EURUSD_price_prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "EURUSD price prediction.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyMBNzPd5sNKf+nAQfiMGSXh",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/abidshafee/google.colaboratory_projects/blob/master/EURUSD_price_prediction.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BleyqTWs2qa8",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Description: This is a program that predict future currency price using artificial recurrent nural network - \n",
        "# The artificial recurrent nural network architecture also called 'Long Short Term Memory' or LSTM\n",
        "# Predicting the closing price of EURUSD currency pair using the past 60 days price."
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dO8AcPAq4Dcx",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 88
        },
        "outputId": "60fac04d-eb98-4093-afd2-a219741ed0d7"
      },
      "source": [
        "import math\n",
        "import pandas_datareader as web\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, LSTM\n",
        "import matplotlib.pyplot as plt\n",
        "plt.style.use('fivethirtyeight')"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/pandas_datareader/compat/__init__.py:7: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
            "  from pandas.util.testing import assert_frame_equal\n",
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "akdBZWdIMu0W",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "outputId": "e31920e4-93d1-4008-c3db-21cfea81ddbb"
      },
      "source": [
        "# geting the eurousd quotes\n",
        "df = web.DataReader('EURUSD=X', data_source='yahoo', start='2012-01-1', end='2020-7-14')\n",
        "# view data\n",
        "df"
      ],
      "execution_count": 3,
      "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>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Open</th>\n",
              "      <th>Close</th>\n",
              "      <th>Volume</th>\n",
              "      <th>Adj Close</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2012-01-02</th>\n",
              "      <td>1.296395</td>\n",
              "      <td>1.292257</td>\n",
              "      <td>1.296008</td>\n",
              "      <td>1.296008</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.296008</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-03</th>\n",
              "      <td>1.306592</td>\n",
              "      <td>1.293628</td>\n",
              "      <td>1.293628</td>\n",
              "      <td>1.294096</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.294096</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-04</th>\n",
              "      <td>1.307395</td>\n",
              "      <td>1.290206</td>\n",
              "      <td>1.305398</td>\n",
              "      <td>1.305602</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.305602</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-05</th>\n",
              "      <td>1.294297</td>\n",
              "      <td>1.278527</td>\n",
              "      <td>1.293092</td>\n",
              "      <td>1.293142</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.293142</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-06</th>\n",
              "      <td>1.281296</td>\n",
              "      <td>1.270406</td>\n",
              "      <td>1.279296</td>\n",
              "      <td>1.279607</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.279607</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-07</th>\n",
              "      <td>1.134559</td>\n",
              "      <td>1.126519</td>\n",
              "      <td>1.127281</td>\n",
              "      <td>1.127523</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.127523</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-08</th>\n",
              "      <td>1.137268</td>\n",
              "      <td>1.128796</td>\n",
              "      <td>1.133787</td>\n",
              "      <td>1.133915</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.133915</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-09</th>\n",
              "      <td>1.132477</td>\n",
              "      <td>1.125720</td>\n",
              "      <td>1.128923</td>\n",
              "      <td>1.128796</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.128796</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-12</th>\n",
              "      <td>1.137048</td>\n",
              "      <td>1.130454</td>\n",
              "      <td>1.130876</td>\n",
              "      <td>1.131004</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.131004</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-14</th>\n",
              "      <td>1.136235</td>\n",
              "      <td>1.133016</td>\n",
              "      <td>1.134816</td>\n",
              "      <td>1.135718</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.135718</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2222 rows × 6 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                High       Low      Open     Close  Volume  Adj Close\n",
              "Date                                                                 \n",
              "2012-01-02  1.296395  1.292257  1.296008  1.296008     0.0   1.296008\n",
              "2012-01-03  1.306592  1.293628  1.293628  1.294096     0.0   1.294096\n",
              "2012-01-04  1.307395  1.290206  1.305398  1.305602     0.0   1.305602\n",
              "2012-01-05  1.294297  1.278527  1.293092  1.293142     0.0   1.293142\n",
              "2012-01-06  1.281296  1.270406  1.279296  1.279607     0.0   1.279607\n",
              "...              ...       ...       ...       ...     ...        ...\n",
              "2020-07-07  1.134559  1.126519  1.127281  1.127523     0.0   1.127523\n",
              "2020-07-08  1.137268  1.128796  1.133787  1.133915     0.0   1.133915\n",
              "2020-07-09  1.132477  1.125720  1.128923  1.128796     0.0   1.128796\n",
              "2020-07-12  1.137048  1.130454  1.130876  1.131004     0.0   1.131004\n",
              "2020-07-14  1.136235  1.133016  1.134816  1.135718     0.0   1.135718\n",
              "\n",
              "[2222 rows x 6 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4j3r_xP0QDIK",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "23c81573-26d4-4c59-9f34-57477101e29a"
      },
      "source": [
        "# number of rows and column in the dataset\n",
        "df.shape"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2222, 6)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WzX--v_1R-Vp",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 558
        },
        "outputId": "abe76998-be16-405b-d499-9d259b0fb62f"
      },
      "source": [
        "# our dataframe has 260 rows and 6 column except index column\n",
        "# Visualizing data specially the closing price, because we are gonna built iur model on closed price\n",
        "plt.figure(figsize = (16,8))\n",
        "plt.title('Closed Price History')\n",
        "plt.plot(df['Close'])\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Closed Price EURUSD', fontsize=18)\n",
        "plt.show()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CecplVWgUik9",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "02d675b0-246e-40b4-89b2-c1740b5e8911"
      },
      "source": [
        "# creating a new dataframe only with close price column\n",
        "newdf = df.filter(['Close'])\n",
        "# now, converting the new dataframe to numpy array\n",
        "dataset = newdf.values\n",
        "# dataset.shape\n",
        "# taking the number of rows to train the model\n",
        "training_data_len = math.ceil( len(dataset) *0.8)\n",
        "# using math.ceil to roundup number\n",
        "training_data_len"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1778"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MwCMRiqgYydl",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Scaling the data before presenting it to the neural network\n",
        "# because scaling or normalization of input data is always a good practice\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "# transform the data to value between 0 and 1\n",
        "# Scaled_data will hold the data that is been scaled\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "# scaled_data"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "md_lEq8WpdoD",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 680
        },
        "outputId": "ef0d32b5-902f-4f49-d754-d1f1b76ddb01"
      },
      "source": [
        "# Creating the training dataset\n",
        "# first we create scaled training dataset\n",
        "train_data = scaled_data[0:training_data_len, :]\n",
        "# this will capture index 0 to training_data_len and return all column\n",
        "# now we will split the data into x_train, y_train dataset\n",
        "x_train = [] # independent data\n",
        "y_train = [] # dependent data, deends on x_train\n",
        "\n",
        "for data in range(60, len(train_data)):\n",
        "  x_train.append(train_data[data-60:data, 0])\n",
        "  y_train.append(train_data[data,0])\n",
        "  if data<=61:\n",
        "    print(x_train)\n",
        "    print(y_train)\n",
        "    print()"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[array([0.72579585, 0.72039568, 0.75289471, 0.71770131, 0.67946944,\n",
            "       0.64679229, 0.67378979, 0.66697947, 0.65909673, 0.68637404,\n",
            "       0.63737043, 0.64302685, 0.66532689, 0.69923304, 0.72717266,\n",
            "       0.70452412, 0.74467996, 0.74866258, 0.76739585, 0.76327551,\n",
            "       0.79580586, 0.77649244, 0.75882655, 0.78509507, 0.77580993,\n",
            "       0.77298458, 0.77142797, 0.80727256, 0.80727256, 0.81571997,\n",
            "       0.80395393, 0.7816687 , 0.77483515, 0.7534725 , 0.77288727,\n",
            "       0.80123398, 0.79491896, 0.80578564, 0.80930629, 0.84260501,\n",
            "       0.86900688, 0.85192316, 0.87208307, 0.82771026, 0.82821162,\n",
            "       0.78965684, 0.80083868, 0.77191418, 0.77659009, 0.81472398,\n",
            "       0.77240072, 0.78460516, 0.75979257, 0.74343413, 0.75930973,\n",
            "       0.7871049 , 0.80182693, 0.80420108, 0.7988632 , 0.79491896])]\n",
            "[0.8170152974641605]\n",
            "\n",
            "[array([0.72579585, 0.72039568, 0.75289471, 0.71770131, 0.67946944,\n",
            "       0.64679229, 0.67378979, 0.66697947, 0.65909673, 0.68637404,\n",
            "       0.63737043, 0.64302685, 0.66532689, 0.69923304, 0.72717266,\n",
            "       0.70452412, 0.74467996, 0.74866258, 0.76739585, 0.76327551,\n",
            "       0.79580586, 0.77649244, 0.75882655, 0.78509507, 0.77580993,\n",
            "       0.77298458, 0.77142797, 0.80727256, 0.80727256, 0.81571997,\n",
            "       0.80395393, 0.7816687 , 0.77483515, 0.7534725 , 0.77288727,\n",
            "       0.80123398, 0.79491896, 0.80578564, 0.80930629, 0.84260501,\n",
            "       0.86900688, 0.85192316, 0.87208307, 0.82771026, 0.82821162,\n",
            "       0.78965684, 0.80083868, 0.77191418, 0.77659009, 0.81472398,\n",
            "       0.77240072, 0.78460516, 0.75979257, 0.74343413, 0.75930973,\n",
            "       0.7871049 , 0.80182693, 0.80420108, 0.7988632 , 0.79491896]), array([0.72039568, 0.75289471, 0.71770131, 0.67946944, 0.64679229,\n",
            "       0.67378979, 0.66697947, 0.65909673, 0.68637404, 0.63737043,\n",
            "       0.64302685, 0.66532689, 0.69923304, 0.72717266, 0.70452412,\n",
            "       0.74467996, 0.74866258, 0.76739585, 0.76327551, 0.79580586,\n",
            "       0.77649244, 0.75882655, 0.78509507, 0.77580993, 0.77298458,\n",
            "       0.77142797, 0.80727256, 0.80727256, 0.81571997, 0.80395393,\n",
            "       0.7816687 , 0.77483515, 0.7534725 , 0.77288727, 0.80123398,\n",
            "       0.79491896, 0.80578564, 0.80930629, 0.84260501, 0.86900688,\n",
            "       0.85192316, 0.87208307, 0.82771026, 0.82821162, 0.78965684,\n",
            "       0.80083868, 0.77191418, 0.77659009, 0.81472398, 0.77240072,\n",
            "       0.78460516, 0.75979257, 0.74343413, 0.75930973, 0.7871049 ,\n",
            "       0.80182693, 0.80420108, 0.7988632 , 0.79491896, 0.8170153 ])]\n",
            "[0.8170152974641605, 0.8387691992737811]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "h9Fip5L-0Of0",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# above the first dataset is our x_training dataset which contains past 60 values,\n",
        "# and below the single row is our y_training dataset that we will predict depending on 60 values of x_train dataset"
      ],
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OztnZxV45VH1",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# now converting the x_train and y_train dataset to numpy array so that we can use them to train the LSTM model\n",
        "x_train, y_train = np.array(x_train), np.array(y_train)"
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z4oHgSnt6TJD",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d96a6f66-be2c-4e9d-f622-7a4b1ec1a9f2"
      },
      "source": [
        "# right now our data is two-dimentional, so we need to reshape the data,\n",
        "# the reason of reshaping is that the LSTM network expect data to be three dimentional in the form of -\n",
        "# number of samples, number of time steps, and number of features\n",
        "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
        "x_train.shape"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1718, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WqDo73pDQwof",
        "colab_type": "text"
      },
      "source": [
        "# Our LSTM model that will predict future data "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "O1GL6iqoIW0U",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Building LSTM Model\n",
        "model = Sequential()\n",
        "model.add(LSTM(50, return_sequences=True, input_shape = (x_train.shape[1], 1)))\n",
        "model.add(LSTM(50, return_sequences=False))\n",
        "model.add(Dense(25))\n",
        "model.add(Dense(1))"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "An1eALpnKmLD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# now we will compile our model\n",
        "model.compile(optimizer='adam', loss = 'mean_squared_error')\n",
        "# the optimizer will improve the model upon loss function, and\n",
        "# the loss function will measure how well the model did on training"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "obPuRbIzMirf",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        },
        "outputId": "428bd5eb-831b-4e4b-d519-2c39926af3b8"
      },
      "source": [
        "# train the model\n",
        "model.fit(x_train, y_train, batch_size=1, epochs=1)"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/1\n",
            "1718/1718 [==============================] - 64s 37ms/step - loss: 0.0035\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.callbacks.History at 0x7fd2ba20dac8>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "trRj8o8rN_gw",
        "colab_type": "text"
      },
      "source": [
        "Now We will create a testing dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "z2bs_V9JOIBW",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "test_data = scaled_data[training_data_len-60: , :]\n",
        "# creating dataset\n",
        "x_test = []\n",
        "y_test = dataset[training_data_len:, :]\n",
        "\n",
        "for tdata in range(60, len(test_data)):\n",
        "  x_test.append(test_data[tdata-60:tdata, 0])"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pXjTE16jlfFW",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Converting the test data to numpy array to use it in LSTM model\n",
        "x_test = np.array(x_test)"
      ],
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hy2qgPNtmdpg",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Reshaping the test data\n",
        "# because our data is two-dimentional but LSTM model expect data to be three-dimentional shape\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))"
      ],
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V-wnIMjqm8mP",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# model predicted price\n",
        "predictions = model.predict(x_test)\n",
        "# inverse transform the data or we unscaling valuees\n",
        "predictions = scaler.inverse_transform(predictions)\n",
        "# here we want the predictions contain the saame dataset that our y_test dataset contains\n"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "35YZNMOervpQ",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "49820f6d-dbee-4d13-8c23-165cc5b06849"
      },
      "source": [
        "# evaluating our model using root-mean-square error (rmse) that how accurate the model predict \n",
        "# the lower value of rmse indicates a better fit\n",
        "rmse = np.sqrt( np.mean(predictions - y_test)**2)\n",
        "rmse"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.0031276841958363852"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-FuCx-FBtXIl",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 660
        },
        "outputId": "d967dfbf-906d-4e25-8944-c76f70b694f1"
      },
      "source": [
        "# ploting the data\n",
        "train = newdf[:training_data_len]\n",
        "# validation dataset\n",
        "valid = newdf[training_data_len:]\n",
        "valid['predictions'] = predictions\n",
        "# visualizing the data\n",
        "plt.figure(figsize=(16, 8))\n",
        "plt.title('Model Visualization')\n",
        "plt.xlabel('Data', fontsize=18)\n",
        "plt.ylabel('Closed Price EURUSD', fontsize=18)\n",
        "plt.plot(train['Close'])\n",
        "plt.plot(valid[['Close', 'predictions']])\n",
        "plt.legend(['train', 'validation', 'prediction'], loc='lower right')\n",
        "plt.show()"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/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": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fqa3l6OZF9Tl",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "outputId": "5c17c14a-a003-496a-fbd4-38e20fa7fb42"
      },
      "source": [
        "# valid and predicted price\n",
        "valid"
      ],
      "execution_count": 21,
      "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>2018-10-31</th>\n",
              "      <td>1.134636</td>\n",
              "      <td>1.137671</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-11-01</th>\n",
              "      <td>1.131670</td>\n",
              "      <td>1.135830</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-11-02</th>\n",
              "      <td>1.140329</td>\n",
              "      <td>1.133860</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-11-05</th>\n",
              "      <td>1.139757</td>\n",
              "      <td>1.132986</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-11-06</th>\n",
              "      <td>1.141292</td>\n",
              "      <td>1.132759</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-07</th>\n",
              "      <td>1.127523</td>\n",
              "      <td>1.121172</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-08</th>\n",
              "      <td>1.133915</td>\n",
              "      <td>1.121910</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-09</th>\n",
              "      <td>1.128796</td>\n",
              "      <td>1.123209</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-12</th>\n",
              "      <td>1.131004</td>\n",
              "      <td>1.124114</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-07-14</th>\n",
              "      <td>1.135718</td>\n",
              "      <td>1.124933</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>444 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "               Close  predictions\n",
              "Date                             \n",
              "2018-10-31  1.134636     1.137671\n",
              "2018-11-01  1.131670     1.135830\n",
              "2018-11-02  1.140329     1.133860\n",
              "2018-11-05  1.139757     1.132986\n",
              "2018-11-06  1.141292     1.132759\n",
              "...              ...          ...\n",
              "2020-07-07  1.127523     1.121172\n",
              "2020-07-08  1.133915     1.121910\n",
              "2020-07-09  1.128796     1.123209\n",
              "2020-07-12  1.131004     1.124114\n",
              "2020-07-14  1.135718     1.124933\n",
              "\n",
              "[444 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "noPs6s97IxAb",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d34e47d8-77d6-4b2f-d662-7beb6b4cdd3c"
      },
      "source": [
        "# Now we will predict future data using our model\n",
        "predict_df = web.DataReader('EURUSD=X', data_source='yahoo', start='2012-01-1', end='2020-7-14')\n",
        "# now we will create a new data set where we want only the Close column\n",
        "\n",
        "predict_data = predict_df.filter(['Close'])\n",
        "# predict_data\n",
        "# we will get now the last 60 days closing price and we will also conver the dataframe into an array\n",
        "sixty_days_data = predict_data[-60:].values\n",
        "# sixty_days_data\n",
        "# now scaling this data value between 0 and 1\n",
        "sixty_days_scaled_data = scaler.transform(sixty_days_data)\n",
        "# creating an empty list\n",
        "x_test =[]\n",
        "x_test.append(sixty_days_scaled_data)\n",
        "# Coverting the x_test dataset o numpy array\n",
        "x_test = np.array(x_test)\n",
        "# reshaping the data to be 3-dimentional\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))\n",
        "# getting the predicted scaled price\n",
        "predicted_price = model.predict(x_test)\n",
        "# now undoing scalling\n",
        "predicted_price = scaler.inverse_transform(predicted_price)\n",
        "# he printed data our model believe will be the price july-14-202\n",
        "print(predicted_price)"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1.1261289]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5pkYG6taLQ96",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 85
        },
        "outputId": "e4da74f6-0e38-4e18-98d6-e9930da47fcf"
      },
      "source": [
        "# Lets Check it individually\n",
        "predict_individual_df = web.DataReader('EURUSD=X', data_source='yahoo', start='2020-7-12', end='2020-7-14')\n",
        "print(predict_individual_df['Close'])"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Date\n",
            "2020-07-12    1.131004\n",
            "2020-07-14    1.135976\n",
            "Name: Close, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Uup-rJx3ZKZz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 23,
      "outputs": []
    }
  ]
}