find the longest sample in the batch. \r\n",
        "    # Note that the sequences do currently include the special tokens!\r\n",
        "    max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "    #print('Max size:', max_size)\r\n",
        "\r\n",
        "    # For each input in this batch...\r\n",
        "    for sen in batch_inputs:\r\n",
        "        \r\n",
        "        # How many pad tokens do we need to add?\r\n",
        "        num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "        # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "        padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "        # Define the attention mask--it's just a `1` for every real token\r\n",
        "        # and a `0` for every padding token.\r\n",
        "        attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "        # Add the padded results to the batch.\r\n",
        "        batch_padded_inputs.append(padded_input)\r\n",
        "        batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "    # Our batch has been padded, so we need to save this updated batch.\r\n",
        "    # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "    py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "    py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "    py_labels.append(torch.tensor(batch_labels))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "roS5lLWdX-5J"
      },
      "source": [
        "### Check the number of token reductions because of smart batching"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wlh7cteVfroV",
        "outputId": "56794f46-43f0-44a8-9641-2cf65d142fb8"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "\r\n",
        "padded_lengths = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for batch in py_inputs:\r\n",
        "    \r\n",
        "    # For each sample...\r\n",
        "    for s in batch:\r\n",
        "    \r\n",
        "        # Record its length.\r\n",
        "        padded_lengths.append(len(s))\r\n",
        "\r\n",
        "# Sum up the lengths to the get the total number of tokens after smart batching.\r\n",
        "smart_token_count = np.sum(padded_lengths)\r\n",
        "\r\n",
        "# To get the total number of tokens in the dataset using fixed padding, it's\r\n",
        "# as simple as the number of samples times our `max_len` parameter (that we\r\n",
        "# would pad everything to).\r\n",
        "fixed_token_count = len(train_sentences) * max_input_length\r\n",
        "\r\n",
        "# Calculate the percentage reduction.\r\n",
        "prcnt_reduced = (fixed_token_count - smart_token_count) / float(fixed_token_count) \r\n",
        "\r\n",
        "print('Total tokens:')\r\n",
        "print('   Fixed Padding: {:,}'.format(fixed_token_count))\r\n",
        "print('  Smart Batching: {:,}  ({:.1%} less)'.format(smart_token_count, prcnt_reduced))\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Total tokens:\n",
            "   Fixed Padding: 3,425,600\n",
            "  Smart Batching: 342,700  (90.0% less)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8wgdhsI-YIAL"
      },
      "source": [
        "## Load the model configuration from the transformers library using AutoConfig"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9er7EHvdfudf",
        "outputId": "0d0a9991-fa4a-4f3e-9d6f-8a053c1b9044"
      },
      "source": [
        "# Load the Config object, with an output configured for classification.\r\n",
        "config = AutoConfig.from_pretrained(pretrained_model_name_or_path=model_name,\r\n",
        "                                    num_labels=len(class_names))\r\n",
        "\r\n",
        "print('Config type:', str(type(config)), '\\n')\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Config type: <class 'transformers.models.bert.configuration_bert.BertConfig'> \n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170,
          "referenced_widgets": [
            "fa35075a0c3b4ac797b447ed0cbdfb5e",
            "3782bf5eb65b49909015511146b467d0",
            "c78ee957ff6b48b7ac56bbc7ad36401d",
            "996c25d462424bbf90f0dff2b92fc816",
            "9d3409c0ec024c4f93dfc46446cb87f5",
            "0250d973b87a4a37af7c14c8a5382793",
            "fa578d2e60d141a8a3f2a86d2ea84a5c",
            "80cd0c340dd248b1ab47f4c7e844b20a"
          ]
        },
        "id": "bWvc9Ikv4HtD",
        "outputId": "55652aa8-120f-4e26-818f-130f255a06de"
      },
      "source": [
        "model = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=model_name,config = config)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "fa35075a0c3b4ac797b447ed0cbdfb5e",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=714314041.0, style=ProgressStyle(descri…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Some weights of the model checkpoint at bert-base-multilingual-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias']\n",
            "- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-multilingual-cased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xouf5M2B55ei",
        "outputId": "0c6ab82a-d35c-4f9d-d5d3-8c6e3efb45e3"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "BertForSequenceClassification(\n",
              "  (bert): BertModel(\n",
              "    (embeddings): BertEmbeddings(\n",
              "      (word_embeddings): Embedding(119547, 768, padding_idx=0)\n",
              "      (position_embeddings): Embedding(512, 768)\n",
              "      (token_type_embeddings): Embedding(2, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): BertEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "    (pooler): BertPooler(\n",
              "      (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "      (activation): Tanh()\n",
              "    )\n",
              "  )\n",
              "  (dropout): Dropout(p=0.1, inplace=False)\n",
              "  (classifier): Linear(in_features=768, out_features=3, bias=True)\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 58
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qYV6GYYUxr4M"
      },
      "source": [
        "## Load the model from the transformers library using AutoModel"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Jmcj0PrXxr4O",
        "outputId": "06fbcfa8-205f-4eb5-f1d4-67259da6dbba"
      },
      "source": [
        "# Load the pre-trained model for classification, passing in the `config` from\r\n",
        "# above.\r\n",
        "model = AutoModel.from_pretrained(\r\n",
        "    pretrained_model_name_or_path=model_name,\r\n",
        "    config=config)\r\n",
        "\r\n",
        "print('\\nModel type:', str(type(model)))\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Model type: <class 'transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaModel'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2LEx-3Spxr4R"
      },
      "source": [
        "# freeze all the parameters\r\n",
        "for param in model.parameters():\r\n",
        "    param.requires_grad = False"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bOXKJrU_xr4S"
      },
      "source": [
        "## Creating a custom BERT model "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "m3CbIF1Axr4U"
      },
      "source": [
        "\r\n",
        "class Custom_Model(nn.Module):\r\n",
        "    ## defining the constructor for the class\r\n",
        "    def __init__(self, model,num_labels):\r\n",
        "      ## calling the super class constructor\r\n",
        "      super(Custom_Model, self).__init__()\r\n",
        "      ## adding the bert layer to the model\r\n",
        "      self.model = model        \r\n",
        "      # relu activation function\r\n",
        "      self.relu =  nn.ReLU()\r\n",
        "      # adding a dense layer to our custom model\r\n",
        "      self.fc1 = nn.Linear(768,512)\r\n",
        "      # adding another dense layer to our custom model ,i.e., the Output layer\r\n",
        "      self.fc2 = nn.Linear(512,num_labels)\r\n",
        "      # adding a softmax  activation function for our custom model's output layer\r\n",
        "      self.softmax = nn.LogSoftmax(dim=1)\r\n",
        "\r\n",
        "    #defining the forward pass\r\n",
        "    def forward(self, input_id, mask):\r\n",
        "      #pass the inputs to the model  \r\n",
        "      outputs = self.model(input_id,mask)\r\n",
        "  \r\n",
        "      last_hidden_state = outputs.last_hidden_state       ## last hidden state from the model\r\n",
        "      pooler_output = outputs.pooler_output               ## pooler output from the model\r\n",
        "      ## adding a fully connected layer to the BERT model\r\n",
        "      x = self.fc1(pooler_output)\r\n",
        "      ## applying relu activation function\r\n",
        "      x = self.relu(x)\r\n",
        "      # the final output layer\r\n",
        "      x = self.fc2(x)\r\n",
        "      # apply softmax activation to our output layer\r\n",
        "      x = self.softmax(x)\r\n",
        "\r\n",
        "      return x"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Lqp1b5hNxr4V",
        "outputId": "e79ece3b-4ed1-4f65-b676-cde5e5cc8634"
      },
      "source": [
        "\r\n",
        "\r\n",
        "print('\\nLoading model ...')\r\n",
        "# pass the pre-trained BERT to our define architecture\r\n",
        "model = Custom_Model(model,num_labels=len(class_names))\r\n",
        "\r\n",
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading model ...\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Custom_Model(\n",
              "  (model): XLMRobertaModel(\n",
              "    (embeddings): RobertaEmbeddings(\n",
              "      (word_embeddings): Embedding(250002, 768, padding_idx=1)\n",
              "      (position_embeddings): Embedding(514, 768, padding_idx=1)\n",
              "      (token_type_embeddings): Embedding(1, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): RobertaEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "    (pooler): RobertaPooler(\n",
              "      (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "      (activation): Tanh()\n",
              "    )\n",
              "  )\n",
              "  (relu): ReLU()\n",
              "  (fc1): Linear(in_features=768, out_features=512, bias=True)\n",
              "  (fc2): Linear(in_features=512, out_features=6, bias=True)\n",
              "  (softmax): LogSoftmax(dim=1)\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 146
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LjQSUqCWJTbI"
      },
      "source": [
        "## Custom Loss function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iOHVl1RRJSUB"
      },
      "source": [
        "# # convert class weights to tensor\r\n",
        "# weights= torch.tensor(class_wts,dtype=torch.float)\r\n",
        "# weights = weights.to(device)\r\n",
        "\r\n",
        "# # loss function\r\n",
        "# cross_entropy  = nn.NLLLoss(weight=weights) \r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "evYV0yrQ2u_b"
      },
      "source": [
        "## Loading Optimizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8tAijXBEh7t8"
      },
      "source": [
        "# Note: AdamW is a class from the huggingface library (as opposed to pytorch) \r\n",
        "# I believe the 'W' stands for 'Weight Decay fix\"\r\n",
        "optimizer = AdamW(model.parameters(),\r\n",
        "                  lr = 2e-5, # This is the value Michael used.\r\n",
        "                  eps = 1e-8 # args.adam_epsilon  - default is 1e-8.\r\n",
        "                )\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "s9n3_5jI2ywo"
      },
      "source": [
        "## Loading lr scheduler"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "agidP6D6iBFI"
      },
      "source": [
        "# Number of training epochs. I chose to train for 1 simply because the training\r\n",
        "# time is long. More epochs may improve the model's accuracy.\r\n",
        "epochs = 4\r\n",
        "\r\n",
        "# Total number of training steps is [number of batches] x [number of epochs]. \r\n",
        "# Note that it's the number of *batches*, not *samples*!\r\n",
        "total_steps = len(py_inputs) * epochs\r\n",
        "\r\n",
        "# Create the learning rate scheduler.\r\n",
        "scheduler = get_linear_schedule_with_warmup(optimizer, \r\n",
        "                                            num_warmup_steps = 0, # Default value in run_glue.py\r\n",
        "                                            num_training_steps = total_steps)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MDDp05Cm245e"
      },
      "source": [
        "## Training Loop"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H4ERR8fBiEJn",
        "outputId": "9296d1fd-ad93-40c5-9179-f9c9fb975df4"
      },
      "source": [
        "# We'll store a number of quantities such as training and validation loss, \r\n",
        "# validation accuracy, and timings.\r\n",
        "training_stats = {\r\n",
        "    'epoch':[],\r\n",
        "    'train_loss':[],\r\n",
        "    'Training Time':[],\r\n",
        "    'val_loss':[],\r\n",
        "    'Validation Time':[],\r\n",
        "    'train_acc':[],\r\n",
        "    'val_acc':[]\r\n",
        "}\r\n",
        "\r\n",
        "# Update every `update_interval` batches.\r\n",
        "update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "# Measure the total training time for the whole run.\r\n",
        "total_t0 = time.time()\r\n",
        "best_accuracy = 0\r\n",
        "# For each epoch...\r\n",
        "for epoch_i in range(0, epochs):\r\n",
        "\r\n",
        "    predictions = []\r\n",
        "    true_labels = []\r\n",
        "    \r\n",
        "    # ========================================\r\n",
        "    #               Training\r\n",
        "    # ========================================\r\n",
        "    \r\n",
        "    # Perform one full pass over the training set.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print('======== Epoch {:} / {:} ========'.format(epoch_i + 1, epochs))\r\n",
        "    \r\n",
        "    # At the start of each epoch (except for the first) we need to re-randomize\r\n",
        "    # our training data.\r\n",
        "    if epoch_i > 0:\r\n",
        "        # Use our `make_smart_batches` function (from 6.1.) to re-shuffle the \r\n",
        "        # dataset into new batches.\r\n",
        "        (py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size,tokenizer,max_input_length)\r\n",
        "    \r\n",
        "    print('Training on {:,} batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "    # Measure how long the training epoch takes.\r\n",
        "    t0 = time.time()\r\n",
        "\r\n",
        "    # Reset the total loss for this epoch.\r\n",
        "    total_train_loss = 0\r\n",
        "\r\n",
        "    # Put the model into training mode. Don't be mislead--the call to \r\n",
        "    # `train` just changes the *mode*, it doesn't *perform* the training.\r\n",
        "    # `dropout` and `batchnorm` layers behave differently during training\r\n",
        "    # vs. test (source: https://stackoverflow.com/questions/51433378/what-does-model-train-do-in-pytorch)\r\n",
        "    model.train()\r\n",
        "\r\n",
        "    # For each batch of training data...\r\n",
        "    for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "        # Progress update every, e.g., 100 batches.\r\n",
        "        if step % update_interval == 0 and not step == 0:\r\n",
        "            # Calculate elapsed time in minutes.\r\n",
        "            elapsed = format_time(time.time() - t0)\r\n",
        "            \r\n",
        "            # Calculate the time remaining based on our progress.\r\n",
        "            steps_per_sec = (time.time() - t0) / step\r\n",
        "            remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "            remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "            # Report progress.\r\n",
        "            print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "        # Copy the current training batch to the GPU using the `to` method.\r\n",
        "        b_input_ids = py_inputs[step].to(device)\r\n",
        "        b_input_mask = py_attn_masks[step].to(device)\r\n",
        "        b_labels = py_labels[step].to(device)\r\n",
        "\r\n",
        "        # Always clear any previously calculated gradients before performing a\r\n",
        "        # backward pass.\r\n",
        "        model.zero_grad()        \r\n",
        "\r\n",
        "        # Perform a forward pass (evaluate the model on this training batch).\r\n",
        "        # The call returns the loss (because we provided labels) and the \r\n",
        "        # \"logits\"--the model outputs prior to activation.\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        loss = output.loss \r\n",
        "        logits = output.logits\r\n",
        "\r\n",
        "        # Move logits and labels to CPU\r\n",
        "        logits = logits.detach().cpu().numpy()\r\n",
        "        label_ids = b_labels.to('cpu').numpy()\r\n",
        "      \r\n",
        "        # Store predictions and true labels\r\n",
        "        predictions.append(logits)\r\n",
        "        true_labels.append(label_ids)\r\n",
        "        \r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        total_train_loss += loss.item()\r\n",
        "\r\n",
        "        # Perform a backward pass to calculate the gradients.\r\n",
        "        loss.backward()\r\n",
        "\r\n",
        "        # Clip the norm of the gradients to 1.0.\r\n",
        "        # This is to help prevent the \"exploding gradients\" problem.\r\n",
        "        torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\r\n",
        "\r\n",
        "        # Update parameters and take a step using the computed gradient.\r\n",
        "        # The optimizer dictates the \"update rule\"--how the parameters are\r\n",
        "        # modified based on their gradients, the learning rate, etc.\r\n",
        "        optimizer.step()\r\n",
        "\r\n",
        "        # Update the learning rate.\r\n",
        "        scheduler.step()\r\n",
        "\r\n",
        "    # Calculate the average loss over all of the batches.\r\n",
        "    avg_train_loss = total_train_loss / len(py_inputs)     \r\n",
        "       \r\n",
        "    training_accuracy = check_accuracy(predictions,true_labels)       \r\n",
        "    \r\n",
        "    # Measure how long this epoch took.\r\n",
        "    training_time = format_time(time.time() - t0)\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average training loss: {0:.2f}\".format(avg_train_loss))\r\n",
        "    print(\"  Training Accuracy: {0:.2f}\".format(training_accuracy))\r\n",
        "    print(\"  Training epoch took: {:}\".format(training_time))\r\n",
        "        \r\n",
        "    (py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "    val_loss,val_accuracy,validation_time = eval_model(model,py_inputs, py_attn_masks, py_labels)  \r\n",
        "\r\n",
        "    if val_accuracy > best_accuracy:\r\n",
        "        torch.save(model.state_dict(), 'best_model_state.bin')\r\n",
        "        best_accuracy = val_accuracy\r\n",
        "    # Record all statistics from this epoch.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average validation loss: {0:.2f}\".format(val_loss))\r\n",
        "    print(\"  Validation Accuracy: {0:.2f}\".format(val_accuracy))\r\n",
        "    print(\"  Validation epoch took: {:}\".format(validation_time))\r\n",
        "    \r\n",
        "    \r\n",
        "    training_stats['epoch'].append(epoch_i + 1)\r\n",
        "    training_stats['train_loss'].append(avg_train_loss)\r\n",
        "    training_stats['Training Time'].append(training_time)\r\n",
        "    training_stats['val_loss'].append(val_loss)\r\n",
        "    training_stats['Validation Time'].append(validation_time)\r\n",
        "    training_stats['train_acc'].append(training_accuracy)\r\n",
        "    training_stats['val_acc'].append(val_accuracy)\r\n",
        "\r\n",
        "print(f'Best val accuracy: {best_accuracy}')\r\n",
        "  \r\n",
        "model.load_state_dict(torch.load('best_model_state.bin'))\r\n",
        "\r\n",
        "print(\"\")\r\n",
        "print(\"Training complete!\")\r\n",
        "\r\n",
        "print(\"Total training took {:} (h:mm:ss)\".format(format_time(time.time()-total_t0)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "======== Epoch 1 / 4 ========\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:08.  Remaining: 0:01:19\n",
            "  Batch     100  of      536.    Elapsed: 0:00:16.  Remaining: 0:01:11\n",
            "  Batch     150  of      536.    Elapsed: 0:00:25.  Remaining: 0:01:06\n",
            "  Batch     200  of      536.    Elapsed: 0:00:34.  Remaining: 0:00:58\n",
            "  Batch     250  of      536.    Elapsed: 0:00:44.  Remaining: 0:00:50\n",
            "  Batch     300  of      536.    Elapsed: 0:00:53.  Remaining: 0:00:42\n",
            "  Batch     350  of      536.    Elapsed: 0:01:02.  Remaining: 0:00:33\n",
            "  Batch     400  of      536.    Elapsed: 0:01:11.  Remaining: 0:00:24\n",
            "  Batch     450  of      536.    Elapsed: 0:01:20.  Remaining: 0:00:15\n",
            "  Batch     500  of      536.    Elapsed: 0:01:29.  Remaining: 0:00:06\n",
            "\n",
            "  Average training loss: 0.49\n",
            "  Training Accuracy: 0.80\n",
            "  Training epoch took: 0:01:37\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:04\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      35  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:01\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.42\n",
            "  Validation Accuracy: 0.84\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 2 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:10.  Remaining: 0:01:34\n",
            "  Batch     100  of      536.    Elapsed: 0:00:19.  Remaining: 0:01:25\n",
            "  Batch     150  of      536.    Elapsed: 0:00:29.  Remaining: 0:01:14\n",
            "  Batch     200  of      536.    Elapsed: 0:00:38.  Remaining: 0:01:03\n",
            "  Batch     250  of      536.    Elapsed: 0:00:47.  Remaining: 0:00:54\n",
            "  Batch     300  of      536.    Elapsed: 0:00:56.  Remaining: 0:00:44\n",
            "  Batch     350  of      536.    Elapsed: 0:01:03.  Remaining: 0:00:34\n",
            "  Batch     400  of      536.    Elapsed: 0:01:12.  Remaining: 0:00:25\n",
            "  Batch     450  of      536.    Elapsed: 0:01:22.  Remaining: 0:00:16\n",
            "  Batch     500  of      536.    Elapsed: 0:01:32.  Remaining: 0:00:07\n",
            "\n",
            "  Average training loss: 0.33\n",
            "  Training Accuracy: 0.87\n",
            "  Training epoch took: 0:01:41\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      35  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.45\n",
            "  Validation Accuracy: 0.84\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 3 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:08.  Remaining: 0:01:19\n",
            "  Batch     100  of      536.    Elapsed: 0:00:18.  Remaining: 0:01:19\n",
            "  Batch     150  of      536.    Elapsed: 0:00:28.  Remaining: 0:01:11\n",
            "  Batch     200  of      536.    Elapsed: 0:00:37.  Remaining: 0:01:02\n",
            "  Batch     250  of      536.    Elapsed: 0:00:46.  Remaining: 0:00:52\n",
            "  Batch     300  of      536.    Elapsed: 0:00:55.  Remaining: 0:00:44\n",
            "  Batch     350  of      536.    Elapsed: 0:01:04.  Remaining: 0:00:34\n",
            "  Batch     400  of      536.    Elapsed: 0:01:13.  Remaining: 0:00:25\n",
            "  Batch     450  of      536.    Elapsed: 0:01:23.  Remaining: 0:00:16\n",
            "  Batch     500  of      536.    Elapsed: 0:01:32.  Remaining: 0:00:07\n",
            "\n",
            "  Average training loss: 0.23\n",
            "  Training Accuracy: 0.92\n",
            "  Training epoch took: 0:01:40\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.52\n",
            "  Validation Accuracy: 0.84\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 4 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:09.  Remaining: 0:01:31\n",
            "  Batch     100  of      536.    Elapsed: 0:00:19.  Remaining: 0:01:24\n",
            "  Batch     150  of      536.    Elapsed: 0:00:29.  Remaining: 0:01:14\n",
            "  Batch     200  of      536.    Elapsed: 0:00:36.  Remaining: 0:01:00\n",
            "  Batch     250  of      536.    Elapsed: 0:00:47.  Remaining: 0:00:53\n",
            "  Batch     300  of      536.    Elapsed: 0:00:56.  Remaining: 0:00:44\n",
            "  Batch     350  of      536.    Elapsed: 0:01:05.  Remaining: 0:00:34\n",
            "  Batch     400  of      536.    Elapsed: 0:01:14.  Remaining: 0:00:25\n",
            "  Batch     450  of      536.    Elapsed: 0:01:24.  Remaining: 0:00:16\n",
            "  Batch     500  of      536.    Elapsed: 0:01:32.  Remaining: 0:00:07\n",
            "\n",
            "  Average training loss: 0.16\n",
            "  Training Accuracy: 0.95\n",
            "  Training epoch took: 0:01:39\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.66\n",
            "  Validation Accuracy: 0.83\n",
            "  Validation epoch took: 0:00:03\n",
            "Best val accuracy: 0.8429906542056075\n",
            "\n",
            "Training complete!\n",
            "Total training took 0:07:00 (h:mm:ss)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "GOmua_S1eXNM",
        "outputId": "97e361f7-6397-4098-fe7b-ed60319b6edf"
      },
      "source": [
        "plot_training_history(training_stats)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1296x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3c-6bOIxVyrM"
      },
      "source": [
        "## Evaluating Performance Over Training Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2QmKPNAeWHkZ",
        "outputId": "c9031199-8c23-475a-edb8-ce531a7c091b"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 536 test batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:02.  Remaining: 0:00:21\n",
            "  Batch     100  of      536.    Elapsed: 0:00:04.  Remaining: 0:00:18\n",
            "  Batch     150  of      536.    Elapsed: 0:00:06.  Remaining: 0:00:16\n",
            "  Batch     200  of      536.    Elapsed: 0:00:09.  Remaining: 0:00:14\n",
            "  Batch     250  of      536.    Elapsed: 0:00:11.  Remaining: 0:00:12\n",
            "  Batch     300  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:10\n",
            "  Batch     350  of      536.    Elapsed: 0:00:15.  Remaining: 0:00:08\n",
            "  Batch     400  of      536.    Elapsed: 0:00:17.  Remaining: 0:00:06\n",
            "  Batch     450  of      536.    Elapsed: 0:00:19.  Remaining: 0:00:04\n",
            "  Batch     500  of      536.    Elapsed: 0:00:21.  Remaining: 0:00:01\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uXsVn0wngZhv",
        "outputId": "51c3b339-8c4c-439c-d584-140bce0a262f"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.87      0.82      0.84      1668\n",
            "Non_hope_speech       0.95      0.96      0.96      6205\n",
            "  not-malayalam       0.94      0.94      0.94       691\n",
            "\n",
            "       accuracy                           0.93      8564\n",
            "      macro avg       0.92      0.91      0.91      8564\n",
            "   weighted avg       0.93      0.93      0.93      8564\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "guClUdRhYPql",
        "outputId": "cef7dfca-3cbe-44ba-8bd4-8e25e4f23009"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VM2N-X1tV3il"
      },
      "source": [
        "## Evaluating Performance Over Validation Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BnadNvtxWIYw",
        "outputId": "f7046be9-604a-468e-c806-7f70285521cb"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      35  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wAjlATBPgh7c",
        "outputId": "0df058b2-0f83-4ff6-a4e8-7c202ca8e428"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.65      0.59      0.62       190\n",
            "Non_hope_speech       0.89      0.91      0.90       784\n",
            "  not-malayalam       0.83      0.79      0.81        96\n",
            "\n",
            "       accuracy                           0.84      1070\n",
            "      macro avg       0.79      0.76      0.78      1070\n",
            "   weighted avg       0.84      0.84      0.84      1070\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "7nELY57NYshD",
        "outputId": "694bd875-4d90-44a4-b0e8-5356600b7b98"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzAAAAHOCAYAAABHD+xbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdd1iTV/sH8G8ChL2XyBIHowKCinsUFRVx4MKBUuu21bZWfa2/TtuqfVupts46KgqCA7e4V3FVrXsPRBREQdkzAfL7g5e0MYwgCKb5fq4r12XOc86T+wGE3LnPOY9AKpVKQUREREREpAKE9R0AERERERGRspjAEBERERGRymACQ0REREREKoMJDBERERERqQwmMEREREREpDKYwBARERERkcrQrO8AiOpSl59P13cIRDUW2NqmvkMgqhWT2jnVdwhEtUJfJKjvEKDrPbXG58i/vLQWInnzmMAQEREREak6gfpMrFKfKyUiIiIiIpXHCgwRERERkaoT1P80trrCBIaIiIiISNWp0RQyJjBERERERKqOFRgiIiIiIlIZalSBUZ8rJSIiIiIilccKDBERERGRquMUMiIiIiIiUhlqNIWMCQwRERERkapjBYaIiIiIiFSGGlVg1OdKiYiIiIhI5bECQ0RERESk6jiFjIiIiIiIVIYaTSFjAkNEREREpOrUqAKjPqkaERERERGpPFZgiIiIiIhUHaeQERERERGRymACQ0REREREKkOoPmtgmMAQEREREak6NarAqM+VEhERERGRymMFhoiIiIhI1anRNspMYIiIiIiIVJ0aTSFjAkNEREREpOpYgSEiIiIiIpWhRhUY9blSIiIiIiJSeazAEBERERGpOk4hIyIiIiIilaFGU8iYwBARERERqTo1qsCoT6pGREREREQqjxUYIiIiIiJVxylkRERERESkMtRoChkTGCIiIiIiVadGFRj1uVIiIiIion8rgbDmj2oQi8X46aef0KlTJ3h6eiIoKAhnz55VauyZM2cwevRotG3bFj4+Phg2bBj27dun9GszgSEiIiIiomr57LPPsH79evTv3x+ff/45hEIhJkyYgMuXL1c67vjx4xg7diyKioowbdo0fPzxxxAKhZg+fTq2bt2q1GtzChkRKQj2sYWztQFcrAzQ0EQHyZkFGLb2Yrl9WzsYo2szCzhb66OxhT60NYX4aMt1XEnMUujbws4I3Zwt0MLOCNaG2pAUS/EkPR/bryTj6N0Xb/qyiAAAf+2OwMU9Gys8LtTQwISVewEAVw9tQ8LVc8h8noiC3Gzo6BvCpIE93Lv1h1PLjnUVMlG1tPRwLbddV1cPp89fquNoqM7U4RqYa9euISYmBnPmzMGYMWMAAIGBgejbty8WLlyIjRsr/h27ceNGWFpaYv369RCJRACAoKAgdO/eHbt27cLQoUOrfH0mMESkYFLnRsjMl+BeSi4MdDQq7evnZokerpaIf5GHhLQ8OFsZVNh3cudGsDQQ4eSDl3j4Ig86Whro5mKBrwNc0NLBGD8djqvtSyFS4NSyI4ysGiq0pyXG4+rBaDh4tpW1pcTfg6G5NRw8fKBjYITC3Gw8vHgKh1Z8j9YDRqNV35F1GTqR0rxbtsagIUFybZpafNv3r1aHa2AOHDgALS0tuWRDW1sbQ4YMwaJFi5CSkgIrK6tyx+bk5MDY2FiWvACASCSCsbExtLW1lXp9/iQTkYJha/9CcmYhACAsxAu6WhUnMatPP8bCI3GQFEsxvFXDShOYlScf4XpSFkqkf7dFX3qKX4Lc0c+jAaIvJSP+ZV6tXQdRecztnGBu56TQHhv+KwDAtVMvWZvfpDkK/Tx6DMS276fh6oFoePcZBqGw8iSfqD7Y2dkhoF//+g6D6lIdVmBu374NJycn6Ovry7V7enpCKpXi9u3bFSYwbdq0wW+//YbFixdj0KBBAIDt27fj0aNHmDNH8XdueZjAEJGCsuRFGS9yxEr3vVrOtDIpgBP3XsLLzhhOFnpMYKheSAoLEHfhD+ibWsDevVWlfYUaGtA3MUda0iOUFBczgaG3lkQihkQigZ6eftWdiQBkZWUhK0vxb7WRkRGMjIxkz1NTU2Ftba3Qz9LSEgCQkpJS4WtMnjwZjx8/xsqVK7FixQoAgJ6eHpYvX46OHZWbmssEhojqnZVhaRk5PU9Sz5GQunr410mI8/Pg3m1AuQlJQW42pCXFKMjJwsO/TuLJzYto6OIJTS1ROWcjqn9HDh/Cvpg9KC4uhqmZGXr28scH0z6BoaFhfYdGb0otTCFbv349li5dqtA+depUTJs2Tfa8oKAAWlpaCv3KpoAVFlb8QahIJEKjRo3Qu3dv+Pn5obi4GFu2bMEnn3yCsLAweHp6VhknExgiqlfm+iL082iApIx8XEtS/NSHqC7cOXUQEAjg0rFnucc3fzEeBTmlP59CDQ00btkRnYI/rMsQiZTm7uGJHj17wd7eEbm5OTh1Mhabozbi4l8XEBYRxYrMv1UtTCF77733MHDgQIX2f1ZfAEBHRwcSieKHjmWJS2VrWb777jtcv34d0dHREApLky5/f3/07dsX8+fPx6ZNm6qMkwkMEdUbbU0h5vV3ha6WEHN2PUDxPxfHENWRjGeJePbgJmzdvGBk2aDcPn5TvkCxRIzcjJd4+NdJFInFkBTkQ9fQpI6jJarahsgtcs/79g9EM2dnLPt1MSIjwjF+4uR6iozeJEEtJDCvThWriKWlZbnTxFJTUwGgwvUvYrEY0dHRmDRpkix5AQAtLS107twZUVFRKCoqgqZm5SkK7wNDRPVCpCHA/P6ucLE2wIJDD1h9oXpz59RBAPKL91/V0NkD9s1bwbVjT/T5+Dto6ehi139noDA3u67CJKqRkDHjoKWlhVOxJ+o7FHpDBAJBjR/KcnV1RXx8PHJzc+Xar169KjtenoyMDBQVFaG4uFjhWFFREYqKiiCVVv1hJhMYIqpzIg0B5g1wQytHE/x4+AEO306t75BITZUUF+Pe2aPQMTCCk3cHpcc5d+iBvMx0xF868wajI6o9WlpasLSyQkZGen2HQv8CvXv3hkQikbvxpFgsxvbt29GyZUvZAv+nT58iLu7vWySYm5vDyMgIhw8flpuClpubi+PHj8PZ2bnctTWv4hQyIqpTZcmLj6MJfjoch/03K96phOhNS7j6J/Kz0uHefQA0qrEgv1hcOs+7II8VGFINhYWFSHn+HO6eLeo7FHpT6m4XZbRo0QK9e/fGwoULkZqaCgcHB+zYsQNPnz7FggULZP1mz56N8+fP4+7duwAADQ0NjB07FosXL8awYcPQv39/lJSUIDo6Gs+ePcPs2bOVen0mMERUZ7Q0BPi+f2nyEnokDjE3ntd3SKTm7pw6BKD86WOSwgJAKoWWjq5ce0lJMW6e2AsAsHYqf5oEUX3JyEiHiYmpQvvypb+gqKgIXbr61kNUVBdqYw1Mdfz4449YvHgxdu3ahczMTLi4uGDVqlVo1aryreinTJkCOzs7bNiwAcuWLYNYLIaLiwuWLl0KPz8/pV6bCQwRKejpZokGRqU7iJjoakFLQ4iQtnYAgGdZhTj0jylfjS300KmJGQDAvWHpwr9e71jB07b039suJyNXXDrX9Ut/Z7RzMsWFhAwUFJXAz81S7nXjUnPx8AXvA0N1IzfjJZ7c/AtWTi7l3tgy83kS9iz8D5xadoJJAzto6xsiN/0l4i6cQMazRDi37wEbZ/d6iJyoYmt+W4nr166gdZu2sLFpiLy8XJw6GYu/zp+Du2cLDB85qr5DpDekrhMYbW1tzJ49u9KqSXh4eLnt/fr1Q79+/V77tZnA0Ftv9OjRyMrKwq5du+o7FLUR4G4Nb3tjubbxHR0BAJefZMolMM5WBrJj/xxf5tDtVFkC42JtAADwcTSBj6Pi7k3rzj5mAkN15u7pw5CWlFS4eF/f1ALN2nVH8v0beHT5DCSF+RDp6sPcvglaBoxA07b8JJvePq192uDhwwfYu3snMjMyINTQgIODIz786BOMCnm/0u1tSbXVdQJTnwRSZZb6q6Ht27djzpw52LlzJ9zc3BSODxgwAEZGRhVmllR7ajOB6fLz6VqIiKh+Bba2qe8QiGrFpHaKlS8iVaQvqv/kwWj4hhqfI2tTSC1E8uaxAkNEREREpOLUqQLDBIaIiIiISNWpT/7C+8DUltzcXMyfPx+dO3eGu7s7+vTpg8jISLk+iYmJcHFxQVhYGNauXYuuXbuiRYsWGDNmDOLj4xXOef/+fUydOhVt2rSBp6cngoKCcPp09adAxcTEYNCgQfD29kbLli3Rr18/rF+/XnZ8yZIlcHFxQXx8PD766CN4e3ujffv2+PHHH+X26C6zbds2DBw4EJ6enmjbti1mz56NFy9eKPQ7fvw4hg8fDi8vL7Rq1QoffvghEhISFPpdvnwZ48ePR+vWreHt7Y3AwEC5fcXL3Lt3D6NHj0aLFi3QuXNnrF69utpfCyIiIqJ/o7q8kWV9YwJThaysLKSlpSk8SkpKZH2kUimmTJmCDRs2wNfXF5999hlsbGwwd+5crFixQuGc27Ztw6ZNmzB69GiMHz8eN27cQEhICDIzM2V97t69i+HDhyMhIQETJ07ErFmzAAATJkzA2bNnlY7/9OnT+PTTT2Fra4vZs2djxowZaN26NS5duqTQ96OPPkJxcTFmzpyJ9u3bY+3atZg3b55cn6VLl+KLL75AkyZNMGfOHAQHB+Po0aMICQlBQUGBrN/27dsxZcoUmJiYYNasWZg0aRKuXbuGkSNHyiU7sbGxGD16NOLj4zFmzBj85z//gZeXF06cOCH3uhkZGRg/fjzc3Nwwe/ZsODk5YeHChfjjjz+U/loQERERkerjFLIqhIRUvJipTZs2AICjR4/i3LlzmDFjBiZOnAgACA4OxsSJE7F8+XIMGzYMZmZmsnGJiYk4ePAgrKysAADt2rXDqFGjEB4ejqlTpwIA5s+fD0dHR2zevFl2R9IRI0Zg4MCBWLRoEdq3b69U/CdOnECzZs2wZMmSKvs2atRI1i84OBja2trYtGkTxo0bB3t7eyQmJmL58uWYNWsWxo4dKxvXpUsXDB8+HDt27MCIESNk1ajg4GB8+eWXsn7+/v7o27cvwsLCMHPmTBQXF+Obb75BgwYNsGPHDhgaGsr6vrq3xLNnzxAaGoq+ffsCAIYMGYJu3bph27Zt6Nq1q1JfCyIiIqJ/K1WqoNQUKzBVmDt3LtatW6fwcHBwkPWJjY2FlpYWRo36e291gUCAkJAQiMVihYqJn5+fLHkBAB8fHzg7OyM2NhZAabXh3Llz6N27N7Kzs2VVn6ysLHTq1AnXr19Hfn6+UvEbGRkhOTkZV69erbLvyJEj5Z4HBwdDKpXi1KlTAIAjR45AKpXCz89Prhrl4OAAS0tLnD9/HgBw5swZZGdnw9/fX66fvr4+XF1dZf1u3ryJpKQkjBkzRi55Kfv6/ZOhoSECAgJkz0UiETw8PPDkyROlvg5ERERE/2bqNIWMFZgqtGjRotxtlPX09GT/TkpKgrW1tVwbADRu3Fh2/J8cHeXvmVHWdvnyZQDA48ePIZVKERoaitDQ0HLjysjIgK6ubrnH/mnkyJHYv38/goKCYGdnh44dO6J3797o0KGDQt9GjRqV+7ws/kePHqGkpAQ9evQo97XS0tJk/YDSBKg89vb2AEorUQDQrFmzKq/DxsZG4T+WsbEx7t69W+VYIiIion87VUpAaooJzFuobH3NhAkTyk00AMhNSauMubk5du7cidOnTyM2NhaxsbHYvHkzBg8ejPnz51c7Lg0NDaxevbrc/yRGRqV3Xi+b/hUaGlpunK9zEy2hkMXCuiAAMKRlQ/T3tEYDIx1k5ktw/O4LrD3zGAVFJVWOj/20Y7nteeJi9F76p0L7u83MEdSqIZpY6kMqBe6n5GDjhST8GZ9e00shNSYtKcH1o7twO3Yfsl88h46hMZq07oLWA0ZDS1un0rEZzxJxcc9GvHgch7zMlygpLoaBmSXs3X3QotcQ6Jso/k57FncbV/ZvxouEByjIzYa+iRkaunrB2z8IRpa8Zw+9vpKSEkRGbMD2rZvx9GkSTE3N4NerN6Z8+BF0X/nQtCbjJRIJflzwPW7euI5nyU+Rm5sLSysrNHf3xPvjJsDV7Z03eZlUW9Qnf2ECUxtsbW1x7tw55OXlyVVhynYWs7W1letf3k5cCQkJaNiwIYC/KxTa2toVJjDVIRKJ4OvrC19fX0ilUnz33XfYuHEjJk+eLDcV7tGjR7CxsZF7DkAWl4ODA4qLi+Ho6Ag7O7sKX68sfktLS7Rt27bKfvfv36+0H9Wdae86YUjLhoi9/xKbLz6Fo5kuBnvboJmVPqZH34Qyd729mpiJ3defy7UVFyuOHOlji8mdG+He8xysPf0YANDTzRI/BLph3v77OHwntTYuidTQmS2rcOPoLjTy7gBPv0FIT36CG8d24cXjOPT9dD4ElXwgkpOeirzMdDTy7gADUwsINIRIS3yE2yf3I+7CHxjy1TLoGpnI+j++8RcO/Po1jCxt0Lxbf+gYGCH9aQJux+5H/MVTGPrNCuibWtTFZdO/UOiPCxC1MRy+3f0w6r33Ef8wDpsiI3Dnzm2sXL2uyg/3lB1fJJHg1s0b8PJuCdt+A6Cvr4/k5KfYs3MHQkYOw9KVq9Gmbbu6uGQipTCBqQVdunTB5s2bERkZifHjxwMorUKEh4dDJBIpLLg/fPgwUlJSZOtgLly4gHv37skW8Jubm8PHxwdRUVEIDg5WqGKkpaUpXYFJT0+Hqamp7LlAIICLiwsAoLCwUK5vZGSkXKwbN26EQCBA586dAZSu3QkNDcWyZcuwYMECubElJSXIysqCiYkJOnXqBAMDA/z2229o1aoVNDXlf8zK4n/nnXdga2uLsLAwDBgwQGERvzqVQt8Gjcx1McjbBn/cf4Ev9/w9NS85sxCfdGuM7q4WOHJHcbvsVz3NLMDh25UnH6Z6Whjb3gEPX+RiUtQ1FJeUJjjbriRj7agW+LibE04/TEOeuLhmF0VqJy0pATeO7YZTy47oOeULWbuRhTVOb1qJBxf+QLO2vhWOt3Pzhp2bt0K7jbMHjvw2H3fPHIZX76Gy9uuHd0AgFGLAZ6HQNTSWtZs2dETshl8Qd/EkPHsMrKWrI3US9+A+NkVGoFsPPyxc9PdGPLa2dvjxh3k4uD8G/gH9amW8rp4eNm7epnCOIUHDEdCzG8LDfmcCowLU6X0TE5ha0K1bN7Rt2xahoaFITExEs2bNcOLECcTGxuLjjz9WSDbs7OwQHByM4cOHIz8/H2FhYbC0tMTo0aNlfb766isEBwejb9++GDp0KOzs7JCSkoKLFy+isLAQGzduVCq2L774ApmZmWjXrh2sra2RnJyMiIgIuLm5oUmTJnJ9Hz16hA8//BAdOnTAxYsXERMTg2HDhskqJY6Ojvjoo4+wePFiPHnyBL6+vtDV1cWTJ09w8OBBTJkyBUOHDoWhoSG+/PJLfPbZZxg8eDD69OkDExMTJCUl4dixY+jevTumT58ODQ0NfP311/jggw8QGBiIgQMHwsLCAg8ePMCzZ8+wdOnSGn5nqDp6uFhCKBBg66Vkufa9159hUmdH9HSzVCqBAQBNoQBaGgLkS8qfdube0BAiTSEO306VJS8AUFwixeHbqZjUuRE6NTHDoSoSIaJXPTh/ApBK4dE9UK7dtYs/zm1fh/t/Hqs0gamIoXnpB06FeTly7eKCPGhoaUFb30CuvWyqmZao8ilrRBU5sC8GUqkUI0e9J9c+cEgQfv3lZ+zbu6fSBKam4wHAzMwcIpEIWVmZlfajtwMTGKoWoVCIFStWYPHixdi/fz+io6Nhb28vS0JeNXjwYBQXF2PDhg1IT0+Ht7c3vvrqK5iY/D0twdnZGdHR0ViyZAm2bt2KrKwsWFhYoHnz5pVu7fyq/v37Y8uWLYiMjERWVhYsLS3Ru3dvTJs2TaH0/Ouvv+Lnn3/GwoULoa2tjbFjx+LTTz+V6zNlyhQ4Ojpiw4YNWLJkCQQCARo2bIgePXrITXcLDAyEtbU1Vq1ahVWrVqGoqAgNGjRAmzZt5HYT69q1K8LCwrB06VKsXbsWQOnmARVtAEBvjmsDAxSXSHH7WbZcu7hYigcpuXC1NqxgpLyuzSzg52YFTaEA6XliHLv7AmtOP0buP6opWhqlP3vlrasp/F9bcxtDJjBUbamP7kEgEMLKyVmuXVNLBHP7Jkh9dE+p8xRJxJAU5KNYIkZ68mOc2/Y7AMDB3Ueun33zVkh5eAfHfw+FV68h0DEwQlpSAs5uWQMTG3s0acNt3un13Lx5HUKhEO4ennLt2tracHFxxc2b12t9fHFxMbKyslBcXITnz55hQ9jvyMvLQ6fO/DlWBUxgCIMGDcKgQYMqPL5r1y655/r6+vj888/x+eefK3X+cePGYdy4cZX2cXR0xMKFC5U6X0V69eqFXr16KdXX3NxcqfvF9OnTB3369KmyX/v27ZW6X42Pjw/Wr19f4fHw8PBy23/44Ycqz03KszAQITNfAkk561VSc8TwsDWCplCAopKKV8LcSs7GiXsvkJhRAH2RBto5mWKwd0N42Rnjg03XZBWZRy/zAAAt7Y2x7bJ8xcfbvnQajpVh9Td7IMrLTIOOgRE0tEQKx/RNzPE87haKiyTQ0NSq9Dx3Th7A6ai/b0RsaG6NbuNmwcbZXa6ft38Q8rMzcPfUITw4d1zW7uDhg+4TZkOkU/VCa6LyvEhJgYmJKUQixZ9lKytrXL1yGRKJGFrl/Ky/7vj4h3EIGtRf9tzA0BDvj5+I98dPrIUrojdOffIXJjBEVEpbU1hu8gIA4uLSxENHS4icworXpUyOuib3/ODtVMS9yMPETo4Y4t0Q4edLt85++CIPFx6lo3NTc0zu7Ij9N1MAAP7NrdC2kaksHqLqKhIXQEOr/OSkLKkpEhdWmcA08moPkwb2kBTm48XjOCRc/RMFOVkK/QRCDeibmMPWzRtO3h2grW+AZ3G3cOPYbhxZ9QN6ffg1NDT5p5aqr6CgoNzkAwBE/9vNsyC/oMIE5nXG29raYcWq3yGRSPDkSQL27d2DnOwcSMRihfWsRPWJP40qqri4WHbflYro6elBX1+/jiIiVVdYVAJdXY1yj4nKpnxVsKalMlF/JWFMO3u0b2wqS2AA4OuYu5jdsymGt7bFSJ/SXe2SMwuw6NhDzO7ZlAv46bVoinSQn5VR7rFiifh/faqu7hmYWcLAzBIA4OTdAY1bdcL2eR+hSFwI7z7DZP2OrwvF87jbCJq7UnZep5YdYWzZECc3LsW9s0fg1rl3TS+L1JCOjk6Ff+fF/9uER0e34jVWrzNeV08Pbdv/PR18wMDBGBk0CDM/fYxlK9dUK36qe5xCRm+95ORkdO/evdI+U6dOxbRp0+ooIlJ1L3LEcDTTg5aGQKESY2kgQkaepNLpYxUpLpHiZa4Yxrryn3jnFBbjyz13YaqnBXtTXeSLi/EgNRdtnUorMAlpea9/MaS29IzNkP70MYolYoVpZLkZL0unl1VRfSmPuZ0TLOyb4OaJvbIEJvtlCh6cO47mvv0UkqLGrTvj5MalSL53nQkMvRYLKys8fBgHsVisUElJSXkOE1PTCqsvtTEeAPT09NGte0+E/b4aT548hr29Q6X9qX4xgaE3ws7OrtbuHG9paYl169ZV2qds97CqTJs2jYkO4c6zHLRpZAq3Boa4lvT3VBmRhgBNrfRxNVFx+owyRBoCWBqIcDM5u9zj6XkSpOdJZM/b/S+B4c0s6XVYNnJG4q1LSIm/J7depUgixssncbBx9njtcxdJxCjM/fvnODfjJQBAKlWsTJaUlFYQS4pZSaTX07y5B/48cxo3rl9Dy1atZe2FhYW4e/cOWrZsXcnomo//u38BACArMxNQ7m0F1RN1SmA4yVxFld3ksrKHsgkMEQAcu/cCJVIphraUv3N4X48G0NXSkLuxZENjHTiY6sr1M9Ip//OQcR0doakhxJmHVSckLtYGCHC3xuUnmbj+tPyEh6gyTXy6AAIBrh/dKdd+J3Y/isSFaPqPLZQzU54iPfmJXL+8zPKn3CTduYr0pARYNXaVtZk0sINAKMSjy2cVtle+d/owAMCqkfxuaETK6tnbHwKBAJER8pvc7IjegoL8fLktkJ88eYz4hw9fe3x6WhpKShQT8RcvUnH40AHo6emhcZOmtXFZRLWCFRgiAlC6sH7HlWQM9m6I7/sJcDY+HY3MdDHY2waXn2TiyD+2NF40pDlsjHXQ5efTsraQtvZ4x8YAl59k4nm2GHpaQrRzMkVLBxPcTM7Gtivyu42N6+AAOxMd3H6Wg1xxEZytDODf3Aovcgoxb79yW90SvcrczgnN3+2Lm8f34ODy7+Dg4YOM5Ce4cWwXbJw90KzNu7K+e3+eg5yXKZi0er+s7WTEUuRlpqGhqxcMza1QLBEjNeEB4i78AS0dXbQfOkHWV0ffEB49AnHt0HZs+3YqXDv3ho6+IZ7F3cL9c8dhZGkD187K7QJJ9Kpmzi4IGj4Sm6M2YsYn09CpcxfEP4zDpsgItGrtA/+AvrK+k8ePQfLTp7h0/c5rjd8XsweREevh280Ptna20NISIeFRPPbu3omsrCx8Ofd76OrKf2hFbx91qsAwgSEimSUn4vEsqxD9PBqgnZMpMgsk2HYlGb+feYyqVr9cScxEI3Nd9G5uBSMdLZRIpUhMz8eqUwnYcjEJ4lfW1dxLyUErB2P4NDKBtqYGUrILsf1KMiLOJ1a60xlRVToMnwRDC2vcjt2Px9fPQ8fAGM19+8NnwGgIhJVPPGja5l3cO3sU9/88ioLsTEAggKG5Fdy6+KNFryGyG1qWaTdkPEys7XDn1EFc3r8ZJUUS6JmY452uAWjdPxgiXW6kQq9v5uz/Q0NbW2yP3oJTsSdgYmqKYSOCMWXqRwr3cqvJeO+WrXDr5g2cjD2BF6mpkEgkMDc3R5t2HTBy1Gi08Gr5Ji+Taov65C8QSKXS6q/KJVJR/6wYEKmqwNY2VXciUgGT2jnVdwhEtUJfVP/Zg+2UHTU+R9KKgbUQyZvHCgwRERERkYpTpylkXMRPRP9fdBEAACAASURBVEREREQqgxUYIiIiIiIVp04VGCYwRERERESqTn3yFyYwRERERESqjhUYIiIiIiJSGeqUwHARPxERERERqQxWYIiIiIiIVJw6VWCYwBARERERqTgmMEREREREpDrUJ3/hGhgiIiIiIlIdrMAQEREREak4TiEjIiIiIiKVwQSGiIiIiIhUhhrlL0xgiIiIiIhUnTpVYLiIn4iIiIiIVAYrMEREREREKk6NCjBMYIiIiIiIVJ06TSFjAkNEREREpOLUKH9hAkNEREREpOqEQvXJYLiIn4iIiIiIVAYrMEREREREKo5TyIiIiIiISGVwET8REREREakMNcpfuAaGiIiIiIhUByswREREREQqjlPIiIiIiIhIZTCBISIiIiIilaFG+QsTGCIiIiIiVadOFRgu4iciIiIiIpXBCgwRERERkYpTowIMExgiIiIiIlWnTlPImMAQEREREak4NcpfmMAQEREREak6darAcBE/ERERERGpDFZgiIiIiIhUnBoVYFiBISIiIiJSdQKBoMaP6hCLxfjpp5/QqVMneHp6IigoCGfPnlV6/J49ezBkyBB4eXmhTZs2GDVqFK5du6bUWFZgSK1ET2hT3yEQ1Zhjl+n1HQJRrZhyfml9h0D0r1HXFZjPPvsMhw4dQkhICBwdHbFjxw5MmDAB4eHh8Pb2rnTsokWLsGbNGvTv3x/Dhg1DXl4e7ty5g9TUVKVemwkMEREREREp7dq1a4iJicGcOXMwZswYAEBgYCD69u2LhQsXYuPGjRWOvXTpEn777TcsWbIEfn5+r/X6nEJGRERERKTi6nIK2YEDB6ClpYWhQ4fK2rS1tTFkyBBcvHgRKSkpFY7dsGEDPDw84Ofnh5KSEuTm5lb7WpnAEBERERGpOIGg5o+srCwkJiYqPLKysuRe6/bt23BycoK+vr5cu6enJ6RSKW7fvl1hnGfPnoWHhwd+/vlntGrVCi1btkS3bt2we/dupa+VU8iIiIiIiFRcbdwHZv369Vi6VHFt2tSpUzFt2jTZ89TUVFhbWyv0s7S0BIAKKzCZmZnIyMhATEwMNDQ0MHPmTJiYmGDjxo2YNWsWdHV1lZpWxgSGiIiIiEjF1cYi/vfeew8DBw5UaDcyMpJ7XlBQAC0tLYV+2traAIDCwsJyz5+XlwcAyMjIwJYtW9CiRQsAgJ+fH/z8/LBs2TImMEREREREpBwjIyOFZKU8Ojo6kEgkCu1liUtZIvOqsnY7OztZ8gIAIpEIvXr1woYNG5Cbm6swNe1VTGCIiIiIiFRcbUwhU5alpWW508TKtkG2srIqd5yJiQlEIhEsLCwUjllYWEAqlSInJ6fKBIaL+ImIiIiIVFxd7kLm6uqK+Ph4hR3Erl69KjteHqFQCDc3Nzx//lzh2LNnz6ChoQFjY+MqX58JDBERERGRiquNXciU1bt3b0gkEmzdulXWJhaLsX37drRs2VK2wP/p06eIi4tTGJucnIzTp0/L2nJycrB//354e3tDR0enytfnFDIiIiIiIhVXl1PIWrRogd69e2PhwoVITU2Fg4MDduzYgadPn2LBggWyfrNnz8b58+dx9+5dWduIESOwdetWTJs2DWPGjIGRkRG2bduG7OxsfPrpp0q9PhMYIiIiIiKqlh9//BGLFy/Grl27kJmZCRcXF6xatQqtWrWqdJyuri42bNiAH3/8ERERESgoKEDz5s2xbt26KseWEUilUmltXASRKkjJVtwxg0jVOHaZXt8hENWKtPOK95sgUkW6ijsK1znfX87U+BzHP+5QC5G8eazAEBERERGpuLqcQlbfmMAQEREREak4NcpfuAsZERERERGpjmpVYGJiYhAeHo6EhARkZGQoHBcIBLh161atBUdERERERFUTqlEJRukEZs2aNQgNDYWJiQlatGgBU1PTNxkXEREREREpSY3yF+UTmMjISLRo0QJhYWFK3WCGiIiIiIjqhjot4ld6DUxqair69evH5IWIiIiI6C0jFNT8oSqUTmAcHR2RnZ39JmMhIiIiIiKqlNIJzPvvv4/o6Gjk5ua+yXiIiIiIiKiaBAJBjR+qQuk1MBoaGjA3N4e/vz8GDx4MOzs7aGhoKPQLDAys1QCJiIiIiKhyKpR/1JjSCcxnn30m+/eKFSvK7SMQCJjAEBERERHVMQHUJ4NROoHZsGHDm4yDiIiIiIioSkonMG3atHmTcRARERER0WtSpV3EakrpBIaIiIiIiN5OqrQIv6aUTmCWLl1a6XGBQAAdHR3Y2Nigbdu2MDc3r3FwRERERERUNTXKX6qXwJRldlKpVO7Yq+2ampoYN24cpk+fXltxEhERERFRBYRqlMEoncDs3bsXs2fPhkgkQkhICJycnAAADx8+xIYNG1BcXIwvv/wSycnJWLduHVatWgUbGxsMHz78jQVPRERERETqRekbWW7ZsgXa2tqIiIiAv78/XF1d4erqij59+iAiIgKampqIiYlBr169EBERAWdnZ2zevPlNxk5ERERERCidQlbTh6pQOoHZt28f/P39y715paamJvz9/RETEyP3PD4+vvYiJSIiIiKicgkEgho/VIXSU8iys7ORnZ2t9HFTU1OV+kIQEREREakqdXrbrXQFxtXVFZGRkUhKSlI4lpiYiKioKLi5ucna4uPjYWlpWTtREhERERFRhYQCQY0fqkLpCsyMGTMwbtw49OnTBz169ECjRo0AlCYqR48eRUlJCUJDQwEAYrEYe/bswbvvvvsmYiYiIiIiIjWldALTpk0brFu3Dj/88INsrUsZd3d3zJ49Gz4+PgAAkUiE48ePQ1OT98kkIiIiInrTVKd+UnPVyjBat26N6OhovHz5EomJiQAAW1tbWFhYKPQViUS1EyEREREREVVKndaev1aJxNzcHObm5rUdCxGpgM6t3ctt19XVxaGTF+Tajh85iC2RG/Dg3j0IhAI0c3bFqDHj0b5Tl7oIldTc55P64IvJfSo8LpEUw6jNxwCA1s0dMSLAB95u9vBwtoOBnjYmfBWOiD3nqnydBhZGuLTtC5ga6WHOzzuwOPxorV0DUWXWrv4Nt2/fxO1bN5GUmAibhrbYf+hYuX3PnjmNo4cP4tatm3hw/x7EYjFW/74BPm3a1nHU9KYI1Sd/eb0EhojUWwvvVug3cIhc26tTRjeGrcXKpYvQzMUN4yZPBQAc2r8Xs6d/iC++XYCe/n3rLF5ST7uOXUHck1SFdo9mDfHpGD/si70ua+vVqTkmBXXB3UfPcf1eItp7NVH6dX6ePRSaGkrviUNUa5b88jOMjU3g6vYOsrMq3ikWAPbF7MH+mL1o2qwZnBo3wd07t+soSqLaV2EC4+rqCqFQiCtXrkAkEsHV1bXK0pRAIMCtW7dqPUgiervY2NqhV59+FR5Pe/kCa39bisZNmmHV+khoamoBAIYMH4lxwUFY/NN8dOz8LvQNDOoqZFJDN+4/xY37TxXaO34+HAAQtvOsrG311pNYtP4I8grEGNjDS+kEJqCrB/r7tsCXv+7C/OkDaydwIiXt3X8Edvb2AIDBgX2Rl5dXYd+pH03Hl19/C5FIhPXr1jKB+RfiFDIAgYGBEAgEshtXlj0nIgIAiUQCiUQCPT09hWM3rl2BRCKBn3+ALHkBAE1NLfTo3Qerlv2Ck38cQ++A/nUZMhH0dEQY2qsVEp+l49CZvz9wS0mr/NPr8hjoaWPxZ0FYvfUk/rr5uDbDJFJKWfKiDGtr6zcYCb0N1OlteoUJzA8//FDpcyJSX38cPYTD+/eiuLgYJqZm6ObXGxM+mAYDA0MApVupA4COjo7C2LK2WzeuMYGhOjfIzxvGhrpYvukESkqkNTrXd9P6Q0NDiK+X7UELF+XfSBIRvQnqVGjgGhgiqha35h7w7dETtvYOyMvJwdnTJ7F9SySuXLqAFb9vhJ6eHpyaNAUAXLxwHkOGj5Ibf+mv0oX+Kc+e1XnsRGMC26OkpATrd/5Zo/O08WiECUM7Y8z/hSErp6CWoiMien1cxK+EJ0+eICYmBs+fP0fTpk0xePDgcj9tJaJ/l1Xro+Se9+47AE2aOWP18l8RHRWOkHGT0KSpM3zatsepP45h+S+h6NM/EACwf88unDtzEgBQUMg3fVS3mjlaoWPLpjh27g4Snr587fNoagqx7MuROPrnHUQfulSLERIRkTIq3TZl69at6N+/P16+lP9Ff/r0afTv3x+//PILoqKi8P3332Po0KHIzc19o8ES0dtpZMj70NLSwtnTsbK2uQsWoqtvD2yKCMPooQMweugAHD9yENNnfw4A0NfXr69wSU2NCWwPAAjbcbaKnpWbMcYPTewt8MkPW2ojLCKiWiEQCGr8UBWVVmBOnDgBfX19uXu+SKVSfPXVVygoKMDEiRPh5eWFw4cPY/v27QgLC8OHH374xoMmoreLpqYWLCytkJGRIWszNDLG9z8tRtrLF3jyOAG6unpo6uyCc2dOAQAcGjnVV7ikhjQ0hBjZty1epOdg17Grr32eBhZGmD2uFyL2nodAADS2L72Rs62VMQDAzEQfje0t8Cw1C3kF4lqJnYhIGaqTftRcpQnMnTt34O/vL9d26dIlJCUlITAwENOnTwcA+Pr6IikpCUePHmUCQ6SGCgsLkfL8OZp7eCocMzO3gJm5hez5n6dLp5C178ibWVLdCejijgYWRli68TjEkqLXPo+VmSF0dUSYMKQTJgzppHB81tiemDW2J0bOWoMdR67UJGQiomoRqlAFpaYqTWDS0tJg/8oWfZcuXYJAIFBIbLp27Yply5bVfoRE9NbIzMiAsYmJQvualUtQXFyEDp3frXT8nVs3sHfXNni1bA1Pr5ZvKEoiRe8FdgAgf++X1/Ho6UuMnLVGod2tsQ2+nBKAiD3nsC/2Os5dja/R6xARVZca5S+VJzCampqQSCRybdevl9652MvLS67dxMREtnUqEf07rV/7G27duAbv1j6wtrZBfn4e/jx9Epf+Oo933D0xZNhIWd81K5bgyeMEuDX3gIGBAe7dvY19u3fCwtIKX3y7oB6vgtSNjaUxenZww4Xrj3DzgeKNLQHAwcYUIwLaAADeaWIDoPQmlbbWpQl7VMx5PE5OR1ZOQbmVlRetSteA3rz/lJUXqjN7d+9EcnLpz3R6WhokRRKs/m05AMDGpiH6/m8DFQC4d/cO/jhxDABw5XLp5hMxe3bhyuWLAIDhI0fD0NCwLsMnem2VJjC2tra4fPkyRo0q3Qa1uLgYFy9ehKOjI4yNjeX6ZmRkwNTU9M1FWg/OnTuHkJAQLFu2DD169KjvcNTW9u3bMWfOHOzcuRNubm71HY5a827lg0fxcTiwdzeyMjMgFGrAzsEBEz74CMOC34O2trasr7OrGy5e+BMXzp1BYUEBrBrYYPCwkRj1/ngYGhrV41WQuhnVry00NTWwbseZCvs4NrTANx/2k2sL7O6FwO6lH9adufwQj5PT32icRNW1Y/s2XPzrvFzbsiW/AABatW4jl8Dcvn1LdqzMzh3bZP/u07c/ExgVp0qL8Guq0gSmZ8+eWL58Oby9vdGuXTts27YNaWlpGDx4sELfa9euwc7OrlovXvbGVEdHB0eOHIGlpaXc8QEDBsDIyAjh4eHVOi8RvRmd3+2Gzu92U6pvF98e6OLLxJ/q30+/H8JPvx+qtM/Ji/eh6z31tV+jpuOJXsfaMOXfHw0IHIQBgYPeYDRU39Qof6l8G+WQkBDY2tpi3rx56NevH9atW4cGDRrg/fffl+uXnZ2NP/74A23btn2tIAoKCrB27drXGktEREREpO6EAkGNH6qi0gqMgYEBtm3bhi1btiAhIQEODg4YOnQojIzkp3/ExcVh0KBBCAgIeK0g3NzcsGnTJkyYMEFuy2YiIiIiIqJ/qrQCA5QmMWPHjsXcuXMxbtw4heQFKF3Q/+WXX6Jp06avFcSkSZMgFourrMLk5uZi/vz56Ny5M9zd3dGnTx9ERkbK9UlMTISLiwvCwsIQFRWFHj16wN3dHYMHD8a1a9deK76SkhIsW7YMnTt3hoeHB9577z0kJCQo9Nu3bx8CAwPh4eGB9u3b4//+7/+QlpYm12f06NEYMGAArl27hmHDhsHT0xN+fn7Yvn27wvkKCgqwaNEidO/eHe7u7vD19cUvv/yCoqLqbQH66NEjTJs2DR07doSHhwe6dOmC6dOnIzs7G4D812zt2rXo2rUrWrRogTFjxiA+XnEnnfv372Pq1Klo06YNPD09ERQUhNOnTyv0S05Oxn/+8x+0b98e7u7u6NevH/bu3avQLyMjA99//z18fX1l1/l///d/yMnJketXWFiIefPmoV27dvDy8sKHH36o8PUlIiIiUkcCQc0fqqLSCkxdadSoEQICAhAVFYXx48fDzMxMoY9UKsWUKVNw/vx5BAUFwdnZGcePH8fcuXORmZmJKVOmyPXftWsX8vLyMGzYMAgEAqxZswbTpk3DkSNHoKWlVa34VqxYAaFQiPHjxyMrKwtr167FzJkzsXXrVlmfsvU8Xl5emDVrFpKTkxEREYHr168jOjpabnFzRkYGJk2ahL59+yIgIAAxMTGytUB9+vQBUJo0TZ48GVevXsXw4cPRqFEj3Lx5EytXrsSzZ8+wYIFyuziJxWKMGzcOGhoaGDNmDExMTPDs2TMcP34cWVlZcgv2tm3bhoKCAowePRr5+flYv349QkJCsHfvXtmmDXfv3sXIkSPRsGFDTJw4Edra2tizZw8mTJiAtWvXon370jtdp6SkICgoCFpaWggJCYGxsTGOHj2KGTNmQCwWY9Cg0nm4OTk5CA4OxqNHjzBkyBC4ubnhxYsXOHToEDIyMmBgYCCLb+7cuTAxMcG0adOQmJiI9evX49tvv8XixYur9f0kIiIi+rfhIv56MGXKFOzduxfr1q3DjBkzFI4fPXoU586dw4wZMzBx4kQAQHBwMCZOnIjly5dj2LBhconPs2fPcOjQIdkbdCcnJ3zwwQc4deoUfH19qxVbUVERtm/fLkt8jI2NMW/ePNy7dw/Ozs6QSCRYuHAhXF1dER4eDpFIBABwd3fHp59+ii1btmD06NFysX3xxReytmHDhmHgwIEIDQ2Fv78/BAIBdu/ejfPnzyMqKgotWrSQjbWzs0NoaCjGjx+PJk2aVBl7XFwcEhMTsXXrVnh6/n2TwWnTpin0TUxMxMGDB2FlZQUAaNeuHUaNGoXw8HBMnVq6OHX+/PlwdHTE5s2bZV+PESNGYODAgVi0aJEsgVm8eDGEQiF27twpq9qNHDkS48ePx88//4zAwEAIhUKsWbMGDx48wIoVK9Ct29+Lw6dOnQqpVCoXn5mZGdasWSP7D1pSUoLw8HBkZ2dz5xQiIiJSa1VOq/oXeWuutXHjxujTpw8iIiKQkZGhcDw2NhZaWlqyLZ2B0kwzJCQEYrEYZ8/K35wsICBA7k1t69atAQBPnjypdmyDBw+Wq9q8eq4bN27g5cuXCA4OliUvAODv7w9ra2ucOHFC7nwikQhDhw6VPdfW1saQIUOQmJiIhw8fAgAOHjyIZs2awd7eHmlpabJHWYJw/rz8tokVKatgHD9+vMr79Pj5+cmSFwDw8fGBs7MzYmNjAZRWjs6dO4fevXsjOztbFlNWVhY6deqE69evIz8/H1KpFIcPH0a3bt1QVFQkF3/nzp2Rmpoqm5p2+PBhNG/eXC55KfPqJwnDhw+Xa2vdujWKi4uRlJSk1NeCiIiI6N9KIBDU+KEq3poKDAB88MEH2LdvH9atW4fp06fLHUtKSoK1tTX09PTk2hs3biw7/k8NGzaUe142BSorK6vacdnY2Mg9L6solJ3r6dPSm0g5OTnJ9RMKhXB0dJQdL2NtbQ0dHR25NkdHR9l1NGnSBAkJCYiLi5MlLK9Sdu2Hvb093n//fSxfvhxhYWFo06YNfH190bdvX7npWf+M4dW2y5cvAwAeP34MqVSK0NBQhIaGlvt6GRkZEIlEyMrKQmRkpMIapTLp6aX3U3jy5Ils2lxVqvo+EBEREdG/31uVwDRp0gT+/v6IiIjA2LFja3QuobD84tKr05KUoaGhUWvnUlZJSQneeecdzJo1q9zj9vb2Sp/rs88+w6BBg3D06FGcOnUKc+fOxcqVK7F582ZYW1tXKyYAmDBhAjp06FBuHzMzM1lCMWjQIPTr16/cfs2aNVP6dcvUx/dB3ZSUlGBrVAR2b9+KZ8lJMDE1hW+P3hg3+UPo6urV6nipVIojB/dh+5ZIPElIgFgihnUDG3Tz642gEaOh/0qCTaQsgUCAqSPfxbjBHeHY0Bwv0nOw7fAlfLs8BnkFlVeiAcDKzBBfTAmAf6fmsDI3xPMXWdh9/Cq+W7EPmTn5cn1bN3fEiAAfeLvZw8PZDgZ62pjwVTgi9px7U5dHaqSkpAQbIzZg29ZNeJqUBFNTM/Ts7Y8PPvwIunrK/U5WdvzBA/tw+tRJ3Ll1Ew8fxqGoqAgxB4/C1rZ69/ij+iNUnQJKjb1VCQxQWoXZv38/1q9fL9dua2uLc+fOIS8vT64KUzYVydbWtk7j/Keyak98fDx8fHxk7VKpFAkJCQpv1p8/f46CggK5KkzZrmZl1+Hg4IAHDx5UmChUl7OzM5ydnTFlyhRcvXoVQUFBiIqKwieffKIQwz8lJCTIrq8sadLW1q40LjMzM+jr60MqlVYZv4ODA+7du/c6l0RvwJKf/4voTRvRxbc7ho16DwnxDxG9aSPu372NRcvXVPjBwOuMX738V4SvW42WPm0xZsIUaGpq4vLFC/j9t2X48/RJrFy3UaXK2fT2+GnmIHw40he7jl7BL+HH4Nq4AT4Y/i5auNihz+SllX7oYWlqgNjwmbCxNMbabadx88FTNG/aEBOGdkbHlk3R7f2fkV8gkfXv1ak5JgV1wd1Hz3H9XiLae1W9NpFIWT/9dz6iNoajW3c/jH5vLOIfxiFqYzju3L6F39aEVfk7uTrjt2yKwo3rV+Hs4go7e3s8KmcXUnq7MYGpRGJiIs6ePYsXL16gX79+sLOzg1gsxosXL2BhYSG3BuR1NG3aFL169cKGDRtgZGQkmybUpUsXbN68GZGRkRg/fjyA0gShbNF8RVOt6oK7uzvMzc0RFRWFwMBA2dfgwIEDeP78OSZMmCDXXywWY+vWrbJF/GKxGNHR0bC1tZVNievVqxf++OMP7NixAwMHDpQbn5ubC01NTbmdzSqSk5MDHR0daGr+/a1u1qwZNDU1UVhYKNf38OHDSElJka2DuXDhAu7duydbwG9ubg4fHx9ERUUhODhYYbe4tLQ0mJmZQUNDA35+fti3bx8mTpwou6ZX+wFAjx49sGLFChw7dkxhHYxUKuUb2DoUH/cA2zZHoqtvD3z/0987u9k0tMUvCxfg6KH98Otd8b2eqjO+qKgIW6Mi4Oz6DhYtWy37Ixo4ZBg0NDVweH8MHty7i2Yurm/oaunfyq1xA0wZ3hU7j17BiJlrZO2Pkl7i59lDEdSrFTYf+KvC8f8Z1wuODc3x3px12HLgoqz9z6sPsX7B+/hoVDf8d81BWfvqrSexaP0R5BWIMbCHFxMYqjUPHtzHpsgIdO/RE6GLl8jabW3t8N8F3+PA/hj0CSh/lsPrjP9+wX9haWkFTU1NLJj3LRMYFaRO75mqlcD89NNPCAsLQ3FxMQQCAby8vGQJTEBAAD7++GOMGTOmxkF98MEHOHDgALKzs2UViW7duqFt27YIDQ1FYmIimjVrhhMnTiA2NhYff/xxuVsv1xUtLS3MnDkTc+bMQUhICAICApCcnIzw8HA4OzsjKChIrr+1tTWWL1+Ox48fw8HBAXv37kVcXBxCQ0NlP3yBgYHYt28f5syZg9OnT8Pb2xsSiQQPHjzA/v37sX379nLXrLzqzz//xLfffotevXrByckJJSUl2L17NwQCAXr16iXX187ODsHBwRg+fDjy8/MRFhYGS0tLuR3UvvrqKwQHB6Nv374YOnQo7OzskJKSgosXL6KwsBAbN24EAMyYMQPnzp3D4MGDMWzYMDRu3Bjp6em4fv06bt26hWPHjgEAxo8fjwMHDmDatGmybZTT0tJw+PBhLFmyBHZ2LF3XlSMH90EqlWLoyNFy7f0GDsFvSxfj0L69lSYw1RlfXFSEwsICmJmbK3yCaGFRmkDr6OrWxmWRmgnq3RpCoRBLNx6Xa/99+2l891F/DA/wqTSB6eLTDHn5YrnkBQC2HryElV8HI6R/O7kEJiUtu3YvgOh/DuzbC6lUiuDR78m1DxoShF8WhyJm7+5KE5jqjrexafjqKUjFsAJTjk2bNmHt2rUYPXo0fH195daoGBgYoFu3bjh+/HitJDDOzs7o2bMnDh78+4+EUCjEihUrsHjxYuzfvx/R0dGwt7eXvaGub4MGDYK2tjZWr16N//73vzAwMEC/fv0wc+ZMhUqJqakpvvvuO3z//ffYtGkTrK2tMW/ePPTt21fWR0NDAytWrMDvv/+O3bt348CBA9DX14eDgwMmTpyo9NoVFxcXdOrUCSdOnMDmzZuhq6sLFxcXrF69Gl5eXnJ9Bw8ejOLiYmzYsAHp6enw9vbGV199BRMTE1kfZ2dnREdHY8mSJdi6dSuysrJgYWGB5s2bIyQkRNbPysoKW7duxdKlS7F//368fPkSJiYmcHFxwccffyzrZ2BggMjISPz66684cuQItm3bBktLS3Ts2BGmpqbV+h5Qzdy+dQNCoRBuzT3k2rW1tdHU2QW3b92otfHaOjpo4d0K58+exsawteja3Q8aGhq4fPECdkZvQk//vrB3qDpBJ3pVq+aOKC4uwYUb8lNiC8VFuHY3Ea2aO1Q6XltLEwViiUK7VCpFfqEEje0tYW6ij5cZubUaN9Grbt4o/Z3q7uEp166trQ0XF1fcunH9jY4nepspncBERkbCz88Pn3/+uWwHqX9ycXHBhQsXqvXigwYNkt3Q8FW/9RcmzQAAIABJREFU/vqrQpu+vj4+//xzfP755xWe087ODnfv3i33WEXtFWnbtm25Yyp6jYCAAAQEVPwJ9T95enpiy5YtlfYRiUSYPHkyJk+erFzA5bC3t8f8+fOV7j9u3DiMGzeu0j6Ojo5YuHBhleeytLTE3Llzq+xnZmaGb775Bt988025xyv6Oano+0Ov52VqKoxNTMqdBmppZY0b165AIpFUeCPY6o7/6vv/Yv43n2Pl0kVYuXQRgP9tjT52IsZNnlqLV0bqxMbSGC8yciCWFCkce5qSifZeTaClqQFJUXG5428/fAYXpwbwdLbFtXt/727p6WwLM2N9AIB9A1MmMPTGpaamwMTEtNzfqVbW1rh65TIkEjG0tMqful/T8aR61GgGmfIJzKNHjzBixIgKj5uampab2BCRaigoyK/wD1nZH8DSPuUnMNUdryUSwcbWDr0D+qNth04AgD+OHcH6tb9BJBIhZNykGl0PqSc9HS2IxYrJCwBZZUVPR6Swm1iZpRuPo9+7noj4cRxmLYzGrQfJcGtig59mDoZYUgSRlib0dPiGj968gvz8CtcVa4tKZ3bk5xdU+Hu3puNJ9QjVKINROoHR1tZGfn75v/CB0nuhlC24f9uJxWJkZmZW2sfQ0FDhXi1vm4yMDEgkilMdymhoaNTr2iBSLTo6ukhPf1nusbKboOroVLwupTrjCwryMWXsKDi7uGHugr+reT169cHXc2Zi7W/L8G73nnD4f/buO77Gs/Hj+OdkD0kkxIg9E0SUoDWKhJolNi0ParRatFVVPK1Wa7WltPRp0WGktiRWbKqlS6k9a5MYMUNkJ78/8svhyBBkOPJ99+XV5jr3uE56O+f+3tcqWy7d44lk5E5MPO5u6U9wYmdj/f/bZDyV8m+7T9Br5Gwmv9eZ5dPfACAhIZHZy//g8IkLBDR9hsiomOyvuMh97OztuXY1/c/U2LiUSXjs7TO+T3nc/cX8PDGr0+eCLAcYHx8fNm7cmO76LLGxsaxYsYJatWpla+Vyyu7du03Ga6Rn4sSJGXZve1IMGTKEHTt2ZPh6iRIljIPlRR6kkLs7p0+dIC4uLs1Tu4jLl3Ap6Jph68vD7r910wbOnz3Da4PeTnMcv2Yt2LJxHfv2/KMAIw/tQsRNqpQvho21VZpuZB5FXIi4fivD7mOpgjftZvmWPXhX9MDJ0Y5jpy8Rcf022wLfJT4+kRPnInLyLYgA4O5ehJMnjqf7mXr50iVcXV0zbT153P1FnmRZDjCpYyOGDx9Op06dALhy5Qrbtm1j+vTpXLp0KcPV2Z80Xl5ezJ49O9NtKlasmCPnDgwMzLZjjRgxItNV6LMyzTJkPm5I8o8qVb35+8/fOXxwPzVq+hrLY2NjOX7sKDVq+Way98PtHxFxGYCkpLQ3komJCf//78xvMkXSs+vgGV6oX4U63mX4bfcJY7mtjRU+niXZ/s/xLB0nKSnZZAxM0UJO1PAsxbZ//jVZB0Ykp1Tz9uaP37dzYP8+avnWNpbHxsZy9OgRfO8py4n9xfzkox5kWQ8w9evXZ8yYMYwfP57Vq1cD8N577wEp0wiPHTuWmjVr5kwts5mLi0u2LRCZl7y9vfO6CvIU8W/eksDZ37F0QaBJAFkVsoyYmGiTKZTDzp8lISGBMmXLP9L+ZculrJWxdvUK/F9oaVKPdatXAuBVTde3PLxlG/7hvX7NGdzDzyTA9O3YAEd7WxatuTuFcrmShbG2suTY6UuZHtNgMPDFe12wtDSYTKEskpNatGzND9/NZH7gXJMAErxsCTHR0SZTIJ87e5aEhHjKla/wSPvL00FjYDLQrVs3/P39WbduHSdPniQ5OZmyZcvSqlWrLE/rKyJPpgoVK9Ohy0sEL1nA+8Pf4rkGz3Pm1CmWLZrPM7VqmwSQt1/vz8UL4WzbeeCR9q//fGOqVKvOn79tY/CA3jTyawbArz9vYu/uXfg1a4GnV9Xce/Py1Dh4PJyZS7bxevfGLJrcn3W/HcSrXDHe6N6EX3f+y+K1dwPM2plDKONRCPuad2e9c7S3YdtPw1m5ZR+nw6/gUsCeLi1r41u1NB9OX8mvO/81OV/p4q681KYuAFUrFAegTePqlCiaMv38wtAdnL2gCW7k4VWq7Em3l3qwaMFPvPPWYBo+35hTp06wcH4gvrXr0uqeAPJq/z5cCA9jz4Gjj7Q/wK6df/PPrpTZZA8dTPlsX7xgPk7OTgAMeO2NnH7L8pjyUX7BkJycnJzXlRDJLZdvqetHZhITE1m6MJCVwcu4eCEMl4Ku+L/Qkn4DB+Pg4GDcrkvb5mkCzMPsD3AnKorAOd/x65bNXAg/j8FgoGSpMjRv3ZZuPXphZfVQz1fylTKNhuZ1FZ5oFhYGhvTwo2/HBpTxcOPqjSiWbfiHT75ZTVT03QH8R0I/ThNgrK0s+X7sf6hbvSzFCrtwJyaOXQfPMu2nLWz643Cacz3vW4kN37+VpjxV8/5fsW3Xvxm+nt9d2/F1XlfhiZaYmMj8wLkELVtMeFgYBV1dadGyNW8MfhMHB0fjdq2a+6cJMA+zP8C3/5vOzG8z/v9x/7HFlH3GQ0RzzZgNj/9ZM6Z5pWyoSc5TgJF8RQFGngYKMPK0UICRp0V+DDBxcXF89dVXrFixgsjISLy8vBg6dCj16tV7qHMOGDCAX3/9lV69emW61uO9svyI80GzdkFKP+G5c+dm9ZAiIiIiIpINcnsMzMiRI9mwYQO9evWiTJkyhISEMGDAAAIDA7M8Ln7r1q3s3LnzwRveJ8sB5vz582nKEhMTiYiIICkpCVdXV+ztM14jQkREREREckZu5pd9+/YRGhrKqFGj6NOnDwDt27fnxRdfZPLkycyfP/+Bx4iLi2PixIn069eP6dOnP9T5sxxgMlpPJC4ujtmzZxMcHJytUwSLiIiIiEjWWORigFm3bh3W1tZ06dLFWGZra0vnzp2ZOnUqly9fpkiRIpkeY968ecTExDxSgHnsRTttbGx47bXX8PHx4dNPP33cw4mIiIiIyEMyZMM/WXX48GHKlSuHo6PpZBA+Pj4kJydz+HDaSU/uFRERwTfffMPQoUMfqQdXtk3z4+vry5QpU7LrcCIiIiIikosiIyPTXSTd2dkZZ2dn488RERHpLqHi7u4OwOXLlzM9z5QpUyhXrhwBAQGPVM9sCzDnz58nPl4zPImIiIiI5Lbs6EI2d+5cvv467eyAgwcPZsiQIcafY2JisLZOO/Wara0tALGxsRmeY9++fSxfvpzAwEAMjzhwJ8sBJjw8PN3ymzdv8vvvvxMYGEjdunUfqRIiIiIiIvLosiPA9O7dmw4dOqQpv7f1BcDOzi7dhovU4JIaZO6XnJzM+PHjad68ObVr137kemY5wPj7+2eYkpKTkylXrhwffPDBI1dEREREREQezaO2Ztzr/q5iGXF3d0+3m1hERARAhgP4N27cyL59+xg6dGiaGY5v377N+fPnKVy4MHZ2dpmeP8sBZtCgQen+YgoWLEjZsmWpX78+FhaPPSeAiIiIiIg8wby8vAgMDCQqKspkIP/evXuNr6cnPDycpKQkevfunea14OBggoOD+e6772jUqFGm589ygLm335uIiIiIiDw5cnMa5ZYtW/Ljjz+ydOlS4zowcXFxBAcHU6tWLeMA//DwcKKjo6lQoQKQ0qOrZMmSaY43aNAg/Pz86Ny5M9WqVXvg+bMUYKKioggICKBnz57GSoqIiIiIyJMhNxeyrFGjBi1btmTy5MlERERQunRpQkJCCA8PZ+LEicbtRowYwY4dOzh69CgApUuXpnTp0ukes1SpUjRr1ixL589SgHF0dOTGjRtp5noWEREREZG8Z5GbCQb4/PPP+fLLL1mxYgU3b97E09OTWbNm4evrm+PnNiQnJydnZcN+/fpRokQJPvnkk5yuk0iOuXxLU32L+SvTaGheV0EkW1zbkXa6VhFzZJ92RuFcN237qcc+xpsNy2VDTXJelkfdv/vuu6xbt46goCCymHlERERERESyVaZdyMLDw3Fzc8POzo6JEyfi7OzMBx98wKRJkyhdunSaKc4MBgNz587N0QqLiIiIiIipXO5BlqcyDTBNmzZl0qRJvPjii8a5mosXLw7AlStXcr52IiIiIiLyQBbknwSTaYBJTk42dhfbsmVLrlRIREREREQejlpgRERERETEbOTmOjB5LcuD+EVERERERPLaA1tgdu7cSWJiYpYP2L59+8eqkIiIiIiIPJzcXgcmLz0wwCxZsoQlS5Y88EDJyckYDAYFGBERERGRXJaP8suDA0zXrl155plncqMuIiIiIiLyCNQCc4/atWvTtm3b3KiLiIiIiIhIpjQLmYiIiIiImctHDTAKMCIiIiIi5i4/TS2sACMiIiIiYuYM+agJJtMAc+TIkdyqh4iIiIiIPKL8E1/yV2uTiIiIiIiYOXUhExERERExc5pGWUREREREzEb+iS8KMCIiIiIiZi8fNcBoDIyIiIiIiJgPtcCIiIiIiJg5TaMsIiIiIiJmIz91q1KAERERERExc2qBERERERERs5F/4osCjOQzzvbWeV0Fkcf2+/KJeV0FkWxRqPuPeV0FkWxxJ6hvXlchX1GAERERERExc+pCJiIiIiIiZkOD+EVERERExGyoBUZERERERMxG/okv+au1SUREREREzJxaYEREREREzFw+6kGmACMiIiIiYu4s8lEnMgUYEREREREzl59aYDQGRkREREREzIZaYEREREREzJxBXchERERERMRc5KcuZAowIiIiIiJmToP4RURERETEbOSnFhgN4hcREREREbOhFhgRERERETOXn1pgFGBERERERMycZiETERERERGzYZF/8osCjIiIiIiIuctPLTAaxC8iIiIiImZDLTAiIiIiImZOg/hFRERERMRs5KcuZAowIiIiIiJmLj8N4tcYGBERERERMRtqgRERERERMXPqQiYiIiIiImZDg/hFRERERMRs5KP8ogAjIiIiImLuLPJRE4wG8YuIiIiIiNlQC4yIiIiIiJnLP+0vCjAiIiIiIuYvHyUYBRgRERERETOnaZRFRERERMRs5KMx/BrELyIiIiIi5kMtMCIiIiIiZi4fNcAowIiIiIiImL18lGAUYEREREREzFxuD+KPi4vjq6++YsWKFURGRuLl5cXQoUOpV69epvtt2LCBNWvWsG/fPq5evUrx4sXx8/PjjTfewMnJKUvnVoAREREREZGHMnLkSDZs2ECvXr0oU6YMISEhDBgwgMDAQGrWrJnhfqNHj6ZIkSIEBATg4eHB0aNHCQwMZNu2bQQFBWFra/vAcyvAiMhj++G7mRw+dJBDhw4Sdv48Hh4lWLtxS15XSyRDyxfO5tTxI5z69wiXL4ZRuGhxvg5cle62ycnJbAoNYnNoMGHnzmBtbU2lKtXp/J9XqVSlei7XXOSu97vW5P1uGd8oxick4dJtjklZy1olGdzWm5rlC2FrbUnY1Sg27w3jne//zOHaSk7LzVnI9u3bR2hoKKNGjaJPnz4AtG/fnhdffJHJkyczf/78DPedNm0azz77rEmZt7c3I0aMIDQ0lI4dOz7w/AowIvLYpn05BReXglSpWpVbkbfyujoiD7Ro9v8o4ORCuYqeREVlfs3+MP1TNq0OomoNX3r0H0JsbAyb14Tw8buvMmrCdKrVqJ1LtRYxteKv05y4GJmm3LuMK++092HNzrMm5f/t8gwfdK/Fxt3nGbd4N9GxCZRyd8S7jFtuVVlyUG52IFu3bh3W1tZ06dLFWGZra0vnzp2ZOnUqly9fpkiRIunue394AWjWrBkAJ06cyNL5FWBE5LGFrttEyVKlAOgY8CLRd+7kcY1EMvfV3OUULV4SgHcHdCUmJjrd7U6fOMqm1UHUqF2fkeO/wvD/jzibtenEO/06892XE5jywzIsLLQqgeS+A2euc+DM9TTl01+rD8DczceMZX4+HnzQvRafLNzFp8v25lodJRdlQ4KJjIwkMjJtKHZ2dsbZ2dn48+HDhylXrhyOjo4m2/n4+JCcnMzhw4czDDDpuXLlCgCurq5Z2l4BRkQeW2p4ETEXqeHlQQ7u2QlA4xfaGMMLgGMBJ2rXa8TmNSEcPbiXKtUz7sYjkpscbK3o3KA856/cZsOeMGP58I4+XLoRzaTgfQA42llxJzaB5OS8qqlkt+wYxD937hy+/vrrNOWDBw9myJAhxp8jIiIoWrRomu3c3d0BuHz58kOd97vvvsPS0pLmzZtnaXsFGBERkQwkxMcDYGNnl+Y1G9uUsuOH9yvAyBOjY/2yuDja8O2aQyQlpaQTB1srGlYtxvp/ztOnaWVGdXkGj0KO3IlNIPTvswz/8U8u34zJ45rLk6B379506NAhTfm9rS8AMTExWFtbp9kudQB+bGxsls+5atUqli1bxmuvvUbp0qWztI8CjIiISAZKlikPpLTE1K7X2FienJzM4f3/AHA14lKe1E0kPb39K5OUlMzcLXe7j1Uo5oyVpQV1KrvTtIYHX4TsZ//pa9SvWpRBraviXcaVhu+tJDouMQ9rLo8rOwbx399VLCN2dnbE//8DnnulBpeszCQGsHPnTt5//32aNGnCW2+9leV6KsCIiIhk4Jm69SlZpjwbVi3FtVBh6jbwJzY2htCg+Zw7nTLYNDZWT67lyVDJw5kGVYuxZV84Zy7fNpYXsE95Ul7ExZ43vtnOnP8fG7Nyxxlu3Ynn/W416elXie/WH8mTekv2yM1B/O7u7ul2E4uIiADI0viXI0eO8Prrr+Pp6cnUqVOxtLTM8vk16lBERCQDlpZWjBw/Dc9qNVjw/XTefqUDIwa+xOkTR3m572AA7B0cH3AUkdzRu2llAOZsOmpSHhOXAEBiYhILfjlu8tpPW/8F4PlqxXKhhpKjDNnwJ4u8vLw4deoUUVFRJuV79+41vp6Zs2fP0r9/f9zc3Jg5cyYODg5ZPzlqgREREclU4SLF+HDSTK5cvkjExXAKOLtQqmwFNqxcCoBHqbJ5W0ERwNLCQI/GFbkSGcPKv86YvBZ2NeUm83pUHHEJSSavXbyeMgNfQcesdfmRJ1d2DOLPqpYtW/Ljjz+ydOlS4zowcXFxBAcHU6tWLeMA//DwcKKjo6lQoYJx34iICPr27YvBYOCHH37Aze3hp/FWgBEREcmCwkWKUbjI3afUu//+DYOFBTVq18vDWomkaFO7NEVdHfh69cE0IeXyzRjORtymZCFH7G0sTca6lCiU8uQ74mb6U4mLpKdGjRq0bNmSyZMnExERQenSpQkJCSE8PJyJEycatxsxYgQ7duzg6NG7rYL9+/fn3Llz9O/fn127drFr1y7ja6VLl6ZmzQdPiqIAIyIi8pB2/vELu//aTqMXXsS9aPG8ro4IvZtWAkzXfrnXwl+OM6LzM/Rr7sXXqw8aywe0qALA+n/O53wlJUdlxyD+h/H555/z5ZdfsmLFCm7evImnpyezZs3C19c30/2OHEkZa/X999+nea1Dhw4KMPlJcHAwo0aNYvPmzZQsmbX1DXKKv78/devW5dNPP83TekjuWbVyORfCwwG4fv0a8fHxzJrxDQDFPTxo2659XlZPJI1fN4Vy5dIFAG7dvEFCQjzB81O+TAsXLU6jZm2M28744hMgmTLlPbGxteXogT1s37KOCp5V6fPGu3lRfRETxV3teaFmSf4+FsHBs2kXtgSYsnw/Ac+VZWKvOlTycGb/6WvU8yrKS40r8vO+cJb9fiqXay3ZLZfzC7a2towYMYIRI0ZkuE1gYGCasntbYx6VAsxDmjVrFuXLl6dZs2Z5XRWRJ8by4CB2/r3DpOx/078CoHadugow8sT5ed0KDu/7x6RsydwZAFTxqWUSYCp6VmPzmhD+2raFhIQEinmUpEvv12jT8WXjWjAieamnXyWsLC2YsznjG8Nb0fG88EEoH75UixfrlKG3f2XCrt3h86C9TFy6x7hmjJix3E4weUgB5iHNmjWLZs2aKcCI3OOHOWmfsIg8yT6aPCvL2zZ7sRPNXuyUg7UReTyTgvcxKXjfA7e7eiuWt2b9wVuz/siFWonkHAUYEREREREzl5uzkOW1p34dmOnTp+Pp6cm5c+d477338PX1xdfXl1GjRhEdfXfGjYSEBL7++muaNm2Kt7c3zZo143//+x+JiXdn6vD09OTWrVuEhITg6emJp6cnI0eOzPT8I0eOpHbt2sbZFp555hn8/PwIDg4GUubL7t69Oz4+PrRo0YLffvvNZP+wsDDGjBlDixYt8PHx4dlnn+XNN9/k/PkHD7bbtGkTr776Kg0bNszwPY0YMYLnnnuOhISENPt3796dzp07G38OCgqiV69e1KtXD29vb1q3bs2CBQseWI8bN27w2Wef0bZtW2rWrEmtWrXo37+/cRBXqr/++gtPT0/Wr1/P1KlTadiwIbVq1WL48OFER0cTFRXF+++/T926dalduzafffYZyclq8hYRERExGB7/j7nINy0wb775JqVKlWLYsGEcOnSIpUuX4ubmxvDhwwH44IMPCAkJoU2bNvj6+rJz506mTZvGhQsXGDduHJAy28JHH31EtWrV6Nq1K5Ay3duDJCQkMGDAAOrVq4efnx9BQUH897//xdrams8++4wuXbrQqlUrZs+ezVtvvcUvv/yCo2PKwmj79+9n9+7dtGnThmLFihEWFsbChQvp1asXoaGh2NvbZ3jekJAQHBwceOWVV3BwcODPP/9k2rRp3L592zjgKiAggOXLl7N9+3aaNGli3PfcuXPs3r2b999/31i2cOFCKlWqhL+/P1ZWVvz88898/PHHJCcn06NHjwzrce7cOTZt2kTLli0pWbIkV65cYfHixfTs2ZPQ0FDjXOGpvvnmGxwcHBg4cCDHjh1j8eLFODo6cv78eRwcHHj77bf59ddf+fHHH/H09KR9e42vEBERkfzNjPLHY8s3AaZ69ep88sknxp9v3LjBsmXLGD58OEeOHCEkJITu3bvz8ccfA9CjRw+cnJyMN9peXl4EBAQwduxYSpUqRUBAQJbPHR0dTefOnenfvz8AzZo1w8/Pj+HDhzN79mzq1UtZQ6BChQr069ePjRs3Gm/KmzRpQsuWLU2O5+fnR7du3Vi/fn2mN+9ffPEFdnZ3B5i+9NJLfPjhhyxcuJChQ4diY2PDc889R9GiRVm1apVJgFm9ejVWVla0aXN3IOtPP/1kcryePXvSr18/Zs+enWmASW1VsbC42+AXEBBAq1atWLZsGYMGDUqzT2BgIFZWKZfnhQsXWLRoEW3btmXSpEkAdOvWDX9/f0JCQhRgRERERPJRgnnqu5Cl6t69u8nPtWvX5saNG9y+fZtffvkFgFdeecVkm9SVRX/99dfHPn+XLl2M/120aFGKFSuGh4eHMbxAyqJAgEn3sHsDQ3x8PNevX6d06dI4Oztz6NChTM957763b9/m2rVr1K5dm+joaE6ePAmAhYUFbdu2ZcuWLdy5c8e4/apVq6hfvz6FChVK93i3bt3i2rVr1K1bl3PnznHr1q0M62FjY2MML4mJiVy/fh0HBwfKlSuX7nvo0KGDMbyk/l6Sk5NNurNZWlri7e2dpa50IiIiIvL0yDctMMWLmy405uzsDMDNmzcJCwvDysoqTXewMmXKYGVlRVhYWKbHjouL4+bNmyZlbm5uWFpaAuDg4ICLi4vJ605OTsZuYveWAURGRhrLYmJimDlzJsHBwVy6dMlkzEdmoQHg33//5csvv+TPP//k9u3bJq/du29AQADff/89mzdvpm3bthw6dIgTJ04wcOBAk3127drF9OnT2bNnj8n4odTjpdb/fklJScybN48FCxZw/vx5kzE4BQsWTLP9/f+vChQokG65k5OTye9KREREJL/KT4P4802ASQ0T98uOQeC7d++mV69eJmX3LiiZ0bmzUqexY8cSHBxM7969eeaZZ3BycsJgMDB06NBM6x4ZGUnPnj0pUKAAb775JqVLl8bW1paDBw8yefJkkpKSjNtWrlyZqlWrsnr1atq2bcuqVatwcHAwmSr67Nmz9OnTh/LlyzNy5EiKFy+OtbU1v/zyC3PmzDE53v1mzJjBV199RadOnXjrrbdwcXHBwsKCCRMmpPseMvq93NsFLb3flTy+pKQk5gfOY9nSRYSHheHq5kbzFq14Y/CbODg4ZOv+69etYfu2bRw5dJCTJ0+QkJDAmg2bKVEibxdiFfOXlJTE2pCFbA4NJuLSBZxcXKnXuBldeg3ELpNxgwDh58+wffNa9u36k0sXzhMfF0fR4iV5rlFTWnV4Od39w8+dZsH30zm8/x8S4uMpW8mLLv95De+adXLqLUo+YTDAoDbV6NfckzLuBbgSGUPQ76cZu+gf7sSmnXznXu93rcn73TJe0Tw+IQmXbnNMyjrUK8uQF6tRvawbScmw79RVJofsY/0/6u1gDsxpEP7jyjcBJjMlSpQgISGBs2fPUrZsWWP52bNnSUhIoESJEsYyQzpXh5eXF7NnzzYpc3d3z5a6pY5zuXe2s9jY2Ae2vuzYsYMbN27w9ddfU6fO3S/RjLpcBQQEMHnyZK5evUpoaCjNmjUzueHcsmULcXFxfPvtt3h4eBjL//rrryy9h2effZYJEyaYlEdGRuLq6vrA/SX3TPpsAgt+CsS/2Qv06t2XkydPsHB+IEcOH2LWD3PSDZGPuv+SRQvZv28vlT29KFmqFKdPaRVoyR7zZkxh3fJF1GngR5vOPQk7e4p1yxdx+vhR3v/sm0yv463rV7Jh5VJ8n2tEQ/+WWFpZcXDvLhbP+ZY/ft3EuK9mmyxeeTH8PB++3Q9LS0vadumFg2MBtqwNYeJ/BzNy/DSq13o2N96yPKU+f+VZBrWpxoo/TzNt5QE8SxbkjdZVqVHOjTYfryOzZ3gr/jrNiYtpeyl4l3HlnfY+rNl51qT8nfbVGfefOuw5eYVPFqUs8vpSowrMY+FFAAAgAElEQVQEjXqBftN+YfG2k9n63iT75aP8ogAD0LhxY6ZMmcLcuXP56KOPjOXz5s0zvp7K3t4+TbclFxcX6tevnyN1S681IjAw0KQbVnpSv6DvbaGIi4vLcNrjF198kc8//5xPPvmES5cu0bZt23TrcX8XtqCgoCy9h/tbStauXculS5coU6bMA/eX3HH8+L8snP8TTZs1Z8pX043lJUqW5LMJ41i3JpTWL7bNtv3HTfgM9yJFsLKyYsK4TxRgJFucO32C9SsWU7ehH+98OMlYXqSYB3O+mczvWzfQ0L9lhvs/+3xT2nd/BQfHAsayF17szGKPUoQs/JEt61bQMqCb8bVFP35NVNQtJv4vkLIVPAFo9EIb3h3QlR+//owpPwSl++BL5EGqlCrI662qsvzP07w8aYux/PSlW0zpX48uDcqzZHvGoeLAmescOHM9Tfn011LuV+ZuPmYsK+Jix+jutThw5hqNRq4iITHlO/vbNYf4fVIAX/Srx5qd57gVHZ9db09yQj76qMk3g/gz4+XlRYcOHViwYAHDhg1j/vz5DBs2jAULFtC5c2c8PT2N21arVo0//viD2bNnExoayt69e3O0bk2aNGHFihWMHz+exYsXM2rUKAIDA9MdO3KvmjVr4uLiwsiRI5k9ezZz5syhW7duGXa5Kly4MA0aNGDdunXG/75XgwYNsLa2ZuDAgcyfP59Zs2bRsWNHk0H+mb2HHTt2MGrUKJYsWcK4ceMYM2YMpUqVyvovQnLcutDVJCcn07NXb5PyTp27YmdvT+jqldm6f3EPD5PJGkSyw+8/ryc5OZlWHV42Kfdv3QFbWzu2b16T6f4VKlc1CS+p6jVpDsD50yeMZTHR0ez641eq+vgawwuAnb0Dfi3bc+H8WU4cPfg4b0fysa4Ny2NhYeDr1abX0OxNx4iKieelxhUe+pgOtlZ0blCe81dus2HP3fG9z3kWxdbaksXbThrDC0BCYjJLtp3EzcmWF+s+eNkIkdyiAPP/xo0bx5AhQ9i9ezcTJ05k9+7dvPnmmyZTL0PKwo/e3t58+eWXvPPOOyxcuDBH6/X+++8TEBDAqlWr+PTTT7l8+TKzZ89OMwHA/VxdXZkxYwbu7u58+eWX/PDDD9SvX9+47k16Uqcjbt26dZqWn/LlyzNt2jQMBgOfffYZixYtomvXrmnG/qRn4MCB9O3bl23btjF+/HgOHjzIzJkz0wzKl7x14MABLCws8K7uY1Jua2uLl6cXBw/sz9H9RbLDiWOHMFhYUNGzmkm5jY0tZSpU5sSxzGdvzMjViEsAuLjefWhz9tS/xMfHUblK9TTbV6ribayPyKOoVbEwiYlJ7Pw3wqQ8Nj6RfaevUatC4Yc+Zsf6ZXFxtOGnn4+TlHQ3qNhYp9wOpjeu5k5cSlndSkUe+nySuwzZ8I+5eOoffw4ZMoQhQ4akKe/YsSMdO3Y0/mxlZcXgwYMZPHhwpscrW7YsgYGBWT7/p59+mm75ihUr0i0/evSoyc/Ozs5MnDgxzXZbtmwx+fn+9wNQq1YtFi9e/MBzpEp9Gt6uXbt0X/f398ff3z9NeadOnTKtm42NDSNGjDAunpnq/t/js88+m27d+vTpY5zS+l4Z/W7l0UREXKagqys2NjZpXitStCh79uwmPi4O63Rez479RbLD9asRODsXTPc6cytchGOH9pEQH4+VtXWWj5mUmEjwgh+wtLSkgV8Lk3MBuBZOe2Pn9v9l165EpHlNJCuKuzpw5VYscQlpJ8kJv3aHel5FsbayID6d1zPS278ySUnJzN1yzKT88LkbADSpXpxv15iG7sbeKQ8bSxbO/MGp5L381FtVLTBitGTJEipUqED16mmfJsrTLyYmGhvr9MOFja0tANExMTm2v0h2iI2NyTCcpIaa2NiHuw7nzviCfw/to0uvgXiUKmtyLgDrdM6Xeq64hzyXSCoHWyvi4tMf7xoTl1LuYJP159CVPJxpULUYWw9c4Mxl06UVDp69zqY9YbStW4Zx/6mNZwkXPEu4MLZnbZrXTJkZ0t72qX/mbfYM2fDHXCjACKGhoUyePJnt27dnqUuYPJ3s7OyJi49L97W42FgA7O9ZzDS79xfJDra2diTEpz/QOD4uzrhNVi2e8y3rVyyhaesOtH/JdLHj1OPEp3O+1HPZPMS5RO51JzYBG+v0lxWws0kpT+3elRW9m1YGYM6m9Hth9JryM8v/PM3b7aqze1ondk/rRKf65Rj63R8A3LqT/ue7SF5QnBbeeecdHBwc6Nq1K126dMnr6kgecXcvwskTx4mLi0vTDezypUu4urpm2v3rcfcXyQ6uhdw5f/ZUut0Vr125jJNLwSx3H1s6byYhC36gSYu29H/rv+meC+D6lctpXrv2/2VuhbNnSn3Jfy5cv0OVkgWxsbJI043Mw82BiJvRWe4+ZmlhoEfjilyJjGHlX2fS3eZGVBwvT9pCERc7Knq4EBUTz77T14wtMMfCbqa7nzxBzKkJ5TGpBUY4evQou3fvZuzYsRkuIilPP29vb5KSkjiwf59JeWxsLEeOHqFqNe8c3V8kO1SoXJXkpCSO3zf7V1xcLGdOHKN8papZOs7SeTMJ+uk7Gr3wIq8OHZ3uVMily1XE2tqGY4fTTlDx7+EDAFk+n8j9/jl+BUtLC2pXMg3BttaW+JR1Y/eJq1k+VpvapSnq6sCiX0+kO6bmXpdvxvD74UvsPXWN5GRoUSslwKzTYpZPvPw0iF8BRkQAaNGqNQaDgZ/mzTUpD1q2hJjoaJM1XM6dPcupkyceeX+RnFKvSXMMBgNrQ0zXvNqyJoTY2BiTNWAuhp8n7OzpNMcI+uk7gn76juebtWbgsA8zXPjSzt6BWs89z6F9uzhz4u6g6JjoO/y8bjnFSpSmole1dPcVeZBlv50iKSmZwS+aXkOvNKuMo501i7bd/QwuV9SJyiVcMjxW76aVANO1X7KiVoVC9GlamV8PXOCPI5ceal/JfQbD4/8xF+pCJiIAVKrsSbeXerBowU8MfWswzz/fmJMnT7BwfiC169SldZu7AeTVfn0IDw9j78Gjj7Q/wK6df7Nr598AHDqY8rR60YL5ODk5pZxj4Bs5/I7laVS6XEWat+vC+hVL+OLj4dSs24Cws6dYt3wRVXxq0eCeADNuxOtcuXSBRRt2GsvWr1zC0nkzKVykGNVr1uW3LetMju/i6oaP73PGn1/qO5gDe/5mwqjBtO74MvYOjmxZG8K1KxGMGPelFrGUR3bw7HVmrjvM662rsnC4P+v/OY9nyYK80boqvx64wOJ7AsyaMS0pU8QJh04/pjlOcVd7XqhZkr+PRXDwbNqFLVN92L0WFYo7s/N4BJF34nimXGH+41+J8Gt36Dft1xx5j5K98tOnjQKMiBi9N/K/eJQoQdDSxWz7ZSsFXV3p/nJPBg1+M8On0I+6/46//mTGN1+blM2bc/fLVwFGHlXvgcNwL+rB5jXB7N6xHSfngrQI6EbX3gMfeB2fOJoyheyVyxf5ZtKYNK9X8allEmCKlSjFJ1N/YMEP01mxeA4JCfGUq+jFqAnTqF7r2Wx9X5L/DJ/9F2cu36bvC5609C3F1cgYvl17iLGL/iGDdanT6OlXCStLC+ZsTn/wfqo9J6/SpHpxmtYogYOtJeeuRPHtmkNMDt7HTQ3glyeMITmjpdlFnkIxWZ+wReSJdTjsVl5XQSRbNHhnaV5XQSRb3Anqm9dV4PTVx5+2vWwh85g5US0wIiIiIiJmzpwG4T8uBRgRERERETOXn4bcKcCIiIiIiJi5fJRfNI2yiIiIiIiYD7XAiIiIiIiYOXUhExERERERM5J/EowCjIiIiIiImctPLTAaAyMiIiIiImZDLTAiIiIiImYuHzXAKMCIiIiIiJi7/NSFTAFGRERERMTMGfJRG4wCjIiIiIiIucs/+UWD+EVERERExHyoBUZERERExMzlowYYBRgREREREXOnQfwiIiIiImI28tMgfo2BERERERERs6EWGBERERERc5d/GmAUYEREREREzF0+yi8KMCIiIiIi5k6D+EVERERExGxoEL+IiIiIiMgTSC0wIiIiIiJmLj91IVMLjIiIiIiImA21wIiIiIiImLn81AKjACMiIiIiYuY0iF9EREREROQJpBYYEREREREzpy5kIiIiIiJiNvJRflGAERERERExe/kowWgMjIiIiIiImA21wIiIiIiImLn8NAuZAoyIiIiIiJnTIH4RERERETEb+Si/KMCIiIiIiJi9fJRgNIhfRERERETMhlpgRERERETMnAbxi4iIiIiI2chPg/gNycnJyXldCRERERERkazQGBgRERERETEbCjAiIiIiImI2FGBERERERMRsKMCIiIiIiIjZUIARERERERGzoQAjIiIiIiJmQwFGRERERETMhgKMiIiIiIiYDQUYERERERExGwowIiIiIiJiNhRgRERERETEbCjAiIiIiIiI2VCAERERERERs6EAIyIiT50//viDmzdvGn9OTEwkKSkpD2skIiLZRQFGRIwiIiIYPXo0hw8fBiAhIYGEhIQ8rpXIw9mxYwevvPIKc+fOBSApKQlLS0ssLCyIiIggOjrauG1ycnJeVVPkkaT3mazrWPIbBRgRMfr9999ZunQps2fPBsDKygorKysSExPZuHEju3btIjExMY9rKZK5smXL0q5dO5YsWcKpU6ewsLDgzp07jBo1ivbt29OzZ0++/PJLAAwGQx7XVuThWFlZAbB69WrWr1/PrVu3dB1LvmM5ZsyYMXldCRHJW8nJyRgMBry8vDh9+jS//fYb5cuXp1y5cixfvpx+/fqxfPlyli9fzuXLlyldujRubm4kJSXpi1OeOI6Ojjg7O7N27VquXbvGc889xwcffMCBAwd4/vnnuX79OqtXr8ZgMFC3bt28rq5IplI/n1M/b/ft20evXr1YunQp69at4+DBgxQtWpSSJUvqM1nyDQUYEcFgMJCYmIiFhQVubm5s3bqV06dP07RpU6ZNm0bNmjXp06cPZcqUISgoiPDwcFq1aqUvSnmiJCcnG2/2XF1diY6OZtGiRbi7u7Nr1y7efPNN+vbtS4sWLYiPj2fu3LnUqlWLkiVL5nXVRdKVkJCApaUlcLe1cPbs2VhbW/P2229Tq1YtVq9ezb59+2jXrh02NjbGvwMiTzMFGBExjhEA8PDwIDw8nO3bt7N9+3bi4uL44IMP8PX1pV69ety+fZvNmzdjb29P9erV9cRPngipN3qp16KNjQ2urq7s3buXZcuW4evry8CBAwGwtbWlQoUK/P777+zfv58mTZpgZ2eXl9UXSVdq98f58+dz/vx5rl69ypo1axg4cCDPP/88NWrUwMrKik2bNnHjxg0aNWqkACP5gsbAiORjqeNZLCxSPgpu3boFQLdu3ShRogRHjhyhadOmFC9enLi4OAC6dOmCl5cXc+fOJTIyEgsLCw0glTyTOrOYlZUV8fHxLF68mOXLlwNQvnx5unTpYnwqHRMTY7xWixcvzoABA/jrr7/YsmWLrmF5Im3fvh0/Pz+mTp3Ku+++y/jx44mKiqJixYrGbQICAmjYsCFLlizh+PHj+kyWfEEtMCL5WGpwWbNmDdOmTWP//v34+Pjg4eFBfHw8W7ZswcnJiVatWmFhYYHBYMDFxYX4+Hi2bdvGzZs3adiwIaDB0JI3Uq+7pUuXMmDAAPbv38/OnTupX78+7u7uuLi4cPLkSQ4fPkybNm1wcnIy7lusWDGOHz/Opk2b8Pf3x9nZOa/ehoiJHTt2cPXqVZYsWULFihUZOXIk1atXZ9euXVy5coWOHTvi5OREcnIyDg4O2NjY8Pvvv3Ps2DHatm2rz2N56inAiORjYWFhvPXWWyxYsIASJUpQoEABqlWrhouLCxUrVuTAgQPs2bOHunXrUqxYMeLi4rC0tKRkyZKcOHGCLVu20LBhQwoXLqyuZJJnlixZwtSpU2natClvvvkmPXv2pGzZsgC4uLhgb2/P8uXLsbGx4bnnnjPuZ2trS/HixVm8eDHJycnUrVvX2JVSJK9cvXqV3r17ExoaSmJiIu+99x7e3t5Ur14dBwcHNm/ejLW1NfXq1TN2FytVqhSXLl1izZo1VKlShXLlyhnHNYo8jRRgRPKxb775hj/++IP//ve//Oc//6F169a4uLiQmJiIra0t9vb2bNu2jYsXL9KqVSssLS1JTEzE3t4eOzs7tm/fzu7du+nYsaPCi+S6pKQkYmJiGDNmDAULFmTMmDFUrlwZZ2fnNAP6r169SlBQEH5+fhQqVMh4jEKFCnH27Fn++usvAgICsLW1zcN3JPlJRgHD1tYWd3d3QkNDsbKy4vXXXzdOnVy0aFEiIiJYtmwZLVq0wM3NjcTERKysrHBzc+Off/5h9erV9O/fX+FFnmq6ukWechmtPn7u3Dnmz59P69atad++PUWKFDFun/rF17x5cxo0aMCff/7JunXrTI7XsGFD/P398fX1Nd4siuSE9NYeSk5OxsLCguvXr3PkyBE6depE8eLFjdenwWAwXseurq506NABBwcHZs6cabIQoI2NDSNGjCA0NFRdyCTH3Pv5mJSURHJysrG179SpU0RGRhpft7S0pGHDhjRp0oSYmBiOHz9ufK1QoUIEBARQoEABpk2bBtztCuzt7U2LFi1o2rQpsbGx+kyWp5oCjMhTKikpySSM3O/8+fPEx8dTrVo14/aAcaxL6k1jjx49KFiwID/99BOxsbFYW1sTHx+PhYUFw4cP5+2338ZgMKgFRrJdajBOvdHbu3cvBw8e5Nq1a8abs8uXL+Pk5MTZs2cB07FYqX8HAKpWrcrLL7/M+vXr+fXXX03OU7BgQSD9Fc5FHtW+ffuYNWsWsbGxGAwG4zWb+hm7c+dOunTpQs+ePWnevDnjxo3j1KlTALi5udGzZ08iIyPZuHEj0dHRxuP6+PjQpUsX1q1bxx9//GHyef3aa68xbtw4bG1t9ZksTzV1IRN5CqU+nTYYDJw4cYJ58+Zx4sQJbt++TalSpQCIjo5m4cKF1K1bF29vb5O+//dOq1y0aFGuXLnCunXrSE5O5tlnnzW+lvpvjX+RnJAajA8ePMgbb7zB3LlzCQoKYtOmTdy+fZvatWvj4ODAihUriIqKol69ejg7O5OQkGC8/g0GA9HR0djb2+Pi4sLmzZuJi4vD398/zTWrLjeSnSZMmEBwcDAVKlQwzhpmMBiIjY1lxowZTJgwgbJly9K4cWPKlStHUFAQYWFh+Pr64uTkhKurK1euXGHlypU899xzFC9eHABra2sKFizIzp07Wb9+PT169DB2MdNnsuQXCjAiTyGDwUBCQgKTJk1i1KhRnD9/ni1bthAUFERERATVqlWjdOnS/PLLL/z77780a9YMBwcH45gBg8FAXFwcu3fvxsPDg5IlS3LgwAHq1auHl5dXuucTyQl79uxh6NChFCtWjD59+vDCCy9w/fp15s+fT+HChfH19eXOnTuEhIRQqFAhfH19jUEkISGBwMBAVq5ciZ+fHy4uLjRt2pROnTrpmpUckzq2xcfHh7Vr13L9+nXq1KmDo6MjAAcOHOCLL77g5ZdfZsCAAbRs2ZJGjRoRHx9v7Kr73HPPYWNjg4eHBytXruTWrVvUqVPHuF6Rq6srlpaWlC5dmnr16qWpg65vedopwIg8pVatWsW8efPo168fgwYNYujQoTg6OhIUFMSlS5do2rQpBoOBxYsX4+zsTMWKFbG3twfg0qVLfPvtt2zfvp1GjRpRuHBh2rZta+xuJpJbZs2axblz5/jwww9p1KgRVapUoWLFioSGhnLo0CFatWpF48aN2bhxI9u2bcPBwYGyZcsaF2NdvHgxdnZ2NGzYEDs7O2N3Mc3QJDnFwsKCpKQkXFxciIqKYu3atbi5uVGjRg0A4uPjiY+Pp1evXsZWlXnz5hnHZ128eJHq1atTrFgx47TfCxcuxMfHh3LlyhnHd1WrVs1kVj2R/EQBRsSMZbTiclxcHGPGjKF48eKMHj2aokWLYmNjw6lTp1izZg0Gg4HmzZtToUIFbty4wY8//kh4eDjOzs78/fffLFu2jA0bNtC2bVtq1qyJpaUllpaWJgOkRbJD6oDmjK6pSZMm0aRJEzp16oSFhQXz589nxIgRuLq68sorr1C5cmXs7e2pUqUKJ06cYMGCBSxatIjNmzcTEhJC1apVGT16NG5ubibHVXiRnGYwGHjmmWcIDQ3lzJkzVK9encKFC+Pg4MDzzz+Pvb09x44dY8CAAaxdu5YBAwbwwgsvsH79emJiYmjWrBlWVlZ4eHiwadMmdu7cSfPmzXFwcDAeHzL+HhB5mlnldQVE5NEkJCQY+z3f7+rVq0RERPDSSy9hY2PD3r17GT9+PAcPHqRnz5506tQJZ2dnLC0t+eSTT0hMTGTTpk2sWbMGe3t7XF1d+fDDD2nVqpXJcXXTJ9kpMTHR2Gc/PDycO3fuULBgQQoXLgykDNC3srIiOTmZbdu28fnnn3Pu3DleeuklunXrhoeHBzY2NgA888wzfPPNN4SGhnL+/HmioqLw9/enfv36AJlOaCGSHVKv59RAER8fj7W1Na+++ioff/wxoaGheHp6Ym1tDcC1a9f4/PPPMRgMfPvtt9SqVQsbGxvmzJnDpk2b8PPzo3nz5ri7uzNs2DAiIyONfzfupfAi+ZEhWfPsiZiVe5+2JSUlsXjxYiwsLChSpAh+fn7G7Ro0aEDz5s2JjY0lODiYBg0a8Nprr+Ht7W18gnfr1i2cnJyIjY3l8uXLREREcPv2bRo1amQ8jm78JCdFR0czduxYNmzYgLW1NVZWVnTr1o3XXnsNa2tr+vfvz/bt27GyssLf359XXnmFqlWrGtdruXTpErt376Zly5YZnuPeoCSS3e6/vuLi4ozBOtWAAQMICwtj9OjRxjErO3fupHfv3owePZru3bsDEBUVRY8ePYiKisLJyYl58+ZRoECB3HszImZCLTAiZiY1vKxZs4Zx48ZhMBiIiYkhKiqK1q1b079/f6pWrUqzZs1YuHAhpUqV4osvvqBevXq4uroa91+3bh1nzpyhb9++2NraUqpUKeMMZXC3hUfhRXLKtWvXGDZsGOfPn6d///64u7vz22+/8eOPP3L58mU++eQTXn/9deNYrP/+978UK1bMuP+JEyeYMmUKV69exc/PzxhqUkN+avhWeJGccu8035s2bSIkJAQrKyueeeYZmjVrZvxMHTJkCK+++iorV67Ex8cHR0dHLl26hKOjo/Ez9ubNmyxfvhw7OzvjZCn3LsgqIncpwIiYof379zN9+nTq169P9+7dcXNz4+TJk4wcOZI7d+4wdepUmjZtys8//4ynpydNmzY1zl4TFRXFH3/8weTJk2nbtm2G58ioe5pIdvnzzz85cOAAo0ePxs/PDycnJ9q1a8eAAQNYsmQJnTt3xtfXl7Zt27Jp0yaCgoIYNGgQFy9e5NSpUyxatIh///2XQYMGGbvlwN2Qr/AtOc1gMHDx4kXGjx/P1q1b8fLy4s6dO2zbto3Vq1ezbNkyDAYDPj4+tGjRgp9//pmNGzfSvn17GjZsSNGiRZkxYwaHDh0iKSmJTZs2MWDAAHr16qXgLZIJ3aGIPMHuf/KW+vOaNWuIjIzkjTfeoHz58gDGJ3mHDx/m2LFj+Pr60rVrV77++mtGjx5Np06diIqK4vDhwwQHB1OiRAlatWplcuMnkt3S676Veh3v2rWLYsWK0a5dOyClS81nn33GyZMn6dGjB66urgCMHTuWa9euMX36dH766ScKFSrE1atXsbe356OPPqJx48a5/r4kf7r/er5+/Tr/+9//uHjxIp988gl16tShZMmSbNiwgeHDhzNlyhSGDRsGwODBg9m2bRtr1qzB19eXUqVK8e6777Jw4UK2bt2KwWCgb9++vPLKKxmeT0RSKMCIPIFSv7TSCy8JCQkcOHAAf39/ypcvz40bN5g8eTLBwcHUqlWL119/nQoVKuDo6MjAgQMxGAwsWbKEVatWUbBgQRITE+ncuTPvvfeeuiVIjkm9XlNnrwsLC6NIkSImK4RfunSJYsWKcezYMWbNmsXq1atp2LAhM2fOxMvLy9j3387Oji+++IK9e/fy119/ERsbS/ny5enRo0ea84nkpNQwsXfvXmrUqIG1tTWHDx+ma9eutG3b1thyvXv3bmJjY5k7dy6tW7emSpUquLu706NHD2bNmsWGDRvo168fjRs35vnnn+fUqVOUKFHC2FKu7o8imdMgfpEn2O+//87ly5epUqUK5cqVMw4MHTJkCBcvXqRr16589tlnuLi4MHDgQJo2bYqLiwuWlpbExMQYvwzDw8MJDw/n1q1bVKtWjSJFigB6uifZ7/5ravHixcyYMYPo6GgcHR0ZMmQI9evXp0iRInz33Xd88cUX2NnZ4eHhwRtvvEGDBg2MLS+QMlbr/gH694aVzGbjE8luSUlJvP/+++zYsYOFCxdSpEgRIiIicHd3B+CXX37hww8/JD4+noCAANavX0/FihWZOXOm8Zrt1q0bt27dYuLEica1YVKlrk+kMC6SOX3qizwh7r3xu3DhAiNHjmTHjh1YW1tjaWmJv78/Y8aMwcnJiZo1a/LVV18xZswYBg8eTIsWLShdurTxRu748eNs3bqV9u3bU7hwYTw8PPDw8DA5l57uSU5IvaYiIyP5559/+P7776lXrx6Ojo4cOXKEDz74gHbt2jFhwgTatWvHsmXLAPj000/x8fExHufatWvMnTuXjRs3UqlSJSpUqGB8zWAwkPrsTeFFcsr9MzAmJydjYWGBs7MzycnJODs7AxjDy4oVKxg7diz+/v68+uqrFC1alKioKJYsWcIvv/xCkyZNAOjVqxczZswwLhx8L30mi2SNPvlFnhCWlpbcvn2bsLAw/v33X27evMmnn36Kq6sr27dvZ968eSQlJfHBBzZ/c3oAACAASURBVB/QoEEDVq5cyY0bN+jXr5+xZSYhIYGjR48yceJEHBwc6NKlS5rz3Dtrjkh2uL/71oQJE9izZw8uLi5UqVKFd99917iQ5LBhw1i1ahXVqlWjR48edOvWjc8//5z169dTpUoVIGV2sQ0bNrB69WpatWplXK38XnpCLTnt3vCS+tAH4Nlnn2Xu3LkcP34cb29vIGU68JCQECpXrsyQIUMoWbIkBoPBGG6mTp1K7dq1KVCgAG3atKFNmza5/4ZEniIKMCJ55P6ne5GRkQwbNoxt27bh7e1Nly5dCAgIAKBhw4aUKlWK8ePHU6VKFV599VW6devGxIkTeeONN+jTpw9OTk4cO3aMoKAgrly5wnvvvYeLi0ua8+rGT7JLemO1AKpWrcq8efOwt7dn7ty5uLm5GdfGGDRoEGFhYXz//fe0a9eOvn37cvjwYebMmcPSpUspVqwYCQkJnDt3jtdee43Bgwfn0buT/G7Dhg0sXbqUqVOnmqzFYmNjg4uLCwcPHjQGGAsLC44fP06LFi2MUyefOnWKTZs20aZNG0JDQ9mxYwf+/v7G46gLr8ijsxwzZsyYvK6ESH6SlJREUlKS8Yvr5s2b2NnZYWtrS3x8PMePH+fs2bO88sorlChRwhh0atSowZYtW9i/fz+NGzemTp06lClThpUrV7Jo0SI2b97Mli1bKFGiBFOmTKF27dp5/E7laZXafSs1gG/dupXQ0FAqVKiAg4MDnp6enDp1isOHD1O1alWqV69u7Nfv6upKZGQkW7dupUiRIlSvXp3GjRvToEED4xPrSpUq8cUXX9C0aVMg5e+MgrfklHvXWrm3NXHjxo2sWrWKv//+m6JFi1K6dGkAihYtyuzZs/H09KROnTokJSURGxvL8ePHWb9+PeXKlePMmTOsWrWKyMhI3nnnHV5//XWqV69ucl5N8y3y6NQCI5KLUvtQQ8rTuRkzZhATE0P79u3x8/OjUaNG7Nmzh2XLlnHnzh0g5Usu9UndoEGDGDRoEOHh4ZQqVYq2bdtSo0YNzp49y82bNylWrBi+vr7A3Zs+3fhJdku9pg4fPsxHH33EmTNnsLGxoVChQnTv3h2DwUC/fv1Yv349e/bsoUWLFiatMC1atODLL7/k1q1bQMo4Fl/f/2vvzuNjPNfHj39mJglZJZNVIiHIJkSIICJFpKVILFFSuxRHai2tqh7aqtqqRx31tR5rSoXaaWOLELHvS2OrRGJJEKqxTZKZ3x9+81QIJ+0Riuv9evXllZlnniW9M899Pfd1X3cQQUFBRTqQxrQd6eiJ0mIsAqFSqbh//76SjgvQp08fGjRowKBBg/jkk0+YNGkSwcHBlClTBj8/P1JTU4mLi0OtVmNlZUXXrl3JyMhgwIABmJqaYmNjw8iRI4ssSgkyCi7EsyB3BSGeI2MZ5AkTJtCmTRvOnj2LjY2NckNzdHSkefPmODk5ER8fr3zO2IFzdnZGrVZz7Ngx5T0PDw8aNmxIy5YtleBFKtmI0rZv3z769euHtbU1o0ePZvbs2cTExCjv+/v7ExMTw8aNG0lNTQVQOocGg4GCggJu374NFJ24bGyzxlFKacPiWTC2wUcZi0D83//9H7169aJv377MnDmT/Px81Go1AQEBfP311/j6+tK/f3+WLFkCQPny5cnLy+Py5cvKvmrWrMnMmTOZPXs248ePJyUlpUgFPXmgJMSzIyMwQjxnK1asYN26dbz//vs0adKESpUqFXnqFxQURJs2bZg5cybr16+nefPmSgcvMzMTvV6Pi4tLsft+eO0NIUpTYmIipqamDBw48LFSsEZ9+vThp59+Yvr06dja2tKwYUNycnJISEhArVYrVZmKI6Mu4lkoLCxkzpw5TJ48mVWrVimjIUa7d+9mzJgxXL9+nRo1anDp0iV27drFmTNnGD9+PCYmJtSpU4caNWowaNAgpkyZgl6vx8fHh23btj1WBU+r1RIWFqb8LGW+hSgdMgdGiOdIr9czYcIEbG1t+eqrr7C3t0ej0ZCfn49Go8FgMGBqaoqVlRUnTpzg559/Jj8/H61Wy4kTJ5g/fz4ajYbevXtja2v72P7l6Z54XubNm4eDgwO9evUCIC0tjRMnTnDy5Enu3r2LVqvFxsaGMmXKsHr1apKSkkhMTGTnzp2sXr2ayMhIoqOjMTU1fcFXIl5larUac3NzDhw4wKlTp4pU/0pPT2fy5MnY2try8ccf0717d7p3746TkxMzZszAw8ODqlWrolarMTExoW7dupQtW5aJEydy69YtMjIyCAkJoWLFisUupCoVH4UoPRLACPEc3b17l3379vH7778TFRVFTk4OK1asIDk5meXLl3Pu3DmCg4NxdnYmPz+f3bt3k5KSwtmzZ1m9ejU3b95k5MiRBAYGvuhLEa8pY0fNxMSEWbNmcfz4cebOncuKFSvYsGEDq1evZt26dajVaoKCgvDz82PXrl3cuXOHyMhIqlatSteuXenVq5cEL+K5sLW1RaPRsGDBAvz8/KhcuTIAGRkZ7Nmzhz59+lCvXj3MzMzIzMzkP//5DxcuXCAzM5OwsDClmqOlpaVSCnnv3r3cunWLatWqUatWrWIfHskDJSFKjwQwQjxHpqam5Obmsm3bNqZNm8b8+fM5e/Ysp06dIjc3l8TERAoKCqhfvz42NjZkZWVx4cIFZs2aRWhoKJ9++imenp4v+jLEa8zYKfP29sbKyorTp0/j5OREo0aNaNeuHf/85z/Zv38/R48epXHjxtjZ2eHg4EBCQgKNGzemS5cuVKlSRanGJ6liorRpNBq0Wi2nTp0iKSmJdu3aYWJigouLCxEREVSqVAmA7777jg8++ABra2u6du3Kpk2bMDMzIygoCI1GoxRGCQwMpHLlyuzatQtHR0caNWpUZJ0YIUTpkwBGiOfEePPz9vYmNDQUS0tLYmJiaNmyJcOGDaNz585cvnyZjRs30rNnTyVFbNOmTRQWFioTpAsKCuRGKZ6p4tJfSiIwMJCoqChatmxJ7dq18fLywsLCggsXLrBjxw66d++OlZUVlSpV4uTJk2zatInAwEBcXV1RqVTSjkWpKK4929jYYGVlxQ8//IC1tTW1atXCYDBgZmZGQUEBX3/9NUuXLqVv3758+OGH+Pv7c+DAAXbv3k29evVwdnZGpVIp3+NOTk6cP3+ew4cP8+6770pbFuI5k784If4i49oBJWW8wZmamuLr68vgwYNp0aIFISEhmJmZkZeXR05ODuXKlePGjRsANGjQgDZt2hAfH8+pU6cAJKdaPDN6vZ7CwsL/KdXF2B41Gg23bt0iNTWVLVu20KpVK+zt7ZXtBg8ezG+//ca6devIzc39n89diOIUFBQ8sT0HBQURGRnJjBkzyM7OVra7fPky69ato1mzZnTu3BlHR0e0Wi2mpqZcvXqVBQsWKCW/jd/jZcuWVfZ77dq1Ur4qIcSjJIAR4i8w3iSNT+T+jEdvrjqdjrS0NJYuXcqvv/5KdHQ0dnZ2AJQrV47IyEg8PDwYM2ZMsZ8X4q8wpm9pNBquXLnC6tWrOXDgABcvXgQocXBuMBjIyspi1qxZfPfddwwbNgyNRkNMTEyR6kve3t506NCBH374gRMnTpTKNYnXl/F72MTEBJ1Ox/z581mwYAGJiYnKNlqtlujoaDQaDdOmTVNe1+l0XL16lZCQEKysrNDr9Wzfvp1r167Rtm1btmzZojxUggeVza5evcrNmzeV9Y+EEM+X1PYT4i8wdszmzZvH+fPnsbOzIyIiAn9/f9RqdYly+3U6HUuXLiU1NZWLFy/y66+/8t5779GtWzfgjzSImjVr8tZbbzFnzhzOnDmDl5dXqV+fePWp1WoMBgNff/0133//PdbW1uTm5uLm5saXX35J3bp1H1uZvDh37txh1apVLFq0CDs7O2JiYujfv3+x28bFxeHh4VGkzKwQz4Lx+3bZsmVMmjQJjUbD/fv3uX37Nh07diQ2NpaKFSvi6+tLTEwMM2bMoH379gQEBGBtbU1gYCCzZs3i/v37aDQafvzxRypXrszHH3/MqFGjMDc3V46l0WgYP348SUlJDB8+HPjraZhCiL9GZfgzOTBCCAAOHDjAiBEjuHnzJq6urpw7dw4LCwtiYmIYPHhwiW9mEyZM4Ndff8XFxYVevXrh7u4O/PF03LifS5cuYWpqiqOjY2lfmniNTJ48mdWrV9OhQwdq165NXl4e33//Penp6YwYMYI333yzRPvJzc0lIyMDLy8vrKysgAdPqSXdUTwvBQUFfP/99yxcuJAmTZrw1ltv4eTkxOHDhxk5ciRdu3Zl8ODBmJmZcerUKT788EO0Wi0LFixAr9dz6NAhBgwYwK1bt4AHC7GOGzdOqVhmbM/G7+bk5GSsra2pXbv2i7xsIV5bMgIjxJ+k1+uZO3cudnZ2jB49Gj8/P8qUKcPYsWOZMWMGwcHBhIaG/td9qNVqBg4cyP3795UJ+8ZKNsanicYgyNXVtXQvSrxWDAaDUsI7IiKCrl27Ym1tDcD169f57LPPOHjwIPXr11defxqtVotWqwX+aMMSvIjSUtwI971790hLS8Pf35/Y2FjlO1OtVlOmTBmSkpIICAigefPmeHp60q1bN0aOHMm6deto1aoVQUFBJCQkcOnSJQwGA/Xq1QMeXxzYeNxGjRo9xysWQjxKAhghnuBJaWAHDx5ky5YtTJs2TbnJZWdn8+uvvwJw6tSp/xrAGPdrbm6upCbo9Xrp9IlnqrhVwI0dsgsXLnDjxg369euHtbU1v/zyC2PHjuXQoUO0a9eO1q1bY2lpWaLjGPcpC/eJ0mQcBSnue7ls2bJ06dIFf39/4MH36aeffsrq1aupXr0658+fZ8OGDQQHB2Nvb09ISAiNGzfm3//+N40bN8bKyooKFSpQoUKFx44nhPj7kUn8QjyisLAQ4LGbpDHb8vr162i1WmrVqgU8SANr2rQpd+7cYdq0abRp0+YvHVfKcIpnzRi87Nq1i19++YV79+4VSW20srIiKSmJcePG0a5dOwwGAzNmzGDEiBH4+voq87mexPg3oVKp+P3332UOgChVxmBi1apVDBw4kKlTpyoV7UxMTPD19QXg+PHjtGrVil27djF69GgSEhJo1aoVW7ZsUSb1V6hQgXbt2nHhwgV279791OMJIf5+ZB0YIf4/41NkYyCRkpLCokWLuHjxIlZWVkplsHPnzrF27Vru37/P8OHDOX36NP379+eDDz6gWrVqJX5qbbRz504KCwuV/QvxVxlLexsDic2bNxMbG8vSpUtJSEjg8OHDlCtXDk9PT+7cucOWLVtYt24dV65cYcSIEfTu3RtfX1/KlCkDwOrVqzE3N1dSHB9lHHVZsGABcXFxODs7K51IIf5XD7dnY7A8evRoZs+eza1bt9i6dSs7d+6kSpUquLm5Kd/dixYt4syZM0yYMEEpU3/79m22bt1Kfn4+3t7eODg44OjoSIcOHZSHUUKIl4c88hWCohVk7t27xxdffEHv3r1Zv349X3zxBTExMcyePRuAZs2a4e7uzsKFC2ncuDFLliyhU6dOODk5odFoyM3NZejQofz000/FHsdo3759REZG8tFHH3HlypXnc6HilWYMwDMzM8nNzeXHH38kKCiIzz77jEGDBnHu3DmGDBnCwYMH8fLyIiwsDJVKRXR0NG3btsXJyQmVSsXt27fZsGEDo0aNYv/+/UWO8XAbTk5OplWrVvz73/+mU6dO/zV1UoiSMq5PpFaryc/PR6VSce3aNY4ePcqYMWNYsGABixYtIjMzk3nz5pGZmQk8WJMlJSUFV1dX6tSpozxQMk6637FjB8nJycCDxS3d3d3/9JpeQogXT+bACMGDjl9BQQGrV6+mbNmyHDlyhC+//JKAgAA0Gg2jRo1i5syZWFhY0LlzZzp27Mj48ePx9vbGyckJMzMz9Ho9Fy5cID4+ntOnT/POO+8o+zcGSMaKYl9//TU//fQTjRs35rPPPpMngOKZSU5OZtCgQVSsWJH8/HymTZuGp6cnALVq1eLzzz9n/PjxzJkzh969e7N//34WLVqEr68v1atXJycnhz179rB8+XLq1aunzPMyUqlUnDt3jgkTJrBjxw6aNWvGpEmT8PHxkTRI8T8zzjsxpm9Nnz6dAwcO4OXlRY0aNXB0dKRp06aYmZnh7u7OkCFD+PLLL6lVqxa9e/fGwcEBW1tbLl++zM6dO6lUqRKpqamkp6ezcOFCjh07RlRUVJFjSuqjEC8fKaMsXkvFlTlOTk7mH//4B9WqVcPNzY0pU6YoHbLz588zfPhwMjMzWbduHVqtltjYWA4cOEBUVBRhYWFkZ2ezdetWTp48yXvvvUfPnj0xNTVV9q/T6Zg5cyZz5szBw8ODvn37Eh4eXmR9ASFK6tEJxsafr127xsCBAzl37hxNmzZl7NixynuFhYVs2LCBYcOG8dlnnxETE0NKSgpz585l165dlC1bFnt7e65cuUJMTAzDhg3DzMxMOcadO3eYMmUKixYtonr16sTFxREaGlpkGyGelf79+3Pw4EHs7e05c+YMAG3atGH8+PHodDql3UVGRpKfn89XX31FUFAQx44do2/fvuTl5eHq6kpmZiYtWrRgzJgxymdKslaXEOLvS+bAiNeKwWB44o2rUqVKpKens3PnToKCgmjatCl6vR6DwYBWq8VgMJCUlARASEgIYWFh5OXlsW7dOn7++WeOHTuGhYUFkyZNokWLFkU6l3v37qV169acPn2a3r178+mnn1KzZs0iAY4QJWFMdzG2r5ycHCwtLZU2bWFhgUajITExEZVKRYcOHZQ1hdRqNba2thw6dIi0tDTat2+Ph4cHLVu2xNPTk8DAQPz8/PjnP/9JVFSUEvQY971mzRpWrVpF3759+eijj/D19ZWJzuKZys7OZtCgQdy5c4eMjAz69+9Pv379aN26NWvWrCE3N5fmzZtTrlw5dDodGo2GqlWrMm/ePGVdlgoVKlCtWjUqVqyIlZUVQ4cOJTY2tkhblVEXIV5uMgIjXjmPBijG0ZaHX79+/TrHjx+nfPnyODo6KhPojalftWrVYsKECTg7OyulaH///Xfat2+Pu7s7kyZNUiY2X7lyhXv37nH79u0iJTzhj8piR44cYdmyZfTs2ZPKlSvLzVP8z3799VcmTpzIhQsXUKvVNGjQgK5du+Lu7o5er+eDDz5g8+bNTJ06lfDw8CJPrAcPHsz+/fv58ccfcXZ2Lnb/D7dh499QQUEBN2/exN7eXtqwKBU7duxg+PDh5OXl0aRJE7799lvlvVmzZjF79mw6derEBx98APzxfd+/f38OHTrEF198QURERLH7lrLIQrw6ZPxUvHKMQcPevXuBP560GV+fPHkyb775JsOGDSM6Opq4uDhOnjwJgLe3NzExMRw8eFCZvGxiYkJBQQHW1tZUrVqVa9euFanK5OLiQqVKlZTg5dHFKAFq1qzJF198QZUqVaTjJ/4y4/OmLVu20KFDB3JzcwkODqZ8+fIsXryYTz75hCNHjqBWq+nYsSOOjo7MnDkToEia182bN9FqtY8tUmncv7FT+OiCqiYmJjg4OEgbFqUmLCyM6OhoCgsLsbe3B+Du3bsAdOvWjapVq/Lzzz9z9OhR4MFaRwAjR47k+vXr/Pjjj+Tl5RXZpzEYl+BFiFeHpJCJV05hYSHvv/8+c+bMITQ0FCcnJwoKClCr1UyaNImEhAQ6d+5Mhw4dqFKlCjt37mTTpk1UqVIFDw8P/P39WbFiBRcuXMDLywtnZ2fUajUZGRnMmTMHNzc3WrRo8cT86T/7uhAlpVKpyM/P51//+peS89+hQweioqJwdHRk1apVZGRk0Lp1a9zd3cnKymLTpk3k5OTg4eHB3bt32bJli7IuRuPGjR/b/8P/CvEs3Lp1S1mAMj8//4mBhF6vR6VSodVqOXz4MIcOHaJnz56YmZmh0+koU6YMlpaW/Pzzz+Tl5REREYFGo0Gn01GuXDlcXV2Jjo5+bFRR2rMQrx4JYMQrxbiafX5+Pnv27CEvL4/w8HDUajXZ2dmMGTOG2rVrKwv1BQcHU69ePZYtW0Z2djaBgYG4uLhgbm7ODz/8wN69e3F2dubYsWNs2LCBffv20b9/f/z8/F70pYpXyMGDB7l69arS8SosLFTmrDzq0qVLTJkyhYiICNq3b6+87u/vT05ODklJSWi1Wvz9/alQoQK7d+9m9+7drFmzhqNHj5KQkIC/vz9Dhw59bARGiGctLS2NefPmcefOHby8vNBoNOTk5GAwGB4r/mAMNBwcHNDpdCQlJZGfn0/9+vWVvwcvLy9OnDjBgQMHcHFxoWrVqsp7fn5+2NnZKYGQEOLVJY+ExUvpSVO3jDettm3bEhgYSHJyMlu3bgUeTA7NycmhUaNGmJubU1hYiF6vx9/fn379+rF9+3YOHToEQHR0NA0aNCAjI4Pp06ezdOlSduzYwahRo4iMjHw+FyleC1evXqVv37588803XL9+HUApI3vjxg2ys7PJz89Xtler1dy6dQsTExN0Oh3wIOAB6NixI+bm5uzYsYN79+5RuXJlZX2X4OBgRo0axbfffkt8fDyurq7P/2LFa8fR0ZE1a9awfPly0tPT+fzzz2nfvj27d+8ust2j3+lvvfUWoaGhLFy4kIsXLxZp7z179uTq1ausXLlSmaP4MBntFuLVJ3/l4qVkDFQSEhLIzs4u8rqxMxcbG4tarWbJkiXcu3cPW1tbzM3NycrKUrY33uiioqIoX748+/btAx7MF+jduzcATZs2ZcyYMSQlJdGxY0fgj5xqIf5XWq2WQYMGcfDgQXbu3Km8Pn78eJo3b07Hjh0ZNGgQN2/eBMDNzY2aNWty/Phx7ty5A6BUC/P29sbX15fLly8rbbRjx464u7vzyy+/oNPpaNSoEYWFhcrfiRClxTiPZcCAAUrJ+W3bthEbG0vNmjWLbKtSqdDpdEydOpWjR4/i7OxM69atMTMz4+uvvwbA1NQUg8FAzZo1mThxIl9//fVjwYsQ4vUgAYx4aR04cIBRo0Yxb9485bWH026CgoLw8PDg8OHDrF27FhcXF3x8fFi3bh03btxQUs3gQelZR0dHTp48qUwKDQkJ4a233iIhIYGrV68CT0/tEeKv0Gg0NGvWjOrVqysrik+fPp0tW7bQunVrAgMD2bt3L8OHD+fatWvAg4D7wIEDSoqNcT/wICi/ceMGZmZmGAwGrK2t6dixI/fv32fOnDnKtjKhWZQ244OmJUuWcP/+faytrRk6dCg9evTA0dGxyLarV6+mVatWTJs2TXnI1KRJE9566y22bt1KamqqUgkPoEWLFtjY2EggLsRrSubAiJeWg4MDv/32GytXrqRhw4Y4Ojoqq92npqYyaNAgfvnlF8zMzMjIyKBVq1ZoNBo2bdrE3bt3CQsLUzpx9+7dY/r06dSoUYNmzZopZWN9fHxYuHAhBoOBwMBALC0tAZkUKp4tCwsLtFotixYtwtzcnJ07dxIdHc0//vEPWrZsiYeHB7NmzcLGxobAwECcnZ05deoUiYmJlC9fHi8vL+7cuUNqairx8fG88847hISEKO3Yy8uLtLQ0du/ejaurK1WrVpV5AuKZMxZLMTK2LxcXFypUqEBqaiouLi6EhYUBKOtsLVy4kM8++4xmzZoxduxYgoODUalUmJqaKpP2s7OziYyMfCzwlodJQryeJIARLy2NRoOLiwsbN24kKyuLt99+m4sXL/Lpp58yefJkAgICmDp1Kra2tmzevBmNRkO3bt04efIkK1euxMrKCq1Wy7Vr11i8eDFHjhwhNjYWLy8v5cZrZ2eHTqdj8eLFVKlSBT8/P+n0iVLh5ORETk4O8fHxaLVaxo0bh0ajwWAw4OXlRVZWFmvXrqVu3bpUqVKF6tWrs2bNGlasWEFqaiqpqaksWbIEe3t73n//faXcsbGst4ODA8uXL+f27du0bNlSOn7imTEGysY2tWnTJq5cuUJ+fj5arZbKlSsTEhLC4cOH2bNnDxUrVsTT01N54GRnZ0eLFi1o27YtLi4uqNVq5XvWmDIZFxf3Ii9RCPE3IwGMeKlptVp0Oh3x8fGcPn2ar776ChMTE0aNGkWPHj1wcXEhMDCQlJQU9u7dS1hYGBEREVy5coX58+ezYsUKtm7dSlJSEu+++y6dO3d+7Amfj48Py5cvJzAwkICAgBd0peJVZ2ZmhpOTEykpKdy/f5/w8HDKlSsHPHiSXa1aNRYtWsT9+/cJDAzEzc2NBg0aYG1tzeXLl7lx4wZNmjRhypQpODk5Kfs1dirLly9PtWrV6Nu3rwQv4pkyBhs//fQTsbGxbNy4kZUrV7J27Vr0ej2VK1fG3Nwcb29v4uPj0el01K9fn7Jly2IwGLC1taV8+fKYmpoW2a8xMKpQoQLwxxpbQgghAYx4qalUKtzd3Tlz5gzbtm1jwIABDBs2jICAAMqUKaOUVba2tiYxMZHc3Fzatm1L8+bNcXV1xcvLC3d3dz7//HNat26tPPF+eJSlbNmydOjQgeDg4Bd4peJ1YGdnx507d9ixYwf16tVTnlIbDAZsbGzQ6/XEx8cTGBiIp6cn9vb2hISE0KJFC9q0aUOTJk1Qq9WPdfSMbbpixYrSARSlIjk5mc8//5w6deoQFxdH06ZNuXv3Lt9//z0mJiZUr14dNzc3cnJySExMxNXVFX9/f2Vei3Fu4cOpjY+OdkvbFUIYSQAjXnpWVlZoNBq2bt3KG2+8QWhoaJH3VSoVVapUIS0tjb1796LVavH19cXPz4+6desSGhqKg4ODko9d3E2yTJkyz+tyxGtMo9Hg6urKtm3bSE9Pp379+lhZWSkdOX9/fzZu3EhaWhrBwcHKCI2pqSlmZmZKG350FFHSHsWz8mhwbJz3MnfuXE6fPs3EiROpU6cOXl5evP3225w5c4a1a9dSqVIlfHx8qFOnDgkJCVy5iEyoKwAAFexJREFUcgVfX1/UajWJiYmkpaVRrVo1aatCiBKRxxnildC4cWPCw8P5z3/+U6RM8qNllXNzc1mzZo2ynoBx7QG9Xo9arZYnfOKZ+aultitUqMB7773Hzp072bFjh1J1yWAwYG5uTq9evThx4gT3799/7LPShkVpMbZnY3BsrMxoYmJCYWEhx44do2rVqlSpUgVAabcjR44kPz+fzZs3c/XqVaysrBg4cCDHjx9nwIAB9O7dm08//ZRbt269gKsSQrysZARGvBLMzMxwcHBg1apV3Lt3jzfeeEN5z9ihc3JywtPTk169ej1WTUye+olnxZgC82ibejQ18UlUKhWurq6cOHGC1NRUQkNDsbOzUz7r6+tLz549HytDK0RpeLQ9JyYm8uGHH/Ljjz+SkZGBo6MjTk5OpKamkpGRQbdu3QCUVEYrKytyc3PZvn0777zzDlZWVvj7++Pg4EB+fj729vZMmTKFJk2avMjLFEK8ZCSAEa8MJycnbt68ydKlSwkNDcXZ2Vl57+FysmXLlpXJoOKZM7YxY0dv+/btzJgxg/T0dJycnJR0r5IwNzfHycmJJUuWoNFoqF27dpEJzhqN5rGStUKUhoeD7nXr1jF69Gg8PT2xsLAgOTmZXbt20alTJ3Jycli/fj1VqlTBy8uL/Px8pTLZ5cuX2bBhA61atVIKTPj7+xMeHs7bb7+NnZ0dhYWFxQb+QghRHAlgxCtDo9Hg5ubGjh07OHnyJM2bN1dWaZbJoKI0PTy6otPpmDBhAuPGjePatWts2rSJpKQkqlWrhqura4n36eDgwJkzZ0hLSyMyMvKxeVjShsXzoNfrGT9+PJs2beLGjRt4e3vz0Ucf0blzZxwdHVm1ahWFhYVERESwd+9ekpKSiImJoUyZMkobXbJkCZcvX6ZLly5FAnljOlphYSEajUaCFyFEickdULxSPD09iYqKYufOnVy4cOFFn454TRgrKS1fvpxt27Zx5MgRvvjiCxYsWMCSJUsoKChg2rRpnDt3Dvhj7tXTmJub8/nnn7N8+XJsbGxK+xKEKJZer+fq1askJCSwadMmOnXqpIyihIeH061bN2bOnInBYKBHjx7cvHmTuLg4UlNTSU9PZ/Xq1aSmphIREYGHh0exx3i06IQQQvw3KkNJ7qRCvETy8vLQ6XRotdoXfSriFVXcfJbk5GT+8Y9/UKNGDTw8PPjmm2+U97Zv306fPn2USctmZmYlnhMDDyZEG0cThXjezp49y7Bhw7h69SpLly7F2dlZCTrS0tIYOHAgfn5+jBs3jo0bN/Lll19y+/ZtXFxcuHbtGkFBQYwbN+5PjUAKIcTTSAqZeOWYmZlhbm4u81zEM2cwGJSKdY+qVKkS58+fJyUlhdDQUBo2bKiUNa5UqRLHjh1j+/btBAQE4Obm9l+Dl4cDHGnH4kWys7Pj1q1bbNmyhcDAQLy9vZU5WOXKlcPU1JS5c+dSo0YNWrRoQf369alVqxbu7u7ExsYyePBgrK2t/1TQLoQQTyMjMEII8ZBHAxRjp+vh169fv87x48cpX748jo6O2NnZAXD69Gnat29P48aN+eyzz7C3tyc/Px9TU1MuX75MkyZN6NChA0OGDMHW1rbYDt3Dr507dw69Xo+Xl9dzunohinf9+nXi4uK4efMmiYmJygKrKpWKixcvMmrUKC5evMjq1auLXTfLOM9FCCGeBXmsJ4QQDzEGKXv37gV4bBRk8uTJvPnmmwwbNozo6Gji4uI4efIkAN7e3sTExLBjxw4OHToEPFhksqCggPLlyxMbG8v69evZs2dPkX3DH/NiVCoV169f55NPPqFly5YcPnxYWVNDiBfF3t6e7t27k5mZyezZs4E/1oZxc3MjOjqa9PR05e/G6NH1Y4QQ4lmQERghhHhIYWEh/fr148CBA8yfPx9/f39lDsqkSZNYtmwZMTExVKtWjXPnzrF48WLKli3LF198QWhoKLm5uURFReHv78+oUaNwc3MrMofFz8+P2rVrM3Xq1MfmaRUWFjJ37lymT5+Os7MzsbGxtGzZEgsLixfxqxCiiHv37vHRRx+RkpLC5s2bsbe3V0ZWfv/9d3777TcqVKjwok9TCPEakDkwQojXlnGRvod/1mg05Ofns2fPHvLy8ggPD0etVpOdnc2YMWOoXbs2I0aMwNfXl+DgYOrVq8eyZcvIzs4mMDAQFxcXypQpw8KFC6lSpQp+fn6YmJig0+nQaDRUq1aNJk2aKCuWG23ZsoX333+fHTt20L17d0aOHEndunWLrP8ixItkYmKCi4sLGzduJDMzkzfffBN4MGpYpkwZbGxsiowkCiFEaZEUMiHEa8fYyVKr1cWmZ7Vt25ZatWqRnJzM1q1bAcjOziYnJ4dGjRopRSL0ej3+/v7069eP7du3K2ljHTp0oHr16ixbtowzZ84AKIFIeHg4QUFByjnk5uby7rvvMnDgQGrUqEF8fDz9+/dXStUK8XdSs2ZNmjRpwpo1a8jOzn6swIQsRimEeB4kgBFCvHaMHazvvvuOyMhIUlJSuHv3Lmq1mvz8fAB69uyJSqViyZIl3Lt3D1tbW8zNzcnKylL2Y+y8RUVFUb58efbt2wc8CFYGDx7M8ePH+emnn5RVyYs7hxs3buDh4cF3333H2LFj8fX1lapj4m9Lo9EwZMgQUlJScHZ2ftGnI4R4TUkKmRDitbR//34+//xzrl27xp49ezh79ixBQUFYWVkB4OrqysWLF9m+fTsODg7UqVOHHTt2cPjwYaKiorCwsCA/Px+NRoNarSYxMZHs7Gyio6NRq9V4eHhQtmxZ2rZti62t7RPPw87OjkaNGlG1alWZ6CxeChYWFlhYWEipeiHECyPfPEKI11L16tXp0qULAF5eXqxfv54ePXqwfv16ZZsePXrg4OCgjMK0adOG69evM336dOCPtLD8/HwuXbpE5cqV0Wg0SuWlXr164erqytNqpahUKszMzErrMoUoNRJwCyFeFBmBEUK8lkxMTNBqtezcuRNPT08GDBjAyZMnmT9/PteuXcPb21upIPbTTz9hYmJCt27dOHnyJCtXrsTKygqtVsu1a9dYvHgxR44cITY2Fi8vr8fKI8ucACGEEOLZkTLKQojXll6vZ/bs2UyePJk5c+ZQt25dJk+eTEJCAlqtlo8//piIiAi6du3KpUuXmDFjBlZWVkyYMIGff/4ZS0tL7O3tyczMpEePHgwZMkSqhgkhhBClTAIYIcRrLScnh7i4OAwGA0uWLMHU1JTjx48zcuRITp8+Tf/+/TE1NeWHH36gdu3aTJo0CYAVK1Zw+fJlbt++TevWrfHx8QFkxEUIIYQobZJCJoR4rVlaWmJlZcWSJUsoV64ctWrVwtnZmTfeeAN7e3tmzJhBdnY2eXl55ObmYmtri4+PD35+ftStW5fQ0FAcHBzQ6/UYDAaZ1CyEEEKUMglghBCvPVdXV86fP8/69et58803KVeuHDY2NgQFBVG5cmWys7M5ceIEt27d4s6dO7Ro0QKNRqOMtuj1etRqtYy8CCGEEM+BpJAJIQSwb98+4uLiaNOmDZ9++mmRYKSgoICJEyei1+vp37//U8siCyGEEKJ0SQAjhBA8KIU8adIklixZQnx8PAEBAcCD4MXExET5F6CwsFBKyAohhBAviCRrCyEED9Z06dixI25ubkyZMoX79+8DKEGL8V+9Xi/BixBCCPECSQAjhBD/n6enJ1FRUezcuZMLFy4Uu41M0hdCCCFeLEkhE0KIh+Tl5aHT6dBqtS/6VIQQQghRDAlghBCiGDLPRQghhPh7kgBGCCGEEEII8dKQZG4hhBBCCCHES0MCGCGEEEIIIcRLQwIYIYQQQgghxEtDAhghhBBCCCHES0MCGCGEEEIIIcRLQwIYIYQQf3tZWVn4+PgwderUp772dzJ8+HB8fHye+X6nTp2Kj48PWVlZz3zfQgjxMjB50ScghBDi72nPnj1069atyGsWFhZ4enrSunVrunTp8tKulZOVlcXKlSuJiIjAz8/vRZ8O9+/fJyEhgVWrVpGVlcXdu3fRarVUqVKFevXq0adPnxd9ikII8bchAYwQQoinatWqFW+88QYGg4GcnBxWrlzJ2LFjOXv2LF9++eULOy83NzeOHj36l4Koixcv8t133+Hm5vbCA5iCggK6d+/OoUOHaNSoEZGRkVhYWJCVlcXRo0eZNWtWkQAmLi6OPn36YGZm9gLPWgghXhwJYIQQQjxVtWrVaN26tfJzp06dePvtt1m2bBmDBg3CwcGh2M/l5eVhZWVVauelUqkoU6ZMqe3/edmyZQuHDh2ie/fujBgx4rH3r169WuRnExMTTEzk9i2EeH3JHBghhBB/ipWVFbVq1cJgMJCZmQlAeHg4Xbt25eTJk7z33nsEBQURFRWlfCY9PZ2PPvqIhg0bUr16dcLDw5kwYQJ37tx5bP/79+8nJiaGgIAAGjRowOjRo4vd7mlzYBITE+natSt16tShZs2aNGvWjDFjxqDT6VixYoWSGvfJJ5/g4+ODj48PXbt2VT5vMBhYvHgx7dq1o2bNmtSqVYuuXbuye/fux451//59JkyYQMOGDQkICKB9+/akpKSU+PeZkZEBQEhISLHvOzo6Fvn5SXNg0tLSiI2NJTAwkHr16vHxxx+Tm5uLj48Pw4cPV7Z7+PeWlJREdHQ0NWrUoGHDhkyYMIGCgoISn7sQQrwI8ghHCCHEn2IwGJROt52dnfL6pUuX6N69O82bN+ett95Sgo7jx4/TvXt3bGxs6NixI87OzqSlpbFo0SIOHTrEokWLMDU1BeDIkSP07NkTS0tLevfujbW1NRs2bODjjz8u8flNnjyZGTNmULVqVXr06IGjoyMXLlxg48aNDBw4kODgYPr27cuMGTPo2LEjQUFBAEVGkj766CPWr19Ps2bNaNeuHTqdjrVr1xIbG8vUqVNp2rSpsu2QIUPYvHkzTZo0ISwsjAsXLjBgwAAqVKhQovN1d3cHYM2aNYSEhFC2bNkSX6tReno6nTt3Rq/X07VrV5ydnUlOTqZXr15P/ExycjKLFy8mJiaG6OhotmzZwty5cylXrhx9+/b90+cghBDPiwQwQgghnuru3bvk5uYCkJOTQ3x8PGlpaQQGBlKpUiVlu6ysLMaMGcM777xT5PMjRozA0dGR5cuXF0kpCwkJoX///qxdu5Z27doBMG7cOAwGA0uWLMHT0xN4kLLWqVOnEp3r0aNHmTFjBvXq1WP27NlFUsw+/PBDAGxsbGjQoAEzZswgMDCwSHocwKZNm1i7di2jR4+mY8eOyuvdunWjQ4cOfPXVV4SHh6NSqUhJSWHz5s20bduW8ePHK9sGBwfTr1+/Ep1z06ZN8ff3Z8OGDezYsYOgoCBq1KhB7dq1CQ4OVoK7p5k8eTJ5eXksXrxYCci6dOnC4MGDOXHiRLGfOXv2LOvWrVMCrXfffZfIyEji4+MlgBFC/K1JCpkQQoinmjp1KiEhIYSEhNC6dWt+/PFHwsPDmTZtWpHtbG1tlUDE6NSpU5w6dYpWrVqh0+nIzc1V/gsKCsLCwoKdO3cCcP36dQ4dOkR4eLgSvACYmZnRo0ePEp3rmjVrABg6dOhj82NUKhUqlapE+7C0tCQiIqLI+d66dYvw8HAuXrxIeno6AJs3bwbgvffeK7KPiIiIItfwNGZmZixatIjBgwfj6upKcnIyU6dOpWfPnjRq1Ei5picpLCxk+/btBAQEKMGLUWxs7BM/17Rp0yKjRCqVinr16nH16lVu375donMXQogXQUZghBBCPFXHjh1p3rw5KpUKc3NzKlWqhK2t7WPbubu7P1YR7Ny5c8CDIOhJ67Vcu3YNQJlPU7ly5ce2qVq1aonONSMjA5VKha+vb4m2L865c+e4ffs2DRo0eOI2169fx9PTk8zMTNRqdZGRKKMqVapw/vz5Eh3T0tKSuLg44uLiyMvL4+jRo2zevJmEhAQ+/vhj3NzcHgtOjHJzc7lz506xAdPTgihj6trDjP9fb968iaWlZYnOXQghnjcJYIQQQjxVxYoVn9qZNzI3N3/ie7GxsYSFhRX7no2NzV8+t+KUdKTlSQwGA1qtlm+++eaJ23h5ef3l/f83VlZWNGjQgAYNGuDr68vIkSNZsWLFEwOYv+pp5acNBsMzPZYQQjxLEsAIIYQoNRUrVgRArVb/1yDImM7066+/Pvbe2bNnS3S8SpUqsX37dtLS0ggICHjidk8LcCpWrEh6ejo1a9b8r6MQ7u7u6PV60tPTHwtqjKNP/4uaNWsCkJ2d/cRttFotFhYWxY72lHQESAghXiYyB0YIIUSpqVatGt7e3vzwww9KitjDCgoKuHnzJvCgClhgYCBbt24t0vHW6XTMnz+/RMeLjIwE4F//+hc6ne6x940jCxYWFgD89ttvj23Tpk0b9Ho9//rXv4o9hjHlDVCqkf3nP/8pss3mzZtLHDz88ssv5OTkFPuecY7N01LoNBoNYWFhHD16lAMHDhR5b+7cuSU6ByGEeJnICIwQQohSo1KpmDhxIt27dycqKoro6GiqVq3KvXv3yMjIYNOmTQwZMkSZ/D98+HC6du3Ku+++S+fOnZUyyoWFhSU6XkBAAL1792b27Nm0a9eOt99+G0dHR7KyskhMTGTZsmXY2NhQtWpVLC0tWbx4MWXLlsXGxgatVktISAjNmzenXbt2xMfHc+LECZo0aYKdnR1Xrlzh8OHDZGRksGXLFgDCwsJo0qQJK1eu5ObNm4SFhZGZmcnSpUvx9vbm9OnT//WcU1NTmTx5MqGhodSuXRsHBwd+//139u7dy9atW3F0dKRnz55P3cfgwYNJSUmhV69edOnSBRcXF7Zt26ZUj/tfUuqEEOLvRgIYIYQQpcrPz4+VK1cyc+ZMtm7dyg8//IClpSVubm60bdu2yAKOtWrVYt68eXzzzTfMmjULa2trmjVrppT4LYkPP/wQX19f4uPjmTNnDgaDARcXF9544w1ljZWyZcsyefJkvv32W8aOHYtOp6Nu3brKuYwbN4569eqRkJDAzJkzyc/Px9HRkWrVqjF06NAix/v222/59ttvWbt2LampqXh7ezN16lTWrVtXogCmWbNm6HQ6UlNTWbx4MdevX8fExAQ3Nzd69OjBe++999hilo+qXLky33//PRMmTGDhwoWUKVOGxo0bM2rUKCIiIh6ryCaEEC8zlUFm6gkhhBCvpOPHjxMdHc3QoUPp06fPiz4dIYR4JmQOjBBCCPEKuHfvXpGfDQYDc+bMAShRFTkhhHhZSAqZEEII8Qpo3bo19evXx9vbm7t375KUlMT+/ftp0aIF1atXf9GnJ4QQz4ykkAkhhBCvgIkTJ5KUlMSVK1coKCigQoUKREZG0rt3b0xNTV/06QkhxDMjAYwQQgghhBDipSFzYIQQQgghhBAvDQlghBBCCCGEEC8NCWCEEEIIIYQQLw0JYIQQQgghhBAvDQlghBBCCCGEEC8NCWCEEEIIIYQQL43/B6EMOx2G1L0kAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j_Ev8kTSNT6L"
      },
      "source": [
        "## Evaluating Performance Over Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "knzcVqvONT6N",
        "outputId": "35b9ec60-cc27-40a8-f769-d0d4e0b49e49"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(test_sentences, test_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,071 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,071 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,071 samples\n",
            "\n",
            "     1,071 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:01\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l6EJfj0TNT6R",
        "outputId": "a9e3ea14-9911-4bc9-d2c7-557a5b36a2b3"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.62      0.64      0.63       194\n",
            "Non_hope_speech       0.89      0.89      0.89       776\n",
            "  not-malayalam       0.83      0.76      0.79       101\n",
            "\n",
            "       accuracy                           0.83      1071\n",
            "      macro avg       0.78      0.77      0.77      1071\n",
            "   weighted avg       0.84      0.83      0.83      1071\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "ZE3EG9RTNT6S",
        "outputId": "503693dd-f727-4fe6-f9dd-742b58a4f22d"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2fOJyH_c3ON2"
      },
      "source": [
        "## Saving the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3PXqG-VpurVS"
      },
      "source": [
        "torch.save(model,\"./drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/BERT_Mutlti_Malayalam\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a9M_91z1yj0F"
      },
      "source": [
        "## Loading the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "42ObCUU1QcsJ"
      },
      "source": [
        "model = torch.load(\r\n",
        "    './drive/MyDrive/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/BERTForSequenceClassification_Mutlti_Malayalam_v2',\r\n",
        "    map_location=device\r\n",
        "    )"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sAaHpZdIzsnT",
        "outputId": "dbea6eee-1e96-4254-d082-a6a842d8fe89"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "BertForSequenceClassification(\n",
              "  (bert): BertModel(\n",
              "    (embeddings): BertEmbeddings(\n",
              "      (word_embeddings): Embedding(105879, 768, padding_idx=0)\n",
              "      (position_embeddings): Embedding(512, 768)\n",
              "      (token_type_embeddings): Embedding(2, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): BertEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): BertLayer(\n",
              "          (attention): BertAttention(\n",
              "            (self): BertSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): BertSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): BertIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): BertOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "    (pooler): BertPooler(\n",
              "      (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "      (activation): Tanh()\n",
              "    )\n",
              "  )\n",
              "  (dropout): Dropout(p=0.1, inplace=False)\n",
              "  (classifier): Linear(in_features=768, out_features=3, bias=True)\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RCo7olPPnYNz"
      },
      "source": [
        "## Making Predictions on Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YkVQsHdKnYN0"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test.csv')\r\n",
        "test_df = pd.read_csv(test_df_path,sep = '\\t')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "nungZ-9dnYN0",
        "outputId": "e39dceb8-ff04-436a-bc01-d9c0fe6889d6"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...\n",
              "3                                          @Albin Baiju\n",
              "4                                       I respect you..\n",
              "...                                                 ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...\n",
              "1067                                      @surya ishaan\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...\n",
              "1070                              Poorru  angodu chellu\n",
              "\n",
              "[1071 rows x 1 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7jLPpljYQcsQ"
      },
      "source": [
        "## Loading `test_sentences`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QEVoAhgIQcsR"
      },
      "source": [
        "test_sentences = test_df['text'].values \r\n",
        "test_ids = test_df.index.values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "slovGuCRThW1",
        "outputId": "896028f4-4527-479f-dd76-b52c74afdfd6"
      },
      "source": [
        "test_ids"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([   0,    1,    2, ..., 1068, 1069, 1070])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gL7aCG2HTjv6",
        "outputId": "987c5f4d-7d48-4f36-9720-a81fe3f850bd"
      },
      "source": [
        "test_sentences"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['അതെ അണപൊട്ടി ഒഴുകുകയാണ്', 'കെവിൻ avde pettupoyi🤣🤣🤣',\n",
              "       '@my voice ullup illa daaa tayoli ath kond alle ninte ammaye njan panniyatha monee',\n",
              "       ..., 'ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ',\n",
              "       'ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...',\n",
              "       'Poorru  angodu chellu'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 71
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "b9dgO1m3QcsU",
        "outputId": "031d1fdf-c46f-4a64-8650-9e5846392433"
      },
      "source": [
        "(py_inputs, py_attn_masks,py_ids) = make_smart_batches_on_test(test_sentences,test_ids, 16,tokenizer,max_input_length = 400)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,071 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,071 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,071 samples\n",
            "\n",
            "     1,071 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vjsjqQpRQcsV"
      },
      "source": [
        "## Evaluating accuracy over test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rwkx-30AQcsV",
        "outputId": "d2d16d92-bf8e-4184-b0d0-ea04f1a6fb9a"
      },
      "source": [
        "y_ids,y_preds  = get_predictions_test(py_inputs, py_attn_masks,py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:01\n",
            "  Batch      63  of       67.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pDM-cnDHQcsW",
        "outputId": "b364feef-d836-44f8-c03d-fe3d5f4be317"
      },
      "source": [
        "print(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 1 1 ... 0 0 1]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kWWWjz7eUPc7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8f0f2176-6317-4380-8ba6-dd2cf9798529"
      },
      "source": [
        "print(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 846  861  871 ...  741  178 1004]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "u2ybbsAoQcsY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5183909c-9ef7-4322-eece-f07c7ce56155"
      },
      "source": [
        "le.inverse_transform(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Non_hope_speech', 'Non_hope_speech', 'Non_hope_speech', ...,\n",
              "       'Hope_speech', 'Hope_speech', 'Non_hope_speech'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "kSMb6sCLQcsZ",
        "outputId": "10fd72ef-4397-4239-effd-01c6285b8c8b"
      },
      "source": [
        "sns.countplot(y =le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f71aa5aa470>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 77
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4KXOXwH9U2MT",
        "outputId": "74497f91-0750-4ff8-e7a3-683a6b9420df"
      },
      "source": [
        "len(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 78
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9-fkBgOxU4bX",
        "outputId": "d4e4aa8e-42d5-45cc-b3e2-9fd4035c48e4"
      },
      "source": [
        "len(le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 79
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sWPDqogJrjIZ"
      },
      "source": [
        "## Creating Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "o4Hb7RD1yHol"
      },
      "source": [
        "df_new = pd.DataFrame({\r\n",
        "    'id':y_ids,\r\n",
        "    'label':le.inverse_transform(y_preds)\r\n",
        "})"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "twQAkVzcn4Lg"
      },
      "source": [
        "test_df['id'] = test_df.index"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "qov36eWmqawv",
        "outputId": "75622337-0274-4f08-d1a7-fdeaaad2275e"
      },
      "source": [
        "df_new"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>846</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>861</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>871</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>953</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>990</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>355</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>585</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>741</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>178</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>1004</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id            label\n",
              "0      846  Non_hope_speech\n",
              "1      861  Non_hope_speech\n",
              "2      871  Non_hope_speech\n",
              "3      953  Non_hope_speech\n",
              "4      990  Non_hope_speech\n",
              "...    ...              ...\n",
              "1066   355  Non_hope_speech\n",
              "1067   585  Non_hope_speech\n",
              "1068   741      Hope_speech\n",
              "1069   178      Hope_speech\n",
              "1070  1004  Non_hope_speech\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "z0CEApHmqdLr",
        "outputId": "1039ba5f-a702-4582-8bfa-8f0a83fc3625"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2\n",
              "3                                          @Albin Baiju     3\n",
              "4                                       I respect you..     4\n",
              "...                                                 ...   ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066\n",
              "1067                                      @surya ishaan  1067\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069\n",
              "1070                              Poorru  angodu chellu  1070\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 83
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "vxReWWmxn7Hj",
        "outputId": "bf948560-c34c-4a16-b554-733764ab87b8"
      },
      "source": [
        "df_f = pd.merge(test_df,df_new,on = 'id')\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id            label\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0  Non_hope_speech\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1  Non_hope_speech\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2  Non_hope_speech\n",
              "3                                          @Albin Baiju     3  Non_hope_speech\n",
              "4                                       I respect you..     4    not-malayalam\n",
              "...                                                 ...   ...              ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066  Non_hope_speech\n",
              "1067                                      @surya ishaan  1067    not-malayalam\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068  Non_hope_speech\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069  Non_hope_speech\n",
              "1070                              Poorru  angodu chellu  1070  Non_hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 84
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "1kuASymYn9aV",
        "outputId": "60fc4fb9-1783-4dee-f856-a3f38e688d80"
      },
      "source": [
        "df_f = df_f[['id','text','label']]\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>1066</td>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>1067</td>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>1068</td>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>1069</td>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>1070</td>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id                                               text            label\n",
              "0        0                            അതെ അണപൊട്ടി ഒഴുകുകയാണ്  Non_hope_speech\n",
              "1        1                            കെവിൻ avde pettupoyi🤣🤣🤣  Non_hope_speech\n",
              "2        2  @my voice ullup illa daaa tayoli ath kond alle...  Non_hope_speech\n",
              "3        3                                       @Albin Baiju  Non_hope_speech\n",
              "4        4                                    I respect you..    not-malayalam\n",
              "...    ...                                                ...              ...\n",
              "1066  1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  Non_hope_speech\n",
              "1067  1067                                      @surya ishaan    not-malayalam\n",
              "1068  1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  Non_hope_speech\n",
              "1069  1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  Non_hope_speech\n",
              "1070  1070                              Poorru  angodu chellu  Non_hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 85
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "p3FtBVTVroJi"
      },
      "source": [
        "## Saving Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SzoT0p9rqrO-"
      },
      "source": [
        "path = './drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/SubmissionFiles'"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LZmgZFM4qi7F"
      },
      "source": [
        "df_f.to_csv(join(path,'bert_multi_malayalam.csv'),index=False)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jW9g_qgMv7mq"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}