Stock_Price_Prediction_Using_LSTM_&_ARIMA.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Stock Price Prediction Using LSTM & ARIMA.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyOTjfPUeg6QfeA8AQnU6lWY",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/neetinds/Stock-Price-Prediction/blob/main/Stock_Price_Prediction_Using_LSTM_%26_ARIMA.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "27uKvhb2xp0v"
      },
      "source": [
        "# **Stock Price Prediction Using LSTM & ARIMA**\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "GmFu3gFixct3"
      },
      "source": [
        "## **1. Stock Price Predicting with LSTM**\n",
        "\n",
        "Neural Networks have been demonstrated to be very powerful in solving the real-world problems like imaging and natural language processing. Interested in stock price movements, I am therefore motivated and curious about employing nerual nets to approach financial time series problems of its kind.\n",
        "\n",
        "Unlike common regression predictions, time series problems are more difficult due to sequence dependence within the input data variables. Among various neural nets, Long Short-Term Memory (LSTM), a type of recurrent neural network, has been proven to take care of complex time series predictions. So I implement LSTM to Amazon's stock prices (AMZN)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Wcw8RybPkFvN"
      },
      "source": [
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
        "import matplotlib.pyplot as plt\n",
        "from datetime import datetime\n",
        "from sklearn import preprocessing\n",
        "import pandas_datareader as web\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, LSTM\n",
        "import math"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Od_m3SkCyLGH"
      },
      "source": [
        "Mount my GDRIVE"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OQQ7XO7vkKSD",
        "outputId": "dee53817-877a-4d63-e61c-02a1675b7acc"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0vIrMGLPyVek"
      },
      "source": [
        "# 1.1 Load Data\n",
        "# LSTM Modeling For AMAZON Stock Price\n",
        "Get up to five-year daily historical stock prices & volumes data from https://finance.yahoo.com/quote/AMZN/history?p=AMZN.\n",
        "\n",
        "Datasets consist of following columns:\n",
        "\n",
        "\n",
        "*   **Date Time** stamp of when data was collected, being used as index column;\n",
        "\n",
        "*   **Volume** The number of shares traded in AMZN during a given trading day;\n",
        "\n",
        "\n",
        "\n",
        "*   **Open** The price at AMZN upon the opening of an exchange on a given trading day\n",
        "\n",
        "\n",
        "*   **High** The highest price at which AMZN traded during the course of the day\n",
        "\n",
        "*   **Low** The lowest price at which AMZN traded during the course of the day;\n",
        "\n",
        "\n",
        "*   **Close** The final price at which AMZN traded during the course of the day; it is also selected as our target data."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EwT-pj7dkd1m"
      },
      "source": [
        "data = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/AMZN.csv')\n"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vcPgAzaakULY",
        "outputId": "1cd88334-21e6-40be-c3c2-5e6f3a349435"
      },
      "source": [
        "data.info()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 2518 entries, 0 to 2517\n",
            "Data columns (total 7 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Date       2518 non-null   object \n",
            " 1   Open       2518 non-null   float64\n",
            " 2   High       2518 non-null   float64\n",
            " 3   Low        2518 non-null   float64\n",
            " 4   Close      2518 non-null   float64\n",
            " 5   Adj Close  2518 non-null   float64\n",
            " 6   Volume     2518 non-null   int64  \n",
            "dtypes: float64(5), int64(1), object(1)\n",
            "memory usage: 137.8+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xrwTGg41lGA0"
      },
      "source": [
        "#Change the date foramt and set it as index\n",
        "data['Date'] = pd.to_datetime(data['Date'])\n",
        "data.set_index('Date',inplace=True)"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cop1WFqXk2Zg",
        "outputId": "6c6ed4e5-7c69-4e4b-ddb6-b6702cb78a14"
      },
      "source": [
        "data.shape"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2518, 6)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 521
        },
        "id": "XnBdbrqzlS_G",
        "outputId": "0bb15569-c506-4512-b0a5-d3a59c88e8e1"
      },
      "source": [
        "#plotting the data\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.title('Close Price History')\n",
        "plt.plot(data['Close'], color='red')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price USD', fontsize = 18)\n",
        "plt.show()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "e-ZI0Bp4z0nV"
      },
      "source": [
        "The next step is to split the data into training and test sets to avoid overfitting and to be able to investigate the generalization ability of our model. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ct9SoaLdlcfi",
        "outputId": "a7f2fd98-59f4-417e-d445-271837863c74"
      },
      "source": [
        "# Create a new data frame with only 'Close column'\n",
        "data = data.filter(['Close'])\n",
        "dataset = data.values #convert the data frame to a numpy array\n",
        "training_data_len = math.ceil(len(dataset)*.7)  # number of rows to train the model on\n",
        "training_data_len"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1763"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EGg0hbC_z9aq"
      },
      "source": [
        "**Scale the data**\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nsCBYE3Ylo2r",
        "outputId": "55f205bb-d6ae-4307-ee9b-9ec1e5c67f03"
      },
      "source": [
        "#Scale the data\n",
        "scaler = MinMaxScaler(feature_range=(0,1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "scaled_data"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00506753],\n",
              "       [0.00468776],\n",
              "       [0.00454534],\n",
              "       ...,\n",
              "       [0.90270824],\n",
              "       [0.89772377],\n",
              "       [0.89055865]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NEKElVeY0GDm"
      },
      "source": [
        "# **Create the training dataset, scaled training dataset**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9OruwkUJluKZ",
        "outputId": "023ff90d-7013-40ae-a8cf-879617f11a5d"
      },
      "source": [
        "train_data = scaled_data[0:training_data_len, :]\n",
        "#Split the data into x_train, y_train datasets\n",
        "x_train = []\n",
        "y_train = []\n",
        "for i in range(60,len(train_data)):\n",
        "    x_train.append(train_data[i-60:i, 0])\n",
        "    y_train.append(train_data[i,0])\n",
        "    if i<=60:\n",
        "        print(x_train)\n",
        "        print(y_train)\n",
        "        print()"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[array([0.00506753, 0.00468776, 0.00454534, 0.00411811, 0.00434656,\n",
            "       0.00394009, 0.00384812, 0.00433173, 0.00506456, 0.00492808,\n",
            "       0.0066222 , 0.00705537, 0.00705834, 0.00641452, 0.006281  ,\n",
            "       0.00596947, 0.00664594, 0.00646199, 0.00564608, 0.00689813,\n",
            "       0.00713251, 0.00784755, 0.0073847 , 0.00727493, 0.0070346 ,\n",
            "       0.00693373, 0.00685659, 0.0072868 , 0.00824215, 0.00898388,\n",
            "       0.00768436, 0.0062276 , 0.00488061, 0.0047115 , 0.00466699,\n",
            "       0.00427832, 0.00696637, 0.00301737, 0.00257233, 0.00330517,\n",
            "       0.00372647, 0.00377988, 0.00443853, 0.00458688, 0.00655396,\n",
            "       0.00721856, 0.00748855, 0.0083905 , 0.00873763, 0.00832522,\n",
            "       0.00761019, 0.00794842, 0.00757459, 0.00577069, 0.00466105,\n",
            "       0.00497852, 0.00482721, 0.00365526, 0.002513  , 0.00327847])]\n",
            "[0.0035069165742997455]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9ocT_DVul33u"
      },
      "source": [
        "#convert the x_train and y_train  to numppy array\n",
        "x_train,y_train = np.array(x_train), np.array(y_train)"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2pAqxKasl7JX",
        "outputId": "d84ff29d-1fc1-410e-f664-fdcfcf55158d"
      },
      "source": [
        "#reshape the data\n",
        "x_train = np.reshape(x_train,(x_train.shape[0],x_train.shape[1],1))\n",
        "x_train.shape"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1703, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "imQv0214l-mt"
      },
      "source": [
        "#Buil the LSTM model\n",
        "model =Sequential()\n",
        "model.add(LSTM(64,return_sequences=True, input_shape=(x_train.shape[1],1)))\n",
        "model.add(LSTM(64, return_sequences= False))\n",
        "model.add(Dense(32))\n",
        "model.add(Dense(1))"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rY8DEJg3mAzh"
      },
      "source": [
        "#Complie the model\n",
        "model.compile(optimizer='adam', loss='mean_squared_error')"
      ],
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7-LSMPVgmG4x",
        "outputId": "b9b42e1e-dea0-4c00-f8f2-7ff2cfc703dd"
      },
      "source": [
        "#Train the model\n",
        "model.fit(x_train,y_train, batch_size=1, epochs=10)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/10\n",
            "1703/1703 [==============================] - 58s 24ms/step - loss: 3.5829e-04\n",
            "Epoch 2/10\n",
            "1703/1703 [==============================] - 40s 24ms/step - loss: 7.1320e-05\n",
            "Epoch 3/10\n",
            "1703/1703 [==============================] - 40s 24ms/step - loss: 5.1347e-05\n",
            "Epoch 4/10\n",
            "1703/1703 [==============================] - 40s 23ms/step - loss: 6.2551e-05\n",
            "Epoch 5/10\n",
            "1703/1703 [==============================] - 39s 23ms/step - loss: 3.0327e-05\n",
            "Epoch 6/10\n",
            "1703/1703 [==============================] - 40s 23ms/step - loss: 2.5827e-05\n",
            "Epoch 7/10\n",
            "1703/1703 [==============================] - 40s 23ms/step - loss: 3.0713e-05\n",
            "Epoch 8/10\n",
            "1703/1703 [==============================] - 40s 24ms/step - loss: 3.3055e-05\n",
            "Epoch 9/10\n",
            "1703/1703 [==============================] - 40s 23ms/step - loss: 3.2677e-05\n",
            "Epoch 10/10\n",
            "1703/1703 [==============================] - 42s 24ms/step - loss: 3.1315e-05\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f3c6b03c590>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7ycrjkcWmQlf"
      },
      "source": [
        "#create the testing data sets\n",
        "#create a new array containing scale values from index 1763 to 2518\n",
        "test_data= scaled_data[training_data_len-60:, :]\n",
        "#create the data sets x_test and y_test\n",
        "x_test = []\n",
        "y_test = dataset[training_data_len:,:]\n",
        "for i in range(60,len(test_data)):\n",
        "    x_test.append(test_data[i-60:i,0])"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0kGTUGvSmweu"
      },
      "source": [
        "#convert the data to a numpy array\n",
        "x_test = np.array(x_test)"
      ],
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5u9duzWi1jyC",
        "outputId": "913c5bed-985d-423f-ec44-8e63eec68d52"
      },
      "source": [
        "y_test.shape"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(755, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xz2yldkIm19h",
        "outputId": "0384ca9e-0b70-4a98-b1a2-eb9c356e8213"
      },
      "source": [
        "#reshape the data\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1],1))\n",
        "x_test.shape"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(755, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tMtWX7DAm5p6"
      },
      "source": [
        "#predicting the data\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)"
      ],
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qQzOUDUs1ezB",
        "outputId": "46085bec-0f10-4d27-eaef-c5ddb745c70d"
      },
      "source": [
        "predictions.shape"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(755, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_bjMCVHCm8aw",
        "outputId": "75469ffd-29e1-4c50-c13a-354725dd0bc1"
      },
      "source": [
        "#get the root mean square error(RMSE)\n",
        "rmse = np.sqrt(np.mean(predictions - y_test)**2)\n",
        "rmse"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "27.198338724679218"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 640
        },
        "id": "YJ_qwlf_nAaO",
        "outputId": "4e8f4b0e-828f-4bf4-81b8-269535087d87"
      },
      "source": [
        "#plot the data\n",
        "train = data[:training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions'] = predictions\n",
        "#Visialization the data\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price' ,fontsize=18)\n",
        "plt.plot(train['Close'],linewidth=3.5)\n",
        "plt.plot(valid[['Close','Predictions']],linewidth=3.5)\n",
        "plt.legend(['Train','Valid','Predictions'])"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  after removing the cwd from sys.path.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7f3c69d27c10>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "bwTZeoaWoSl_",
        "outputId": "c6d6d5d3-a202-4399-c5bb-581827d0e75c"
      },
      "source": [
        "#show the valid and predicted price\n",
        "valid"
      ],
      "execution_count": 27,
      "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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2017-12-06</th>\n",
              "      <td>1152.349976</td>\n",
              "      <td>1180.535889</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-07</th>\n",
              "      <td>1159.790039</td>\n",
              "      <td>1190.031006</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-08</th>\n",
              "      <td>1162.000000</td>\n",
              "      <td>1196.109253</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-11</th>\n",
              "      <td>1168.920044</td>\n",
              "      <td>1197.122437</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-12</th>\n",
              "      <td>1165.079956</td>\n",
              "      <td>1204.060181</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-11-30</th>\n",
              "      <td>3168.040039</td>\n",
              "      <td>3171.243408</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-01</th>\n",
              "      <td>3220.080078</td>\n",
              "      <td>3141.889893</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-02</th>\n",
              "      <td>3203.530029</td>\n",
              "      <td>3206.718262</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-03</th>\n",
              "      <td>3186.729980</td>\n",
              "      <td>3174.059326</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-04</th>\n",
              "      <td>3162.580078</td>\n",
              "      <td>3163.927002</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>755 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                  Close  Predictions\n",
              "Date                                \n",
              "2017-12-06  1152.349976  1180.535889\n",
              "2017-12-07  1159.790039  1190.031006\n",
              "2017-12-08  1162.000000  1196.109253\n",
              "2017-12-11  1168.920044  1197.122437\n",
              "2017-12-12  1165.079956  1204.060181\n",
              "...                 ...          ...\n",
              "2020-11-30  3168.040039  3171.243408\n",
              "2020-12-01  3220.080078  3141.889893\n",
              "2020-12-02  3203.530029  3206.718262\n",
              "2020-12-03  3186.729980  3174.059326\n",
              "2020-12-04  3162.580078  3163.927002\n",
              "\n",
              "[755 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "b_kzNCT5oaN2",
        "outputId": "d9772dad-6cd5-46c1-d885-585d2461a355"
      },
      "source": [
        "#get the quote\n",
        "amzn_quote = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/AMZN.csv')\n",
        "#Create new data frame\n",
        "new_df = amzn_quote.filter(['Close'])\n",
        "#get the last 60 days closing price values and convert the dataframe to an array\n",
        "last_60_days = new_df[-60:].values\n",
        "#scaled the data to be values between 0 and 1\n",
        "last_60_days_scaled = scaler.transform(last_60_days)\n",
        "#create an empty list\n",
        "X_test = []\n",
        "#append the past 60 days \n",
        "X_test.append(last_60_days_scaled)\n",
        "#convert the X_test data set to a numpy array\n",
        "X_test = np.array(X_test)\n",
        "#Reshape the data\n",
        "X_test = np.reshape(X_test,(X_test.shape[0], X_test.shape[1],1))\n",
        "#get the predicted scaled price\n",
        "pred_price= model.predict(X_test)\n",
        "#undo the scalling\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "pred_price"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[3142.0105]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZLtslyL_EpKD"
      },
      "source": [
        "# Accuracy Score - AMAZON LSTM Prediction"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "y-zDKT8AEs5j",
        "outputId": "daf4c51e-cb7b-49e2-99e0-6044680cbddc"
      },
      "source": [
        "# Measure the Accuracy Score\n",
        "Acc = []\n",
        "from sklearn.metrics import r2_score\n",
        " \n",
        "print(\"Accuracy score of the predictions: {0}\".format(r2_score(y_test, predictions)))\n",
        "Acc.append(r2_score(y_test, predictions))"
      ],
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the predictions: 0.989736026487859\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "V1iHK8DDE2ep"
      },
      "source": [
        "\n",
        "\n",
        "---\n",
        "\n",
        "\n",
        "\n",
        "---\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yN6V1nvCsobm"
      },
      "source": [
        "# 1.2 LSTM Modeling For Google Stock"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R2ATAgCBsmeo"
      },
      "source": [
        "data_G = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/GOOG.csv')"
      ],
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iSSbvO14tZ2j",
        "outputId": "bdc4de81-8026-4e81-abe1-2c5b287effe5"
      },
      "source": [
        "data_G.info()"
      ],
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 2752 entries, 0 to 2751\n",
            "Data columns (total 7 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Date       2752 non-null   object \n",
            " 1   Open       2752 non-null   float64\n",
            " 2   High       2752 non-null   float64\n",
            " 3   Low        2752 non-null   float64\n",
            " 4   Close      2752 non-null   float64\n",
            " 5   Adj Close  2752 non-null   float64\n",
            " 6   Volume     2752 non-null   int64  \n",
            "dtypes: float64(5), int64(1), object(1)\n",
            "memory usage: 150.6+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1IgGixgmuKKx",
        "outputId": "675f16fd-1049-42ae-ed22-dc84d725580f"
      },
      "source": [
        "#Change the date foramt and set it as index\n",
        "#dtype.data_G['Date']\n",
        "data_G['Date'] = pd.to_datetime(data_G['Date'])\n",
        "data_G.set_index('Date',inplace=True)\n",
        "data_G.info()"
      ],
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "DatetimeIndex: 2752 entries, 2010-01-04 to 2020-12-07\n",
            "Data columns (total 6 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Open       2752 non-null   float64\n",
            " 1   High       2752 non-null   float64\n",
            " 2   Low        2752 non-null   float64\n",
            " 3   Close      2752 non-null   float64\n",
            " 4   Adj Close  2752 non-null   float64\n",
            " 5   Volume     2752 non-null   int64  \n",
            "dtypes: float64(5), int64(1)\n",
            "memory usage: 150.5 KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "B1LI2bRiuN6K",
        "outputId": "b5bfe870-857c-4f09-96e7-39df997f72a8"
      },
      "source": [
        "data_G.shape"
      ],
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2752, 6)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 521
        },
        "id": "aUAgB--uuUDF",
        "outputId": "23d0729f-6bce-4cb4-dfe3-0241eb71b16e"
      },
      "source": [
        "#plotting the data\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.title('Close Price History')\n",
        "plt.plot(data_G['Close'], color='blue')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price USD', fontsize = 18)\n",
        "plt.show()"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-lJwUXRQugPg",
        "outputId": "0eeb1473-d4be-4234-bfec-16361e807887"
      },
      "source": [
        "# Create a new data frame with only 'Close column'\n",
        "data_G = data_G.filter(['Close'])\n",
        "dataset_G = data_G.values #convert the data frame to a numpy array\n",
        "training_data_len_G = math.ceil(len(dataset_G)*.7)  # number of rows to train the model on\n",
        "training_data_len_G"
      ],
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1927"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 51
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2oW94wy_u0MF",
        "outputId": "01aaa3ce-b1d5-42fc-966c-65d1f508fd8e"
      },
      "source": [
        "#Scale the data\n",
        "scaler_G = MinMaxScaler(feature_range=(0,1))\n",
        "scaled_data_G = scaler_G.fit_transform(dataset_G)\n",
        "scaled_data_G"
      ],
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.05896808],\n",
              "       [0.05811454],\n",
              "       [0.05325002],\n",
              "       ...,\n",
              "       [0.99924262],\n",
              "       [1.        ],\n",
              "       [0.9947168 ]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L81azBWuvIX9",
        "outputId": "2462402c-a5b7-4f3a-cf31-d256d62e9194"
      },
      "source": [
        "train_data_G = scaled_data_G[0:training_data_len_G, :]\n",
        "#Split the data into x_train, y_train datasets\n",
        "x_train_G = []\n",
        "y_train_G = []\n",
        "for i in range(60,len(train_data_G)):\n",
        "    x_train_G.append(train_data_G[i-60:i, 0])\n",
        "    y_train_G.append(train_data_G[i,0])\n",
        "    if i<=60:\n",
        "        print(x_train_G)\n",
        "        print(y_train_G)\n",
        "        print()"
      ],
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[array([0.05896808, 0.05811454, 0.05325002, 0.04887102, 0.05132029,\n",
            "       0.05103887, 0.04775154, 0.04670316, 0.0475567 , 0.04451056,\n",
            "       0.04686706, 0.04463737, 0.04543213, 0.03523611, 0.03214051,\n",
            "       0.0328889 , 0.03278994, 0.03037467, 0.02902944, 0.02998193,\n",
            "       0.02939435, 0.03239409, 0.0280522 , 0.02944693, 0.0301211 ,\n",
            "       0.03103958, 0.03042416, 0.03102721, 0.03001286, 0.03254253,\n",
            "       0.03158695, 0.0331363 , 0.03237554, 0.03300642, 0.03061589,\n",
            "       0.02950259, 0.02794396, 0.0280584 , 0.02987988, 0.03246832,\n",
            "       0.03378573, 0.0366525 , 0.03962749, 0.03909249, 0.03838429,\n",
            "       0.04341272, 0.04486311, 0.04436832, 0.03930897, 0.03993365,\n",
            "       0.04004498, 0.04030475, 0.03832554, 0.03755241, 0.03492377,\n",
            "       0.03749984, 0.03921619, 0.03915744, 0.03908321, 0.04040061])]\n",
            "[0.04052741994976586]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DsgqfYsUwac7"
      },
      "source": [
        "#convert the x_train_G and y_train_G  to numppy array\n",
        "x_train_G,y_train_G = np.array(x_train_G), np.array(y_train_G)"
      ],
      "execution_count": 54,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EwwWmSWVwify",
        "outputId": "25a27ce4-0070-4d17-d6ed-fe1a2f5b5ba5"
      },
      "source": [
        "#reshape the data\n",
        "x_train_G = np.reshape(x_train_G,(x_train_G.shape[0],x_train_G.shape[1],1))\n",
        "x_train_G.shape"
      ],
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1867, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 55
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aDhpuiUnwqAD"
      },
      "source": [
        "#BuilD the LSTM model\n",
        "model =Sequential()\n",
        "model.add(LSTM(64,return_sequences=True, input_shape=(x_train_G.shape[1],1)))\n",
        "model.add(LSTM(64, return_sequences= False))\n",
        "model.add(Dense(32))\n",
        "model.add(Dense(1))\n"
      ],
      "execution_count": 56,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7oQiHaYtvgzH"
      },
      "source": [
        "\n",
        "#Complie the model\n",
        "model.compile(optimizer='adam', loss='mean_squared_error')"
      ],
      "execution_count": 57,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-XquPBBnwz_v",
        "outputId": "ef622db9-c5fc-47cc-f4eb-73b7e69cae90"
      },
      "source": [
        "#Train the model\n",
        "model.fit(x_train_G,y_train_G, batch_size=1, epochs=10)\n"
      ],
      "execution_count": 58,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/10\n",
            "1867/1867 [==============================] - 47s 24ms/step - loss: 6.8833e-04\n",
            "Epoch 2/10\n",
            "1867/1867 [==============================] - 44s 23ms/step - loss: 1.7279e-04\n",
            "Epoch 3/10\n",
            "1867/1867 [==============================] - 46s 25ms/step - loss: 1.2227e-04\n",
            "Epoch 4/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 1.3040e-04\n",
            "Epoch 5/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 8.3214e-05\n",
            "Epoch 6/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 8.1420e-05\n",
            "Epoch 7/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 6.9770e-05\n",
            "Epoch 8/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 6.6640e-05\n",
            "Epoch 9/10\n",
            "1867/1867 [==============================] - 44s 24ms/step - loss: 6.9495e-05\n",
            "Epoch 10/10\n",
            "1867/1867 [==============================] - 43s 23ms/step - loss: 4.9899e-05\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f3c66ab2090>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 58
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V8DhA_8t2A88"
      },
      "source": [
        "#create the testing data sets\n",
        "test_data_G= scaled_data_G[training_data_len_G-60:, :]\n",
        "\n",
        "#create the data sets x_test_G and y_test_G\n",
        "x_test_G = []\n",
        "y_test_G = dataset_G[training_data_len_G:,:]\n",
        "for i in range(60,len(test_data_G)):\n",
        "    x_test_G.append(test_data_G[i-60:i,0])"
      ],
      "execution_count": 79,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cm5zfl5Xy0ZG",
        "outputId": "829b9736-5d72-4126-f7fc-572969e7ccee"
      },
      "source": [
        "y_test_G.shape"
      ],
      "execution_count": 80,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(825, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 80
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GRVNO3nIy6xv",
        "outputId": "4384c8de-e8b4-4fd4-cd57-a6bba5d1057f"
      },
      "source": [
        "#convert the data to a numpy array\n",
        "x_test_G = np.array(x_test_G)\n",
        "#y_test_G = np.array(y_test_G)\n",
        "\n",
        "#reshape the data\n",
        "x_test_G = np.reshape(x_test_G, (x_test_G.shape[0], x_test_G.shape[1],1))\n",
        "x_test_G.shape"
      ],
      "execution_count": 81,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(825, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 81
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Dr9ZPutJ0EAi"
      },
      "source": [
        "#predicting the data\n",
        "predictions_G = model.predict(x_test_G)\n",
        "predictions_G = scaler_G.inverse_transform(predictions_G)"
      ],
      "execution_count": 82,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yc2Q4Dyy1TEa",
        "outputId": "6a0a9703-33d7-4586-da14-1029842be714"
      },
      "source": [
        "predictions_G.shape"
      ],
      "execution_count": 83,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(825, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 83
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dJl3UsoTyzhc",
        "outputId": "b96c80fc-d771-44aa-9bdb-a6a5c3fb31d6"
      },
      "source": [
        "#get the root mean square error(RMSE)\n",
        "rmse = np.sqrt(np.mean(predictions_G - y_test_G)**2)\n",
        "rmse"
      ],
      "execution_count": 84,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "29.617026592125942"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 84
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-74a-jKe-HLI",
        "outputId": "1d6e8d7d-c7d3-4c60-e66d-e8753da91406"
      },
      "source": [
        "print(training_data_len_G)"
      ],
      "execution_count": 129,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "1927\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 640
        },
        "id": "AunvR5VCy7Ue",
        "outputId": "db32ba75-8401-4fa6-dcfb-463c57b9fd3d"
      },
      "source": [
        "#plot the data\n",
        "train = data_G[:training_data_len_G]\n",
        "valid = data_G[training_data_len_G:]\n",
        "valid['Predictions'] = predictions_G\n",
        "#Visialization the data\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price' ,fontsize=18)\n",
        "plt.plot(train['Close'],linewidth=3.5)\n",
        "plt.plot(valid[['Close','Predictions']],linewidth=3.5)\n",
        "plt.legend(['Train','Valid','Predictions'])"
      ],
      "execution_count": 85,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:4: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  after removing the cwd from sys.path.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7f3c65cebfd0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 85
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "VmI1dvW5y-6c",
        "outputId": "043b3903-8c60-4b09-808a-92bfcc4c7b26"
      },
      "source": [
        "#show the valid and predicted price\n",
        "valid"
      ],
      "execution_count": 86,
      "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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2017-08-29</th>\n",
              "      <td>921.289978</td>\n",
              "      <td>897.207458</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-08-30</th>\n",
              "      <td>929.570007</td>\n",
              "      <td>905.766968</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-08-31</th>\n",
              "      <td>939.330017</td>\n",
              "      <td>914.047302</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-09-01</th>\n",
              "      <td>937.340027</td>\n",
              "      <td>923.658875</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-09-05</th>\n",
              "      <td>928.450012</td>\n",
              "      <td>920.111633</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-01</th>\n",
              "      <td>1798.099976</td>\n",
              "      <td>1680.980957</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-02</th>\n",
              "      <td>1827.949951</td>\n",
              "      <td>1726.870972</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-03</th>\n",
              "      <td>1826.770020</td>\n",
              "      <td>1752.894043</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-04</th>\n",
              "      <td>1827.989990</td>\n",
              "      <td>1744.541992</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-07</th>\n",
              "      <td>1819.479980</td>\n",
              "      <td>1745.313599</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>825 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                  Close  Predictions\n",
              "Date                                \n",
              "2017-08-29   921.289978   897.207458\n",
              "2017-08-30   929.570007   905.766968\n",
              "2017-08-31   939.330017   914.047302\n",
              "2017-09-01   937.340027   923.658875\n",
              "2017-09-05   928.450012   920.111633\n",
              "...                 ...          ...\n",
              "2020-12-01  1798.099976  1680.980957\n",
              "2020-12-02  1827.949951  1726.870972\n",
              "2020-12-03  1826.770020  1752.894043\n",
              "2020-12-04  1827.989990  1744.541992\n",
              "2020-12-07  1819.479980  1745.313599\n",
              "\n",
              "[825 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 86
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5Fr2RRejzBCW",
        "outputId": "a6600ca7-9027-47a6-a9cf-463293845e03"
      },
      "source": [
        "#get the quote\n",
        "goog_quote = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/GOOG.csv')\n",
        "#Create new data frame\n",
        "new_df = goog_quote.filter(['Close'])\n",
        "#get the last 60 days closing price values and convert the dataframe to an array\n",
        "last_60_days = new_df[-60:].values\n",
        "#scaled the data to be values between 0 and 1\n",
        "last_60_days_scaled = scaler.transform(last_60_days)\n",
        "#create an empty list\n",
        "X_test_G = []\n",
        "#append the past 60 days \n",
        "X_test_G.append(last_60_days_scaled)\n",
        "#convert the X_test data set to a numpy array\n",
        "X_test_G = np.array(X_test_G)\n",
        "#Reshape the data\n",
        "X_test_G = np.reshape(X_test_G,(X_test_G.shape[0], X_test_G.shape[1],1))\n",
        "#get the predicted scaled price\n",
        "pred_price_G= model.predict(X_test_G)\n",
        "#undo the scalling\n",
        "pred_price_G = scaler_G.inverse_transform(pred_price_G)\n",
        "pred_price_G\n"
      ],
      "execution_count": 87,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[990.24835]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 87
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qkVxOtNOEaf5"
      },
      "source": [
        "#  Accuracy Score - GOOGLE LSTM Prediction "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "seKPAWQ_EZeo",
        "outputId": "4ecd4f98-c6f0-4aad-939f-5924189d6292"
      },
      "source": [
        "# Measure the Accuracy Score\n",
        "Acc_G = []\n",
        "from sklearn.metrics import r2_score\n",
        " \n",
        "print(\"Accuracy score of the predictions: {0}\".format(r2_score(y_test_G, predictions_G)))\n",
        "Acc_G.append(r2_score(y_test_G, predictions_G))"
      ],
      "execution_count": 88,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the predictions: 0.957041764999876\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cyTWIimHpWIK"
      },
      "source": [
        "# 2. Stock Price Predicting with - The AutoRegressive Integrated Moving Average (ARIMA) model"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vPqCesf006cw"
      },
      "source": [
        "Time-series & forecasting models Time-series forecasting models are the models that are capable to predict future values based on previously observed values. Time-series forecasting is widely used for non-stationary data. Non-stationary data are called the data whose statistical properties e.g. the mean and standard deviation are not constant over time but instead, these metrics vary over time. These non-stationary input data (used as input to these models) are usually called time-series. Some examples of time-series include the temperature values over time, stock price over time, price of a house over time etc. So, the input is a signal (time-series) that is defined by observations taken sequentially in time.A time series is a sequence of observations taken sequentially in time.\n",
        "\n",
        "\n",
        "\n",
        "*   AR: < Auto Regressive > means that the model uses the dependent relationship \n",
        "between an observation and some predefined number of lagged observations (also known as “time lag” or “lag”).\n",
        "\n",
        "\n",
        "*   I:< Integrated > means that the model employs differencing of raw observations (e.g. it subtracts an observation from an observation at the previous time step) in order to make the time-series stationary\n",
        "\n",
        "\n",
        "*   MA: < Moving Average > means that the model exploits the relationship between the residual error and the observations.\n",
        "Model parameters\n",
        "\n",
        "The standard ARIMA models expect as input parameters 3 arguments i.e. p,d,q. p is the number of lag observations. d is the degree of differencing. q is the size/width of the moving average window."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pVj9sDXg8cmk"
      },
      "source": [
        "# 2.1 Amazon Stock Price Prediction "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Pckn-gIHpevF",
        "outputId": "de71d4f8-29be-43ae-a2bb-cef2b4a4b0b1"
      },
      "source": [
        "from pandas.plotting import lag_plot\n",
        "from pandas import datetime\n",
        "from statsmodels.tsa.arima_model import ARIMA\n",
        "from sklearn.metrics import mean_squared_error"
      ],
      "execution_count": 89,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: FutureWarning: The pandas.datetime class is deprecated and will be removed from pandas in a future version. Import from datetime module instead.\n",
            "  \n",
            "/usr/local/lib/python3.7/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
            "  import pandas.util.testing as tm\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1nwONzFBwUB_"
      },
      "source": [
        "Adata = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/AMZN.csv')\n",
        "Adata['Date'] = pd.to_datetime(Adata['Date'])\n",
        "Adata.set_index('Date',inplace=True)"
      ],
      "execution_count": 90,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8eK_v2tiwiRE",
        "outputId": "62a954de-f1da-4165-8f2b-7f5601d38cda"
      },
      "source": [
        "Adata.info()"
      ],
      "execution_count": 91,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "DatetimeIndex: 2518 entries, 2010-12-06 to 2020-12-04\n",
            "Data columns (total 6 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Open       2518 non-null   float64\n",
            " 1   High       2518 non-null   float64\n",
            " 2   Low        2518 non-null   float64\n",
            " 3   Close      2518 non-null   float64\n",
            " 4   Adj Close  2518 non-null   float64\n",
            " 5   Volume     2518 non-null   int64  \n",
            "dtypes: float64(5), int64(1)\n",
            "memory usage: 137.7 KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "ahIf7_ycp8dP",
        "outputId": "ce3c29f0-37f9-4f91-a1aa-5387475cf574"
      },
      "source": [
        "#Our target variable will be the Close value.\n",
        "#Before building the ARIMA model, let’s see if there is some cross-correlation in our data.\n",
        "plt.figure(figsize=(16,8))\n",
        "lag_plot(Adata['Open'], lag=3)\n",
        "plt.title('AMAZON Stock - Autocorrelation plot with lag = 3')\n",
        "plt.show()\n"
      ],
      "execution_count": 92,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "feB8Wrx31OMA"
      },
      "source": [
        "We can now confirm that ARIMA is going to be a good model to be applied to this type of data (there is auto-correlation in the data).\n",
        "\n",
        "Finally, let’s plot the stock price evolution over time."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "stk4hvp7qDfI",
        "outputId": "8b359e4b-3a7b-45f8-e206-9b24458b7683"
      },
      "source": [
        "plt.figure(figsize=(16,8))\n",
        "plt.plot(Adata.index, Adata['Close'], color='royalblue')\n",
        "plt.title('Daily close price')\n",
        "plt.xlabel('Day')\n",
        "plt.ylabel('Dollar')\n",
        "plt.show()"
      ],
      "execution_count": 93,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Uz_2ZWWE1XYD"
      },
      "source": [
        "Build the predictive ARIMA model\n",
        "\n",
        "Next, let’s divide the data into a training (70 % ) and test (30%) set. For this tutorial we select the following ARIMA parameters: p=4, d=1 and q=0."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Byi9HRhbqLih",
        "outputId": "774a55fb-f2c0-4a29-cee6-26467128935c"
      },
      "source": [
        "train_data, test_data = Adata[0:int(len(Adata)*0.7)], Adata[int(len(Adata)*0.7):]\n",
        "training_data = train_data['Close'].values\n",
        "test_data = test_data['Close'].values\n",
        "history = [x for x in training_data]\n",
        "model_predictions = []\n",
        "N_test_observations = len(test_data)\n",
        "for time_point in range(N_test_observations):\n",
        "    model = ARIMA(history, order=(4,1,0))\n",
        "    model_fit = model.fit(disp=0)\n",
        "    output = model_fit.forecast()\n",
        "    yhat = output[0]\n",
        "    model_predictions.append(yhat)\n",
        "    true_test_value = test_data[time_point]\n",
        "    history.append(true_test_value)\n",
        "MSE_error = mean_squared_error(test_data, model_predictions)\n",
        "print('Testing Mean Squared Error is {}'.format(MSE_error))"
      ],
      "execution_count": 94,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Testing Mean Squared Error is 1977.6938758025142\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uNMHRwZy1fpA"
      },
      "source": [
        "Summary of the code We split the training dataset into train and test sets and we use the train set to fit the model, and generate a prediction for each element on the test set. A rolling forecasting procedure is required given the dependence on observations in prior time steps for differencing and the AR model. To this end, we re-create the ARIMA model after each new observation is received. Finally, we manually keep track of all observations in a list called history that is seeded with the training data and to which new observations are appended at each iteration. Testing Mean Squared Error is **1977.6938758025142**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1hEXEtJU1n6B"
      },
      "source": [
        "The MSE of the test set is quite large denoting that the precise prediction is a hard problem. However, this is the average squared value across all the test set predictions. Let’s visualize the predictions to understand the performance of the model more."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "sql8yGKKqdkL",
        "outputId": "3d0eaa50-eb4b-4f69-d24b-7036d7d59bad"
      },
      "source": [
        "test_set_range = Adata[int(len(Adata)*0.7):].index\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.plot(test_set_range, model_predictions, color='blue', marker='o', linestyle='dashed',label='Predicted Price')\n",
        "plt.plot(test_set_range, test_data, color='red', label='Actual Price')\n",
        "plt.title('Amazon Prices Prediction')\n",
        "plt.xlabel('Date')\n",
        "plt.ylabel('Price')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "execution_count": 95,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RUTj19MK-R79",
        "outputId": "792bc5a5-e3ac-4a04-9ee7-1422f16e045c"
      },
      "source": [
        "#Get records from dataframe to plot VALID tabular comparison of Close Prediction\n",
        "Adata = Adata.filter(['Close'])\n",
        "Adataset = Adata.values #convert the data frame to a numpy array\n",
        "Atraining_data_len = math.ceil(len(Adataset)*.7)  # number of rows to train the model on\n",
        "Atraining_data_len"
      ],
      "execution_count": 143,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1763"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 143
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 552
        },
        "id": "N-xoUYqk-mZ_",
        "outputId": "9e0d507d-91ea-4e33-dc55-72774d7a939b"
      },
      "source": [
        "#Plot the Close & Prediction values\n",
        "train = Adata[:Atraining_data_len]\n",
        "valid = Adata[Atraining_data_len - 1:]\n",
        "model_predictions = np.array(model_predictions)\n",
        "valid['Predictions'] = model_predictions\n",
        "#Visialization the datamodel_predictions.shape\n",
        "valid"
      ],
      "execution_count": 145,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  \"\"\"\n"
          ],
          "name": "stderr"
        },
        {
          "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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2017-12-05</th>\n",
              "      <td>1141.569946</td>\n",
              "      <td>1134.937334</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-06</th>\n",
              "      <td>1152.349976</td>\n",
              "      <td>1142.708562</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-07</th>\n",
              "      <td>1159.790039</td>\n",
              "      <td>1154.893957</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-08</th>\n",
              "      <td>1162.000000</td>\n",
              "      <td>1161.372195</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-12-11</th>\n",
              "      <td>1168.920044</td>\n",
              "      <td>1161.691395</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-11-30</th>\n",
              "      <td>3168.040039</td>\n",
              "      <td>3195.327823</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-01</th>\n",
              "      <td>3220.080078</td>\n",
              "      <td>3164.858146</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-02</th>\n",
              "      <td>3203.530029</td>\n",
              "      <td>3217.185273</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-03</th>\n",
              "      <td>3186.729980</td>\n",
              "      <td>3209.321957</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-04</th>\n",
              "      <td>3162.580078</td>\n",
              "      <td>3183.933098</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>756 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                  Close  Predictions\n",
              "Date                                \n",
              "2017-12-05  1141.569946  1134.937334\n",
              "2017-12-06  1152.349976  1142.708562\n",
              "2017-12-07  1159.790039  1154.893957\n",
              "2017-12-08  1162.000000  1161.372195\n",
              "2017-12-11  1168.920044  1161.691395\n",
              "...                 ...          ...\n",
              "2020-11-30  3168.040039  3195.327823\n",
              "2020-12-01  3220.080078  3164.858146\n",
              "2020-12-02  3203.530029  3217.185273\n",
              "2020-12-03  3186.729980  3209.321957\n",
              "2020-12-04  3162.580078  3183.933098\n",
              "\n",
              "[756 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 145
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DtjsP5NjEJn0"
      },
      "source": [
        "# Accuracy score  - Amazon ARIMA prediction"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cQzqH5Lap_KP",
        "outputId": "3db3ee41-01cc-48d0-e03c-9baca35606ad"
      },
      "source": [
        "\n",
        "from sklearn.metrics import r2_score\n",
        " \n",
        "print(\"Accuracy score of the predictions: {0}\".format(r2_score(test_data, model_predictions)))\n",
        "Acc.append(r2_score(test_data, model_predictions))"
      ],
      "execution_count": 99,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the predictions: 0.9936222183900572\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6rFmH2C69bwo"
      },
      "source": [
        "# 2.2 Google Stock Price Prediction Using ARIMA"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w6d6iM_Y9acT"
      },
      "source": [
        "Adata_G = pd.read_csv('/content/gdrive/MyDrive/Stock-Price-Prediction-main/Time Series - Stock Price Prediction/GOOG.csv')\n",
        "Adata_G['Date'] = pd.to_datetime(Adata_G['Date'])\n",
        "Adata_G.set_index('Date',inplace=True)\n"
      ],
      "execution_count": 100,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QG2vcqtN-t3t",
        "outputId": "e3625a49-effb-4a20-e2df-fa8aca624824"
      },
      "source": [
        "Adata_G.info()"
      ],
      "execution_count": 101,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "DatetimeIndex: 2752 entries, 2010-01-04 to 2020-12-07\n",
            "Data columns (total 6 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Open       2752 non-null   float64\n",
            " 1   High       2752 non-null   float64\n",
            " 2   Low        2752 non-null   float64\n",
            " 3   Close      2752 non-null   float64\n",
            " 4   Adj Close  2752 non-null   float64\n",
            " 5   Volume     2752 non-null   int64  \n",
            "dtypes: float64(5), int64(1)\n",
            "memory usage: 150.5 KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "I5qSkyJ4-wWR",
        "outputId": "90562a92-e7d7-4f5f-f9ee-4f8d1ebaace5"
      },
      "source": [
        "#Our target variable will be the Close value.\n",
        "#Before building the ARIMA model, let’s see if there is some cross-correlation in our data.\n",
        "plt.figure(figsize=(16,8))\n",
        "lag_plot(Adata_G['Open'], lag=3)\n",
        "plt.title('Google Stock - Autocorrelation plot with lag = 3')\n",
        "plt.show()\n"
      ],
      "execution_count": 102,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "pvvqsF6M-24Z",
        "outputId": "4fffc307-bc6b-4546-a4b5-cdae45a91296"
      },
      "source": [
        "plt.figure(figsize=(16,8))\n",
        "plt.plot(Adata_G.index, Adata_G['Close'], color='royalblue')\n",
        "plt.title('Daily close price')\n",
        "plt.xlabel('Day')\n",
        "plt.ylabel('Dollar')\n",
        "plt.show()"
      ],
      "execution_count": 103,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6YiKb4M1-7G8",
        "outputId": "e8ecddc3-c343-41cc-97a1-f393a04c9d1b"
      },
      "source": [
        "train_data_G, test_data_G = Adata_G[0:int(len(Adata_G)*0.7)], Adata_G[int(len(Adata_G)*0.7):]\n",
        "training_data_G = train_data_G['Close'].values\n",
        "test_data_G = test_data_G['Close'].values\n",
        "history_G = [x for x in training_data_G]\n",
        "model_predictions_G = []\n",
        "N_test_observations_G = len(test_data_G)\n",
        "for time_point in range(N_test_observations_G):\n",
        "    model = ARIMA(history_G, order=(4,1,0))\n",
        "    model_fit_G = model.fit(disp=0)\n",
        "    output = model_fit_G.forecast()\n",
        "    yhat = output[0]\n",
        "    model_predictions_G.append(yhat)\n",
        "    true_test_value_G= test_data_G[time_point]\n",
        "    history_G.append(true_test_value_G)\n",
        "MSE_error= mean_squared_error(test_data_G, model_predictions_G)\n",
        "print('Testing Mean Squared Error is {}'.format(MSE_error))\n"
      ],
      "execution_count": 104,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/statsmodels/base/model.py:512: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
            "  \"Check mle_retvals\", ConvergenceWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/statsmodels/base/model.py:512: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
            "  \"Check mle_retvals\", ConvergenceWarning)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "Testing Mean Squared Error is 537.6466806589963\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "aDfHbDrf_Ugj",
        "outputId": "9bd8141b-1ca0-4f1d-8240-201aecf7e27a"
      },
      "source": [
        "test_set_range_G = Adata_G[int(len(Adata_G)*0.7):].index\n",
        "plt.figure(figsize=(16,8))\n",
        "plt.plot(test_set_range_G, model_predictions_G, color='blue', marker='o', linestyle='dashed',label='Predicted Price')\n",
        "plt.plot(test_set_range_G, test_data_G, color='red', label='Actual Price')\n",
        "plt.title('Google Prices Prediction')\n",
        "plt.xlabel('Date')\n",
        "plt.ylabel('Price')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "execution_count": 105,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X8UUmZkk19aJ",
        "outputId": "b5ea23e4-d148-4cee-a5b6-bc8c84dac85c"
      },
      "source": [
        "#Get records from dataframe to plot VALID tabular comparison of Close Prediction\n",
        "Adata_G = Adata_G.filter(['Close'])\n",
        "Adataset_G = Adata_G.values #convert the data frame to a numpy array\n",
        "Atraining_data_len_G = math.ceil(len(Adataset_G)*.7)  # number of rows to train the model on\n",
        "Atraining_data_len_G"
      ],
      "execution_count": 146,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1927"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 146
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 552
        },
        "id": "bgEbr2JUB7YS",
        "outputId": "8bc8c114-013c-40ee-bfbf-5b640723e88d"
      },
      "source": [
        "#Plot the Close & Prediction values\n",
        "train = Adata_G[:Atraining_data_len_G]\n",
        "valid = Adata_G[Atraining_data_len_G - 1:]\n",
        "model_predictions_G = np.array(model_predictions_G)\n",
        "valid['Predictions'] = model_predictions_G\n",
        "#Visialization the datamodel_predictions.shape\n",
        "valid"
      ],
      "execution_count": 148,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:5: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  \"\"\"\n"
          ],
          "name": "stderr"
        },
        {
          "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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2017-08-28</th>\n",
              "      <td>913.809998</td>\n",
              "      <td>915.612122</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-08-29</th>\n",
              "      <td>921.289978</td>\n",
              "      <td>914.205372</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-08-30</th>\n",
              "      <td>929.570007</td>\n",
              "      <td>922.101908</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-08-31</th>\n",
              "      <td>939.330017</td>\n",
              "      <td>930.372567</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017-09-01</th>\n",
              "      <td>937.340027</td>\n",
              "      <td>939.748759</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-01</th>\n",
              "      <td>1798.099976</td>\n",
              "      <td>1764.306477</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-02</th>\n",
              "      <td>1827.949951</td>\n",
              "      <td>1794.222022</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-03</th>\n",
              "      <td>1826.770020</td>\n",
              "      <td>1824.787629</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-04</th>\n",
              "      <td>1827.989990</td>\n",
              "      <td>1829.052615</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-07</th>\n",
              "      <td>1819.479980</td>\n",
              "      <td>1827.883653</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>826 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                  Close  Predictions\n",
              "Date                                \n",
              "2017-08-28   913.809998   915.612122\n",
              "2017-08-29   921.289978   914.205372\n",
              "2017-08-30   929.570007   922.101908\n",
              "2017-08-31   939.330017   930.372567\n",
              "2017-09-01   937.340027   939.748759\n",
              "...                 ...          ...\n",
              "2020-12-01  1798.099976  1764.306477\n",
              "2020-12-02  1827.949951  1794.222022\n",
              "2020-12-03  1826.770020  1824.787629\n",
              "2020-12-04  1827.989990  1829.052615\n",
              "2020-12-07  1819.479980  1827.883653\n",
              "\n",
              "[826 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 148
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "w7zjZUH8FfMh"
      },
      "source": [
        "# Accuracy score - Google ARIMA Prediction "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pkogJAHo_ZFU",
        "outputId": "12ea309f-266c-4843-d2fa-599aac85c24c"
      },
      "source": [
        "# FInd the Accuracy score of the Googl ARIMA predictions\n",
        "from sklearn.metrics import r2_score\n",
        " \n",
        "print(\"Accuracy score of the predictions: {0}\".format(r2_score(test_data_G, model_predictions_G)))\n",
        "Acc_G.append(r2_score(test_data_G, model_predictions_G))"
      ],
      "execution_count": 106,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy score of the predictions: 0.9855455121667532\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UivXhPyR_ia3"
      },
      "source": [
        "# Amazon Stock - Accuracies in LSTM & ARIMA  Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 404
        },
        "id": "m0P-_upJqoU6",
        "outputId": "e347f21b-7002-476d-a05e-7800bc968183"
      },
      "source": [
        "plt.figure(figsize=(12,6))\n",
        "plt.plot(range(2), Acc, color='green', linestyle='dashed', linewidth = 3, \n",
        "          marker='o', markerfacecolor='blue', markersize=12) \n",
        "plt.ylabel('Acc')\n",
        "plt.xlabel('Models')\n",
        "plt.title(\"AMAZON - Accuracies\")\n",
        "plt.xticks(range(2), ['LSTM','ARIMA'])\n",
        "plt.show()"
      ],
      "execution_count": 108,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hjUbOQfiAjwm"
      },
      "source": [
        "# Google Stock - Accuracies in LSTM & ARIMA Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 404
        },
        "id": "g-Mp9ZkDAiZx",
        "outputId": "8c35fe5b-5ede-41d1-8098-21ce5e07bbb7"
      },
      "source": [
        "plt.figure(figsize=(12,6))\n",
        "plt.plot(range(2), Acc_G, color='green', linestyle='dashed', linewidth = 3, \n",
        "         marker='o', markerfacecolor='blue', markersize=12) \n",
        "plt.ylabel('Acc')\n",
        "plt.xlabel('Models')\n",
        "plt.title(\"GOOGLE - Accuracies\")\n",
        "plt.xticks(range(2), ['LSTM', 'ARIMA'])\n",
        "plt.show()"
      ],
      "execution_count": 109,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ojUZUG4drCmt"
      },
      "source": [
        "**Conclusion**\n",
        "\n",
        "\n",
        "\n",
        "*  ARIMA model results are appreciable . \n",
        "*  As shown for both AMAZON & GOOGLE, ARIMA model offers better prediction accuracy with respect to LSTM and is relatively fast as well to LSTM, in terms of training/fitting time and complexity.\n",
        "*  ARIMA model predicts GOOGLE to be better Stock than AMAZON\n",
        "\n"
      ]
    }
  ]
}