LSTM_stock_price_prediction_LGMVIP_intern.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 42,
      "metadata": {
        "id": "g6TH_GvNkUb0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "outputId": "385396bc-72b5-4335-e6da-0e58c1a8c867"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Date       Open       High        Low      Close  Adj Close  \\\n",
              "0     2013-01-02  19.779285  19.821428  19.343929  19.608213  16.890799   \n",
              "1     2013-01-03  19.567142  19.631071  19.321428  19.360714  16.677595   \n",
              "2     2013-01-04  19.177500  19.236786  18.779642  18.821428  16.213049   \n",
              "3     2013-01-07  18.642857  18.903570  18.400000  18.710714  16.117680   \n",
              "4     2013-01-08  18.900356  18.996071  18.616072  18.761070  16.161058   \n",
              "...          ...        ...        ...        ...        ...        ...   \n",
              "1254  2017-12-22  43.669998  43.855000  43.625000  43.752499  41.673252   \n",
              "1255  2017-12-26  42.700001  42.867500  42.419998  42.642502  40.616016   \n",
              "1256  2017-12-27  42.525002  42.695000  42.427502  42.650002  40.623150   \n",
              "1257  2017-12-28  42.750000  42.962502  42.619999  42.770000  40.737446   \n",
              "1258  2017-12-29  42.630001  42.647499  42.305000  42.307499  40.296925   \n",
              "\n",
              "         Volume  \n",
              "0     560518000  \n",
              "1     352965200  \n",
              "2     594333600  \n",
              "3     484156400  \n",
              "4     458707200  \n",
              "...         ...  \n",
              "1254   65397600  \n",
              "1255  132742000  \n",
              "1256   85992800  \n",
              "1257   65920800  \n",
              "1258  103999600  \n",
              "\n",
              "[1259 rows x 7 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a05f4d9a-4b0a-4bfb-9f4e-34b331186003\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Date</th>\n",
              "      <th>Open</th>\n",
              "      <th>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Close</th>\n",
              "      <th>Adj Close</th>\n",
              "      <th>Volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2013-01-02</td>\n",
              "      <td>19.779285</td>\n",
              "      <td>19.821428</td>\n",
              "      <td>19.343929</td>\n",
              "      <td>19.608213</td>\n",
              "      <td>16.890799</td>\n",
              "      <td>560518000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2013-01-03</td>\n",
              "      <td>19.567142</td>\n",
              "      <td>19.631071</td>\n",
              "      <td>19.321428</td>\n",
              "      <td>19.360714</td>\n",
              "      <td>16.677595</td>\n",
              "      <td>352965200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2013-01-04</td>\n",
              "      <td>19.177500</td>\n",
              "      <td>19.236786</td>\n",
              "      <td>18.779642</td>\n",
              "      <td>18.821428</td>\n",
              "      <td>16.213049</td>\n",
              "      <td>594333600</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2013-01-07</td>\n",
              "      <td>18.642857</td>\n",
              "      <td>18.903570</td>\n",
              "      <td>18.400000</td>\n",
              "      <td>18.710714</td>\n",
              "      <td>16.117680</td>\n",
              "      <td>484156400</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2013-01-08</td>\n",
              "      <td>18.900356</td>\n",
              "      <td>18.996071</td>\n",
              "      <td>18.616072</td>\n",
              "      <td>18.761070</td>\n",
              "      <td>16.161058</td>\n",
              "      <td>458707200</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",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1254</th>\n",
              "      <td>2017-12-22</td>\n",
              "      <td>43.669998</td>\n",
              "      <td>43.855000</td>\n",
              "      <td>43.625000</td>\n",
              "      <td>43.752499</td>\n",
              "      <td>41.673252</td>\n",
              "      <td>65397600</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1255</th>\n",
              "      <td>2017-12-26</td>\n",
              "      <td>42.700001</td>\n",
              "      <td>42.867500</td>\n",
              "      <td>42.419998</td>\n",
              "      <td>42.642502</td>\n",
              "      <td>40.616016</td>\n",
              "      <td>132742000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1256</th>\n",
              "      <td>2017-12-27</td>\n",
              "      <td>42.525002</td>\n",
              "      <td>42.695000</td>\n",
              "      <td>42.427502</td>\n",
              "      <td>42.650002</td>\n",
              "      <td>40.623150</td>\n",
              "      <td>85992800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1257</th>\n",
              "      <td>2017-12-28</td>\n",
              "      <td>42.750000</td>\n",
              "      <td>42.962502</td>\n",
              "      <td>42.619999</td>\n",
              "      <td>42.770000</td>\n",
              "      <td>40.737446</td>\n",
              "      <td>65920800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1258</th>\n",
              "      <td>2017-12-29</td>\n",
              "      <td>42.630001</td>\n",
              "      <td>42.647499</td>\n",
              "      <td>42.305000</td>\n",
              "      <td>42.307499</td>\n",
              "      <td>40.296925</td>\n",
              "      <td>103999600</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1259 rows × 7 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a05f4d9a-4b0a-4bfb-9f4e-34b331186003')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-a05f4d9a-4b0a-4bfb-9f4e-34b331186003 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-a05f4d9a-4b0a-4bfb-9f4e-34b331186003');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 42
        }
      ],
      "source": [
        "import pandas as pd\n",
        "df=pd.read_csv('/content/AAPL (5) _main file.csv')\n",
        "df"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df1=df.iloc[:,[1,5]]\n",
        "df1"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "DiMFM_q5gphz",
        "outputId": "cc17cbe2-8bc8-41e5-a71a-93349a52ecc8"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           Open  Adj Close\n",
              "0     19.779285  16.890799\n",
              "1     19.567142  16.677595\n",
              "2     19.177500  16.213049\n",
              "3     18.642857  16.117680\n",
              "4     18.900356  16.161058\n",
              "...         ...        ...\n",
              "1254  43.669998  41.673252\n",
              "1255  42.700001  40.616016\n",
              "1256  42.525002  40.623150\n",
              "1257  42.750000  40.737446\n",
              "1258  42.630001  40.296925\n",
              "\n",
              "[1259 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-315b05ea-06eb-4e38-94f2-fef2e7da933e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Open</th>\n",
              "      <th>Adj Close</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>19.779285</td>\n",
              "      <td>16.890799</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>19.567142</td>\n",
              "      <td>16.677595</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>19.177500</td>\n",
              "      <td>16.213049</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>18.642857</td>\n",
              "      <td>16.117680</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>18.900356</td>\n",
              "      <td>16.161058</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1254</th>\n",
              "      <td>43.669998</td>\n",
              "      <td>41.673252</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1255</th>\n",
              "      <td>42.700001</td>\n",
              "      <td>40.616016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1256</th>\n",
              "      <td>42.525002</td>\n",
              "      <td>40.623150</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1257</th>\n",
              "      <td>42.750000</td>\n",
              "      <td>40.737446</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1258</th>\n",
              "      <td>42.630001</td>\n",
              "      <td>40.296925</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1259 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-315b05ea-06eb-4e38-94f2-fef2e7da933e')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-315b05ea-06eb-4e38-94f2-fef2e7da933e button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-315b05ea-06eb-4e38-94f2-fef2e7da933e');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df1.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "31wE6YXC5v3B",
        "outputId": "1cc6f0a6-697d-421d-f326-0666adedb5c5"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1259, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(df1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EVqBgw0F9-EO",
        "outputId": "91d76da3-38c1-4e83-b8ad-18e522aad5d3"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1259"
            ]
          },
          "metadata": {},
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import MinMaxScaler\n",
        "scalar=MinMaxScaler(feature_range=(0,1))  #you must pass to MinMaxScaler function a 2D input\n",
        "df1_scaled=scalar.fit_transform(df1)\n",
        "df1_scaled"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SQwX1Xs2USgV",
        "outputId": "0938c446-3bb8-4797-eccc-bf9783280ccc"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.19795893, 0.16061139],\n",
              "       [0.19086893, 0.15348663],\n",
              "       [0.17784675, 0.13796265],\n",
              "       ...,\n",
              "       [0.95814044, 0.9536882 ],\n",
              "       [0.96566006, 0.95750769],\n",
              "       [0.96164959, 0.94278656]])"
            ]
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df1_scaled.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "89z9hJQ-Ut40",
        "outputId": "2e2eaa74-8acf-469a-9471-b261243fb4fb"
      },
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1259, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "split_percent=0.65\n",
        "split=int(split_percent*len(df1_scaled))\n",
        "split"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zM-G7VyeNIif",
        "outputId": "8a2530c4-b06b-4eeb-a18e-ba4db90399bb"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "818"
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_data=df1_scaled[:split]\n",
        "train_data"
      ],
      "metadata": {
        "id": "EMwXmPuWLE6Y",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "dfc22303-1916-4b17-e885-92bd15f1f42b"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.19795893, 0.16061139],\n",
              "       [0.19086893, 0.15348663],\n",
              "       [0.17784675, 0.13796265],\n",
              "       ...,\n",
              "       [0.44471235, 0.44005311],\n",
              "       [0.45365243, 0.43566278],\n",
              "       [0.44579853, 0.44336529]])"
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_data=df1_scaled[split:]\n",
        "test_data"
      ],
      "metadata": {
        "id": "GIfBXc2aLRAC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "91e6944d-9ebf-4662-b5ef-629e88024b8f"
      },
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.45950108, 0.45206929],\n",
              "       [0.45189787, 0.44197879],\n",
              "       [0.45791362, 0.45083688],\n",
              "       [0.4555741 , 0.43219651],\n",
              "       [0.44688474, 0.43312097],\n",
              "       [0.44738602, 0.43589383],\n",
              "       [0.45047742, 0.44683149],\n",
              "       [0.4626761 , 0.45915564],\n",
              "       [0.46952737, 0.45961771],\n",
              "       [0.4736214 , 0.4422869 ],\n",
              "       [0.4467176 , 0.42403187],\n",
              "       [0.4382788 , 0.41964147],\n",
              "       [0.42791837, 0.42133598],\n",
              "       [0.43034138, 0.41240106],\n",
              "       [0.4142994 , 0.4101672 ],\n",
              "       [0.41421581, 0.40554575],\n",
              "       [0.40510866, 0.39992302],\n",
              "       [0.33901887, 0.34962538],\n",
              "       [0.35247077, 0.32659474],\n",
              "       [0.32222485, 0.31819892],\n",
              "       [0.32205778, 0.31742864],\n",
              "       [0.32397945, 0.3292907 ],\n",
              "       [0.33233466, 0.32166505],\n",
              "       [0.32230844, 0.31872017],\n",
              "       [0.31704468, 0.31469075],\n",
              "       [0.31395322, 0.31523308],\n",
              "       [0.31671044, 0.32011511],\n",
              "       [0.31796376, 0.31306314],\n",
              "       [0.31161376, 0.29624687],\n",
              "       [0.28888757, 0.29764178],\n",
              "       [0.30885654, 0.32368003],\n",
              "       [0.32690384, 0.32065765],\n",
              "       [0.3236453 , 0.32894958],\n",
              "       [0.32765577, 0.32615971],\n",
              "       [0.32765577, 0.3340641 ],\n",
              "       [0.33793272, 0.34344119],\n",
              "       [0.34921223, 0.35483266],\n",
              "       [0.36132729, 0.36816189],\n",
              "       [0.36976606, 0.37428361],\n",
              "       [0.36776084, 0.37381884],\n",
              "       [0.36909765, 0.37002171],\n",
              "       [0.36425159, 0.35917233],\n",
              "       [0.35238721, 0.35343782],\n",
              "       [0.3539747 , 0.35498769],\n",
              "       [0.35564571, 0.36048982],\n",
              "       [0.36617332, 0.36358943],\n",
              "       [0.36425159, 0.36289214],\n",
              "       [0.35990691, 0.36839427],\n",
              "       [0.36015756, 0.36203976],\n",
              "       [0.36149443, 0.35049293],\n",
              "       [0.35004775, 0.35142301],\n",
              "       [0.35422536, 0.34894312],\n",
              "       [0.34277868, 0.3521204 ],\n",
              "       [0.34419914, 0.33491661],\n",
              "       [0.33901887, 0.33313429],\n",
              "       [0.33016237, 0.3394114 ],\n",
              "       [0.34110767, 0.33662137],\n",
              "       [0.33851759, 0.34088371],\n",
              "       [0.31320128, 0.31996016],\n",
              "       [0.31395322, 0.30942087],\n",
              "       [0.3131177 , 0.3214326 ],\n",
              "       [0.32205778, 0.32770978],\n",
              "       [0.32598476, 0.33700885],\n",
              "       [0.33475767, 0.33925628],\n",
              "       [0.33392219, 0.33228177],\n",
              "       [0.32732157, 0.33646648],\n",
              "       [0.33651227, 0.33964389],\n",
              "       [0.34311289, 0.34537827],\n",
              "       [0.34528528, 0.3477032 ],\n",
              "       [0.34879447, 0.35111319],\n",
              "       [0.35079976, 0.34685072],\n",
              "       [0.35063262, 0.36172961],\n",
              "       [0.3634161 , 0.36165215],\n",
              "       [0.36157792, 0.36978912],\n",
              "       [0.3687634 , 0.3700989 ],\n",
              "       [0.37243973, 0.37079659],\n",
              "       [0.37101935, 0.36668944],\n",
              "       [0.36625691, 0.36072247],\n",
              "       [0.3578181 , 0.35049293],\n",
              "       [0.34587015, 0.34530085],\n",
              "       [0.40811647, 0.39396735],\n",
              "       [0.39608499, 0.40473895],\n",
              "       [0.40744812, 0.40373168],\n",
              "       [0.40928627, 0.41799051],\n",
              "       [0.42298882, 0.40582392],\n",
              "       [0.41262829, 0.4159758 ],\n",
              "       [0.41906184, 0.4210401 ],\n",
              "       [0.4248269 , 0.43358437],\n",
              "       [0.43527092, 0.44051872],\n",
              "       [0.44120319, 0.44394685],\n",
              "       [0.44521366, 0.43763598],\n",
              "       [0.44362614, 0.43709044],\n",
              "       [0.43744331, 0.43903838],\n",
              "       [0.44045119, 0.44916731],\n",
              "       [0.45290043, 0.44838804],\n",
              "       [0.4484722 , 0.44714137],\n",
              "       [0.44955841, 0.44605082],\n",
              "       [0.44571494, 0.44823239],\n",
              "       [0.44646695, 0.44160973],\n",
              "       [0.444211  , 0.44425874],\n",
              "       [0.44404393, 0.43786954],\n",
              "       [0.43418478, 0.43428564],\n",
              "       [0.43435192, 0.42937717],\n",
              "       [0.42775129, 0.42844218],\n",
              "       [0.42090002, 0.42205305],\n",
              "       [0.41973029, 0.42283211],\n",
              "       [0.42374076, 0.42774098],\n",
              "       [0.43677486, 0.43553228],\n",
              "       [0.43844594, 0.43529836],\n",
              "       [0.43786107, 0.44044089],\n",
              "       [0.43301505, 0.41831323],\n",
              "       [0.41120793, 0.39969167],\n",
              "       [0.39458105, 0.41768999],\n",
              "       [0.43518744, 0.4372463 ],\n",
              "       [0.4453808 , 0.46700964],\n",
              "       [0.48824302, 0.49661691],\n",
              "       [0.49877063, 0.49155261],\n",
              "       [0.4993555 , 0.48111204],\n",
              "       [0.48147533, 0.48103411],\n",
              "       [0.48815947, 0.48087825],\n",
              "       [0.49233708, 0.48921512],\n",
              "       [0.49292195, 0.47433356],\n",
              "       [0.46969445, 0.47565796],\n",
              "       [0.48105754, 0.47729422],\n",
              "       [0.48682267, 0.48399497],\n",
              "       [0.48239441, 0.47020395],\n",
              "       [0.47654572, 0.47698273],\n",
              "       [0.47863453, 0.47285296],\n",
              "       [0.48155882, 0.47659308],\n",
              "       [0.48439963, 0.47698273],\n",
              "       [0.48690616, 0.48352742],\n",
              "       [0.49200284, 0.484852  ],\n",
              "       [0.49793504, 0.5003568 ],\n",
              "       [0.52032702, 0.50230484],\n",
              "       [0.51740273, 0.51040773],\n",
              "       [0.51272381, 0.50760276],\n",
              "       [0.52183096, 0.51266732],\n",
              "       [0.51723562, 0.51204388],\n",
              "       [0.52433756, 0.51142071],\n",
              "       [0.51656721, 0.50869377],\n",
              "       [0.51330867, 0.5082262 ],\n",
              "       [0.51289088, 0.50464223],\n",
              "       [0.51531392, 0.51282311],\n",
              "       [0.52241582, 0.51749796],\n",
              "       [0.49200284, 0.49677293],\n",
              "       [0.50102651, 0.48812427],\n",
              "       [0.48832661, 0.48220275],\n",
              "       [0.48648843, 0.48080042],\n",
              "       [0.48490094, 0.4648281 ],\n",
              "       [0.46768919, 0.46560693],\n",
              "       [0.46418004, 0.45628785],\n",
              "       [0.44370972, 0.44853445],\n",
              "       [0.45666031, 0.46082993],\n",
              "       [0.45858197, 0.46592039],\n",
              "       [0.45498923, 0.46451081],\n",
              "       [0.46509904, 0.44031163],\n",
              "       [0.4319289 , 0.44532369],\n",
              "       [0.43685845, 0.42402221],\n",
              "       [0.4273335 , 0.43498637],\n",
              "       [0.42841965, 0.45754084],\n",
              "       [0.45440437, 0.45722749],\n",
              "       [0.45365243, 0.45808899],\n",
              "       [0.45699455, 0.47116758],\n",
              "       [0.47228453, 0.47171566],\n",
              "       [0.46735498, 0.46725158],\n",
              "       [0.46543325, 0.47163733],\n",
              "       [0.46793985, 0.46991439],\n",
              "       [0.46250896, 0.46905308],\n",
              "       [0.46936024, 0.46169143],\n",
              "       [0.45908335, 0.45362511],\n",
              "       [0.44905706, 0.45683593],\n",
              "       [0.45599189, 0.45064911],\n",
              "       [0.45181428, 0.45722749],\n",
              "       [0.44980906, 0.4656855 ],\n",
              "       [0.46317738, 0.47422168],\n",
              "       [0.47529241, 0.48855312],\n",
              "       [0.48348055, 0.48346266],\n",
              "       [0.48807589, 0.49826433],\n",
              "       [0.49810218, 0.49826433],\n",
              "       [0.50094292, 0.50319809],\n",
              "       [0.51005014, 0.50437262],\n",
              "       [0.50445218, 0.50961977],\n",
              "       [0.51230601, 0.51204732],\n",
              "       [0.51280739, 0.5129089 ],\n",
              "       [0.50904751, 0.50687877],\n",
              "       [0.50269751, 0.50867994],\n",
              "       [0.51046787, 0.51447508],\n",
              "       [0.51882308, 0.51055948],\n",
              "       [0.509883  , 0.51032442],\n",
              "       [0.51155408, 0.50319809],\n",
              "       [0.50445218, 0.50578237],\n",
              "       [0.5048699 , 0.50476427],\n",
              "       [0.50545477, 0.50938471],\n",
              "       [0.51264026, 0.51956567],\n",
              "       [0.52241582, 0.52802348],\n",
              "       [0.5292671 , 0.52896332],\n",
              "       [0.52901645, 0.53397555],\n",
              "       [0.53035331, 0.53005965],\n",
              "       [0.53210791, 0.52841517],\n",
              "       [0.52567436, 0.53593341],\n",
              "       [0.53954405, 0.53585492],\n",
              "       [0.53453092, 0.53421037],\n",
              "       [0.54330386, 0.53593341],\n",
              "       [0.53954405, 0.53655979],\n",
              "       [0.53578424, 0.53569849],\n",
              "       [0.54305324, 0.55065635],\n",
              "       [0.55349726, 0.55112623],\n",
              "       [0.55742421, 0.55120463],\n",
              "       [0.5473144 , 0.54869861],\n",
              "       [0.54915255, 0.54650579],\n",
              "       [0.59828122, 0.60445829],\n",
              "       [0.60621871, 0.60273548],\n",
              "       [0.60897586, 0.6070426 ],\n",
              "       [0.61582721, 0.61651851],\n",
              "       [0.62760796, 0.62622958],\n",
              "       [0.63437582, 0.63022365],\n",
              "       [0.63688225, 0.63769551],\n",
              "       [0.64365011, 0.63533616],\n",
              "       [0.64883027, 0.64453865],\n",
              "       [0.65208881, 0.65814564],\n",
              "       [0.66921704, 0.66199962],\n",
              "       [0.67047028, 0.66074135],\n",
              "       [0.66570788, 0.66365171],\n",
              "       [0.67514917, 0.67135954],\n",
              "       [0.67682018, 0.67458446],\n",
              "       [0.68475774, 0.6700228 ],\n",
              "       [0.67247557, 0.67104504],\n",
              "       [0.68275245, 0.6731687 ],\n",
              "       [0.68225114, 0.67364089],\n",
              "       [0.68901886, 0.69566358],\n",
              "       [0.70664837, 0.68913543],\n",
              "       [0.69645501, 0.69558491],\n",
              "       [0.70138455, 0.69212403],\n",
              "       [0.69879443, 0.69353966],\n",
              "       [0.69787536, 0.68945006],\n",
              "       [0.69612083, 0.68693298],\n",
              "       [0.70038196, 0.6905512 ],\n",
              "       [0.69703994, 0.69102285],\n",
              "       [0.70079975, 0.68937139],\n",
              "       [0.70171882, 0.70093336],\n",
              "       [0.71266412, 0.70274242],\n",
              "       [0.71500358, 0.69723678],\n",
              "       [0.70999039, 0.70879888],\n",
              "       [0.72427787, 0.69605684],\n",
              "       [0.70539515, 0.70848425],\n",
              "       [0.71717591, 0.70455144],\n",
              "       [0.71918119, 0.70234939],\n",
              "       [0.70155169, 0.70423682],\n",
              "       [0.71425165, 0.72720362],\n",
              "       [0.7373955 , 0.72972067],\n",
              "       [0.74165676, 0.7282261 ],\n",
              "       [0.73772977, 0.72610258],\n",
              "       [0.73764629, 0.72641721],\n",
              "       [0.73380282, 0.73483342],\n",
              "       [0.74190738, 0.72893412],\n",
              "       [0.74249218, 0.72610258],\n",
              "       [0.73781329, 0.72358554],\n",
              "       [0.73672721, 0.72224854],\n",
              "       [0.73121274, 0.71013585],\n",
              "       [0.72001678, 0.71147312],\n",
              "       [0.72260686, 0.70557395],\n",
              "       [0.71901406, 0.71170908],\n",
              "       [0.71842926, 0.70675362],\n",
              "       [0.72235621, 0.70266362],\n",
              "       [0.71684173, 0.71650707],\n",
              "       [0.72703513, 0.71516957],\n",
              "       [0.73589162, 0.72594515],\n",
              "       [0.7393173 , 0.73294546],\n",
              "       [0.74399618, 0.72625988],\n",
              "       [0.73940082, 0.72712523],\n",
              "       [0.74082117, 0.72602382],\n",
              "       [0.74926004, 0.74906935],\n",
              "       [0.76964663, 0.75638442],\n",
              "       [0.75335399, 0.75284514],\n",
              "       [0.76112441, 0.74867636],\n",
              "       [0.7631296 , 0.76778923],\n",
              "       [0.78209597, 0.79964403],\n",
              "       [0.82253518, 0.80735209],\n",
              "       [0.82053   , 0.80161012],\n",
              "       [0.81067077, 0.81203525],\n",
              "       [0.82947001, 0.82901591],\n",
              "       [0.84041534, 0.82585665],\n",
              "       [0.83983054, 0.8240402 ],\n",
              "       [0.82027937, 0.78281352],\n",
              "       [0.80081169, 0.80089916],\n",
              "       [0.81844119, 0.80500611],\n",
              "       [0.82362139, 0.81235125],\n",
              "       [0.83114102, 0.81085033],\n",
              "       [0.82228452, 0.80721761],\n",
              "       [0.82136545, 0.8114036 ],\n",
              "       [0.82362139, 0.80935042],\n",
              "       [0.81877537, 0.80982402],\n",
              "       [0.82337074, 0.80263707],\n",
              "       [0.81668656, 0.8059538 ],\n",
              "       [0.8201122 , 0.82388214],\n",
              "       [0.82646213, 0.81187716],\n",
              "       [0.8227858 , 0.815984  ],\n",
              "       [0.83214375, 0.82325011],\n",
              "       [0.83406541, 0.82024942],\n",
              "       [0.83356413, 0.77278278],\n",
              "       [0.75460734, 0.74466653],\n",
              "       [0.76647175, 0.75390741],\n",
              "       [0.76931249, 0.74261352],\n",
              "       [0.73438775, 0.73574194],\n",
              "       [0.73823109, 0.71978874],\n",
              "       [0.73722849, 0.75193264],\n",
              "       [0.76404867, 0.74142847],\n",
              "       [0.75276919, 0.74822062],\n",
              "       [0.754858  , 0.74632554],\n",
              "       [0.74951066, 0.75145894],\n",
              "       [0.76655527, 0.74782582],\n",
              "       [0.74850797, 0.73131936],\n",
              "       [0.74416332, 0.74790485],\n",
              "       [0.7460015 , 0.7309243 ],\n",
              "       [0.74382905, 0.73360977],\n",
              "       [0.74742186, 0.72950292],\n",
              "       [0.73747915, 0.73416263],\n",
              "       [0.73188115, 0.72342136],\n",
              "       [0.73087843, 0.73487358],\n",
              "       [0.74098831, 0.74182353],\n",
              "       [0.74616851, 0.74553555],\n",
              "       [0.75569345, 0.74719416],\n",
              "       [0.75260206, 0.76322666],\n",
              "       [0.77323944, 0.77325674],\n",
              "       [0.78034144, 0.77736409],\n",
              "       [0.78351632, 0.78147067],\n",
              "       [0.794211  , 0.78889471],\n",
              "       [0.80273335, 0.78352421],\n",
              "       [0.79011701, 0.78297145],\n",
              "       [0.79504655, 0.7973452 ],\n",
              "       [0.80523995, 0.80247887],\n",
              "       [0.81819057, 0.8081654 ],\n",
              "       [0.82153259, 0.78526186],\n",
              "       [0.78928145, 0.77688973],\n",
              "       [0.78936494, 0.77080853],\n",
              "       [0.7826809 , 0.78123394],\n",
              "       [0.86773693, 0.83722944],\n",
              "       [0.84910483, 0.82483006],\n",
              "       [0.84091676, 0.83130568],\n",
              "       [0.84918832, 0.85041894],\n",
              "       [0.86205545, 0.86044928],\n",
              "       [0.86756979, 0.86818895],\n",
              "       [0.8729171 , 0.82767256],\n",
              "       [0.84534502, 0.84479908],\n",
              "       [0.86807121, 0.86359047],\n",
              "       [0.87926716, 0.8774659 ],\n",
              "       [0.88996184, 0.87231211],\n",
              "       [0.87809743, 0.84781201],\n",
              "       [0.85587253, 0.84495765],\n",
              "       [0.85286465, 0.84265822],\n",
              "       [0.85896392, 0.8630349 ],\n",
              "       [0.8659824 , 0.8646211 ],\n",
              "       [0.87734536, 0.85899158],\n",
              "       [0.87082829, 0.86366963],\n",
              "       [0.87492242, 0.87643513],\n",
              "       [0.87458828, 0.88785254],\n",
              "       [0.90550254, 0.89134136],\n",
              "       [0.90416567, 0.89649501],\n",
              "       [0.91385776, 0.89689161],\n",
              "       [0.90508475, 0.88127189],\n",
              "       [0.89639539, 0.87992392],\n",
              "       [0.89121506, 0.87476987],\n",
              "       [0.88093817, 0.85391692],\n",
              "       [0.8779303 , 0.8766726 ],\n",
              "       [0.8955598 , 0.87159821],\n",
              "       [0.87266648, 0.8620045 ],\n",
              "       [0.86531395, 0.85114186],\n",
              "       [0.86096921, 0.86382847],\n",
              "       [0.87467176, 0.85423422],\n",
              "       [0.8696586 , 0.85470972],\n",
              "       [0.85620667, 0.83361954],\n",
              "       [0.83866081, 0.81236986],\n",
              "       [0.80306749, 0.80047656],\n",
              "       [0.79011701, 0.78985195],\n",
              "       [0.80507281, 0.8103876 ],\n",
              "       [0.82195038, 0.81902995],\n",
              "       [0.82270232, 0.81149767],\n",
              "       [0.81702084, 0.81815812],\n",
              "       [0.82579371, 0.81570009],\n",
              "       [0.82370491, 0.82101248],\n",
              "       [0.82053   , 0.81308323],\n",
              "       [0.82512526, 0.82822759],\n",
              "       [0.83172595, 0.82751399],\n",
              "       [0.8387443 , 0.83179545],\n",
              "       [0.8408331 , 0.83227121],\n",
              "       [0.84008117, 0.83742513],\n",
              "       [0.84325622, 0.83306411],\n",
              "       [0.8464311 , 0.84091392],\n",
              "       [0.85620667, 0.86382847],\n",
              "       [0.87191454, 0.86850625],\n",
              "       [0.87726188, 0.8628767 ],\n",
              "       [0.84659824, 0.83290564],\n",
              "       [0.84542851, 0.83504651],\n",
              "       [0.84776797, 0.83441217],\n",
              "       [0.84275477, 0.84178575],\n",
              "       [0.8479351 , 0.83631517],\n",
              "       [0.85060871, 0.84424378],\n",
              "       [0.86782042, 0.88896287],\n",
              "       [0.90625448, 0.91806173],\n",
              "       [0.93975883, 0.93645624],\n",
              "       [0.95621864, 0.91940942],\n",
              "       [0.92889718, 0.92908256],\n",
              "       [0.99072571, 0.96389038],\n",
              "       [0.97710667, 0.97776571],\n",
              "       [0.98997377, 0.98220626],\n",
              "       [0.99624019, 0.9935444 ],\n",
              "       [1.        , 0.99069017],\n",
              "       [1.        , 0.98607431],\n",
              "       [0.9865481 , 0.98050481],\n",
              "       [0.98270464, 0.95957664],\n",
              "       [0.95705419, 0.94159286],\n",
              "       [0.96716393, 0.95766703],\n",
              "       [0.9659942 , 0.95010771],\n",
              "       [0.95972779, 0.94875467],\n",
              "       [0.96382192, 0.9738998 ],\n",
              "       [0.98537837, 0.98838243],\n",
              "       [0.99991651, 0.98846173],\n",
              "       [0.99949872, 0.98145925],\n",
              "       [0.99323231, 0.97334286],\n",
              "       [0.9792791 , 0.94477598],\n",
              "       [0.96089752, 0.96363503],\n",
              "       [0.95688705, 0.95726879],\n",
              "       [0.97802575, 0.94732246],\n",
              "       [0.94945091, 0.94604908],\n",
              "       [0.93641681, 0.94103602],\n",
              "       [0.94920029, 0.94350283],\n",
              "       [0.96139894, 0.94390084],\n",
              "       [0.95062064, 0.97016011],\n",
              "       [0.97526849, 0.96244132],\n",
              "       [0.97819289, 0.96697685],\n",
              "       [0.9773573 , 0.96657902],\n",
              "       [0.98763431, 0.98050481],\n",
              "       [0.99807833, 1.        ],\n",
              "       [0.99933158, 0.9850401 ],\n",
              "       [0.99799471, 0.98352833],\n",
              "       [0.9921461 , 0.98878003],\n",
              "       [0.99640719, 0.98878003],\n",
              "       [0.96398905, 0.9534498 ],\n",
              "       [0.95814044, 0.9536882 ],\n",
              "       [0.96566006, 0.95750769],\n",
              "       [0.96164959, 0.94278656]])"
            ]
          },
          "metadata": {},
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(len(train_data),'  ', len(test_data))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6EpVvvWFjraa",
        "outputId": "e4733ba5-8ee8-479c-c110-c67b030ce125"
      },
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "818    441\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(train_data)-60-1"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fFfvXesG9KTO",
        "outputId": "98151d67-258c-4ec2-bb21-ea57b2db32d8"
      },
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "757"
            ]
          },
          "metadata": {},
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy\n",
        "#create dataset\n",
        "def  create_dataset (dataset, time_step):\n",
        "      data_x=[] \n",
        "      data_y=[]\n",
        "      for i in range(len(dataset)-time_step):#i=0,1,2,3,4,....\n",
        "          a=dataset[i:(i+time_step)]\n",
        "          data_x.append(a)\n",
        "          data_y.append(dataset[i+time_step])\n",
        "      return numpy.array(data_x), numpy.array(data_y) \n",
        "#0..59>>60\n",
        "#1..60>>61\n",
        "#2..61>>62\n",
        "#3..62>>63\n"
      ],
      "metadata": {
        "id": "sQuS2F26XWPr"
      },
      "execution_count": 53,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "time_step=60\n",
        "x_train,y_train=create_dataset (train_data, time_step)\n",
        "x_test,y_test=create_dataset (test_data, time_step)\n",
        "print(x_train.shape)\n",
        "print(y_train.shape)\n",
        "print(x_test.shape)\n",
        "print(y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "q_Ap710Xa406",
        "outputId": "bdc6de69-cc27-4616-b16e-684147afdfa4"
      },
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(758, 60, 2)\n",
            "(758, 2)\n",
            "(381, 60, 2)\n",
            "(381, 2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(train_data)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "z8htKSA48txJ",
        "outputId": "7d3d31de-299e-4399-9378-232803cfacbe"
      },
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "818"
            ]
          },
          "metadata": {},
          "execution_count": 55
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(len(x_train),'',len(train_data)-time_step)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VCzJ-dYCh8UX",
        "outputId": "0203a907-3c47-48af-d01f-bdb237018521"
      },
      "execution_count": 56,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "758  758\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(len(x_test),'',len(test_data)-time_step)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nY7y4FpFU-6l",
        "outputId": "f85a79eb-222b-4777-b04a-eb6ae09fea2a"
      },
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "381  381\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#reshape input to be [samples,time_steps,features] which is required to lstm\n",
        "x_train=x_train.reshape(x_train.shape[0],x_train.shape[1],2)\n",
        "x_train.shape"
      ],
      "metadata": {
        "id": "i-Vubrdrnugp",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1ac55108-8a4d-4cfe-8564-9ec57a16e564"
      },
      "execution_count": 58,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(758, 60, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 58
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_test=x_test.reshape(x_test.shape[0],x_test.shape[1],2)\n",
        "x_test.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MutRXdJ0CS7v",
        "outputId": "2cad5870-d46a-4c03-f104-0a0742750504"
      },
      "execution_count": 59,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(381, 60, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 59
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.models import Sequential\n",
        "from keras.layers import*"
      ],
      "metadata": {
        "id": "lRJED3gE0-9P"
      },
      "execution_count": 60,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model=Sequential()\n",
        "model.add(LSTM(units=50, return_sequences=True, input_shape=(time_step,2)))\n",
        "model.add(LSTM(units=50, return_sequences=True))\n",
        "model.add(LSTM(units=50))\n",
        "model.add(Dense(units=2))"
      ],
      "metadata": {
        "id": "fOTjewg51tBT"
      },
      "execution_count": 61,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J8MEoA_eE9xG",
        "outputId": "230b91cf-24b9-412a-8d8b-d7a1c436bec0"
      },
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " lstm_3 (LSTM)               (None, 60, 50)            10600     \n",
            "                                                                 \n",
            " lstm_4 (LSTM)               (None, 60, 50)            20200     \n",
            "                                                                 \n",
            " lstm_5 (LSTM)               (None, 50)                20200     \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 2)                 102       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 51,102\n",
            "Trainable params: 51,102\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(optimizer='adam',loss='mean_squared_error')"
      ],
      "metadata": {
        "id": "8B4TPhRt4hRz"
      },
      "execution_count": 63,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.fit(x_train,y_train,epochs=100,batch_size=32)"
      ],
      "metadata": {
        "id": "vi5zP8eg4yFY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "97c24342-5430-4642-889b-07334efac791"
      },
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "24/24 [==============================] - 5s 13ms/step - loss: 0.0177\n",
            "Epoch 2/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 0.0019\n",
            "Epoch 3/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 0.0012\n",
            "Epoch 4/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 0.0012\n",
            "Epoch 5/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 0.0012\n",
            "Epoch 6/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 0.0011\n",
            "Epoch 7/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 0.0011\n",
            "Epoch 8/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 0.0011\n",
            "Epoch 9/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 9.6612e-04\n",
            "Epoch 10/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 8.9436e-04\n",
            "Epoch 11/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 8.9496e-04\n",
            "Epoch 12/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 8.3987e-04\n",
            "Epoch 13/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 8.0347e-04\n",
            "Epoch 14/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 8.1477e-04\n",
            "Epoch 15/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 8.1688e-04\n",
            "Epoch 16/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 9.0708e-04\n",
            "Epoch 17/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 7.2258e-04\n",
            "Epoch 18/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 8.2624e-04\n",
            "Epoch 19/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 8.0599e-04\n",
            "Epoch 20/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 7.8158e-04\n",
            "Epoch 21/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.8045e-04\n",
            "Epoch 22/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 6.7845e-04\n",
            "Epoch 23/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.6734e-04\n",
            "Epoch 24/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.3938e-04\n",
            "Epoch 25/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 6.3403e-04\n",
            "Epoch 26/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.0997e-04\n",
            "Epoch 27/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 7.0318e-04\n",
            "Epoch 28/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.8996e-04\n",
            "Epoch 29/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.5746e-04\n",
            "Epoch 30/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.0230e-04\n",
            "Epoch 31/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.6891e-04\n",
            "Epoch 32/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 6.0053e-04\n",
            "Epoch 33/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 5.4384e-04\n",
            "Epoch 34/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.1573e-04\n",
            "Epoch 35/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.8167e-04\n",
            "Epoch 36/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 6.3333e-04\n",
            "Epoch 37/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.0710e-04\n",
            "Epoch 38/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 5.9690e-04\n",
            "Epoch 39/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.9787e-04\n",
            "Epoch 40/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 5.6640e-04\n",
            "Epoch 41/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 5.1315e-04\n",
            "Epoch 42/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.9064e-04\n",
            "Epoch 43/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 5.3240e-04\n",
            "Epoch 44/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 4.5227e-04\n",
            "Epoch 45/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 4.7038e-04\n",
            "Epoch 46/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 5.3486e-04\n",
            "Epoch 47/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 4.4775e-04\n",
            "Epoch 48/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.3775e-04\n",
            "Epoch 49/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.2097e-04\n",
            "Epoch 50/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.7765e-04\n",
            "Epoch 51/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.6443e-04\n",
            "Epoch 52/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 3.9260e-04\n",
            "Epoch 53/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.9863e-04\n",
            "Epoch 54/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 4.4507e-04\n",
            "Epoch 55/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 3.9785e-04\n",
            "Epoch 56/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 4.1790e-04\n",
            "Epoch 57/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 3.6419e-04\n",
            "Epoch 58/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 3.4668e-04\n",
            "Epoch 59/100\n",
            "24/24 [==============================] - 0s 14ms/step - loss: 3.3287e-04\n",
            "Epoch 60/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 3.4482e-04\n",
            "Epoch 61/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 3.1924e-04\n",
            "Epoch 62/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 3.2399e-04\n",
            "Epoch 63/100\n",
            "24/24 [==============================] - 0s 13ms/step - loss: 3.3235e-04\n",
            "Epoch 64/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 3.9725e-04\n",
            "Epoch 65/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.8533e-04\n",
            "Epoch 66/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 3.1391e-04\n",
            "Epoch 67/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 3.0524e-04\n",
            "Epoch 68/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.8582e-04\n",
            "Epoch 69/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.8977e-04\n",
            "Epoch 70/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 2.5611e-04\n",
            "Epoch 71/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.5452e-04\n",
            "Epoch 72/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4846e-04\n",
            "Epoch 73/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4241e-04\n",
            "Epoch 74/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.6779e-04\n",
            "Epoch 75/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4290e-04\n",
            "Epoch 76/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4784e-04\n",
            "Epoch 77/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.1995e-04\n",
            "Epoch 78/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.2968e-04\n",
            "Epoch 79/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4870e-04\n",
            "Epoch 80/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.4717e-04\n",
            "Epoch 81/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.9588e-04\n",
            "Epoch 82/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 2.0385e-04\n",
            "Epoch 83/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.8728e-04\n",
            "Epoch 84/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.8647e-04\n",
            "Epoch 85/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.9084e-04\n",
            "Epoch 86/100\n",
            "24/24 [==============================] - 0s 10ms/step - loss: 1.8550e-04\n",
            "Epoch 87/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.7310e-04\n",
            "Epoch 88/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.6984e-04\n",
            "Epoch 89/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.6803e-04\n",
            "Epoch 90/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.8613e-04\n",
            "Epoch 91/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.7080e-04\n",
            "Epoch 92/100\n",
            "24/24 [==============================] - 0s 11ms/step - loss: 1.9483e-04\n",
            "Epoch 93/100\n",
            "24/24 [==============================] - 0s 17ms/step - loss: 1.6694e-04\n",
            "Epoch 94/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 1.5639e-04\n",
            "Epoch 95/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 1.9215e-04\n",
            "Epoch 96/100\n",
            "24/24 [==============================] - 0s 15ms/step - loss: 1.5992e-04\n",
            "Epoch 97/100\n",
            "24/24 [==============================] - 0s 16ms/step - loss: 2.0908e-04\n",
            "Epoch 98/100\n",
            "24/24 [==============================] - 0s 17ms/step - loss: 1.7728e-04\n",
            "Epoch 99/100\n",
            "24/24 [==============================] - 0s 17ms/step - loss: 2.0684e-04\n",
            "Epoch 100/100\n",
            "24/24 [==============================] - 0s 17ms/step - loss: 1.8128e-04\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7fb52449cee0>"
            ]
          },
          "metadata": {},
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_predict=model.predict(x_train)\n",
        "test_predict=model.predict(x_test)"
      ],
      "metadata": {
        "id": "gfsDq_mC6_Xn",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2f748f8e-ced9-47ca-b48b-dc14f7eae9f1"
      },
      "execution_count": 65,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "24/24 [==============================] - 1s 7ms/step\n",
            "12/12 [==============================] - 0s 6ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_test.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kdCiiFgCmX-o",
        "outputId": "a0ed4428-816c-482b-da2c-e54a4f6347cf"
      },
      "execution_count": 66,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(381, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_predict.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PCLZj4wEmyhZ",
        "outputId": "d363d89e-9376-48e7-9591-c5a180fab602"
      },
      "execution_count": 67,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(381, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 67
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_predict=scalar.inverse_transform(train_predict)\n",
        "test_predict=scalar.inverse_transform(test_predict)"
      ],
      "metadata": {
        "id": "yl5GhjqLnAYy"
      },
      "execution_count": 68,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_predict.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jqT_4CAVXM2p",
        "outputId": "9343406c-eb9a-4699-b192-372402b3f0fc"
      },
      "execution_count": 69,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(758, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 69
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4FeEgcXHowmc",
        "outputId": "82448cbb-ae14-4221-8e45-367a64f67dd5"
      },
      "execution_count": 70,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(758, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_train=scalar.inverse_transform(y_train)  #to make inverse transform\n",
        "y_test=scalar.inverse_transform(y_test)"
      ],
      "metadata": {
        "id": "1nQZXoSg-vgL"
      },
      "execution_count": 71,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import mean_squared_error\n",
        "mse_train=mean_squared_error(y_train,train_predict)  \n",
        "mse_train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sTpjVxbpHcUk",
        "outputId": "a9ee5baa-99e1-4b0c-89ea-997529769f01"
      },
      "execution_count": 72,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.1491818160383244"
            ]
          },
          "metadata": {},
          "execution_count": 72
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "mse_test=mean_squared_error(y_test,test_predict)  \n",
        "mse_test"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a2RmZQRqH2CN",
        "outputId": "cd39f0a1-d249-4ef3-a6ea-98e3cf857163"
      },
      "execution_count": 73,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.32098075758360844"
            ]
          },
          "metadata": {},
          "execution_count": 73
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.figure(figsize=(10,6))\n",
        "plt.plot(train_predict,color='red',label=\"predictions stock\")\n",
        "plt.plot(y_train,color='green',label=\"actual stock\")"
      ],
      "metadata": {
        "id": "fAws9k9uHFN2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 468
        },
        "outputId": "e8bbd563-b876-4710-a8fa-f11e42039c7a"
      },
      "execution_count": 74,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7fb51b4834f0>,\n",
              " <matplotlib.lines.Line2D at 0x7fb51b483520>]"
            ]
          },
          "metadata": {},
          "execution_count": 74
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(10,6))\n",
        "plt.plot(test_predict,color='red',label=\"predictions stock\")\n",
        "plt.plot(y_test,color='green',label=\"actual stock\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 468
        },
        "id": "ceiUfA5NPUX_",
        "outputId": "f5feaf05-94b4-4245-8ef0-c9698457574f"
      },
      "execution_count": 75,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7fb51b1bbcd0>,\n",
              " <matplotlib.lines.Line2D at 0x7fb51b1bbd00>]"
            ]
          },
          "metadata": {},
          "execution_count": 75
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_predict.shape\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UTWlZ6Z_CsLy",
        "outputId": "0a11c759-75d5-415c-f716-2604b3e1b1bf"
      },
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(758, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 76
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_predict.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5xcsC_bLC2Ah",
        "outputId": "1ebd5b5e-ed8b-4c99-ef03-ff768f3c4a4e"
      },
      "execution_count": 77,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(381, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 77
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_test[0]"
      ],
      "metadata": {
        "id": "-sMBwkUSCCZ2",
        "outputId": "2934b930-316e-4f5f-fec2-6cd8a602aa08",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 78,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([23.225   , 21.703278])"
            ]
          },
          "metadata": {},
          "execution_count": 78
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_predict[0]"
      ],
      "metadata": {
        "id": "rRDlpAeQCMOU",
        "outputId": "ef6d3a5e-ede3-48fc-92b8-9aca6b2e9fbf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 79,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([23.347672, 21.609188], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 79
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "trainpredictplot=numpy.empty_like(df1)#create a new array with the same shape and type as a given array.\n",
        "trainpredictplot[:,:]=numpy.nan\n",
        "trainpredictplot[time_step:len(train_predict)+time_step,:]=train_predict\n"
      ],
      "metadata": {
        "id": "JdobTS8G3XQ7"
      },
      "execution_count": 80,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "testpredictplot=numpy.empty_like(df1)\n",
        "testpredictplot[:,:]=numpy.nan\n",
        "testpredictplot[split+time_step:len(test_predict)+split+time_step,:]=test_predict\n"
      ],
      "metadata": {
        "id": "Up_6sATK5tlo"
      },
      "execution_count": 81,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.plot(df1,color='red')\n",
        "plt.plot(trainpredictplot,'yellow')\n",
        "plt.plot(testpredictplot,color='blue')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "9kruj2M86LjQ",
        "outputId": "da82bc1a-6d08-42c7-afee-fc63a4dacc30"
      },
      "execution_count": 82,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7fb51b2690f0>,\n",
              " <matplotlib.lines.Line2D at 0x7fb51b269120>]"
            ]
          },
          "metadata": {},
          "execution_count": 82
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}