Stock_trend_prediction.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "R9sKSVrarXuw",
        "outputId": "c33a5ba4-2e3b-4283-c132-f3d0584d1118"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: yfinance in /usr/local/lib/python3.7/dist-packages (0.1.70)\n",
            "Requirement already satisfied: lxml>=4.5.1 in /usr/local/lib/python3.7/dist-packages (from yfinance) (4.8.0)\n",
            "Requirement already satisfied: multitasking>=0.0.7 in /usr/local/lib/python3.7/dist-packages (from yfinance) (0.0.10)\n",
            "Requirement already satisfied: pandas>=0.24.0 in /usr/local/lib/python3.7/dist-packages (from yfinance) (1.3.5)\n",
            "Requirement already satisfied: numpy>=1.15 in /usr/local/lib/python3.7/dist-packages (from yfinance) (1.21.6)\n",
            "Requirement already satisfied: requests>=2.26 in /usr/local/lib/python3.7/dist-packages (from yfinance) (2.27.1)\n",
            "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.24.0->yfinance) (2022.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.24.0->yfinance) (2.8.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.7.3->pandas>=0.24.0->yfinance) (1.15.0)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.7/dist-packages (from requests>=2.26->yfinance) (2.0.12)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests>=2.26->yfinance) (2021.10.8)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests>=2.26->yfinance) (1.24.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests>=2.26->yfinance) (2.10)\n"
          ]
        }
      ],
      "source": [
        "!pip install yfinance\n",
        "import math\n",
        "import numpy as np\n",
        "import yfinance as yf\n",
        "# !pip install pandas\n",
        "# !pip install --upgrade pandas\n",
        "# !pip install --upgrade pandas-datareader\n",
        "# import pandas as pd #data read\n",
        "import matplotlib.pyplot as plt #graph plot\n",
        "# import pandas_datareader as dr #data read\n",
        "from sklearn.preprocessing import MinMaxScaler #min max\n",
        "plt.style.use('seaborn')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 455
        },
        "id": "mp4OyUjOr7YE",
        "outputId": "f789fb08-fd18-452e-d1b5-c4a79f6bab37"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  Open        High         Low       Close     Volume  \\\n",
              "Date                                                                    \n",
              "1980-12-12    0.100326    0.100762    0.100326    0.100326  469033600   \n",
              "1980-12-15    0.095528    0.095528    0.095092    0.095092  175884800   \n",
              "1980-12-16    0.088548    0.088548    0.088112    0.088112  105728000   \n",
              "1980-12-17    0.090293    0.090729    0.090293    0.090293   86441600   \n",
              "1980-12-18    0.092911    0.093347    0.092911    0.092911   73449600   \n",
              "...                ...         ...         ...         ...        ...   \n",
              "2022-04-18  163.919998  166.600006  163.570007  165.070007   69023900   \n",
              "2022-04-19  165.020004  167.820007  163.910004  167.399994   67723800   \n",
              "2022-04-20  168.759995  168.880005  166.100006  167.229996   67929800   \n",
              "2022-04-21  168.910004  171.529999  165.910004  166.419998   87227800   \n",
              "2022-04-22  166.460007  167.869995  161.500000  161.789993   84775200   \n",
              "\n",
              "            Dividends  Stock Splits  \n",
              "Date                                 \n",
              "1980-12-12        0.0           0.0  \n",
              "1980-12-15        0.0           0.0  \n",
              "1980-12-16        0.0           0.0  \n",
              "1980-12-17        0.0           0.0  \n",
              "1980-12-18        0.0           0.0  \n",
              "...               ...           ...  \n",
              "2022-04-18        0.0           0.0  \n",
              "2022-04-19        0.0           0.0  \n",
              "2022-04-20        0.0           0.0  \n",
              "2022-04-21        0.0           0.0  \n",
              "2022-04-22        0.0           0.0  \n",
              "\n",
              "[10429 rows x 7 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ed43b1a0-7c7b-482a-8f55-7b96dbf4c804\">\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>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Close</th>\n",
              "      <th>Volume</th>\n",
              "      <th>Dividends</th>\n",
              "      <th>Stock Splits</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",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1980-12-12</th>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100762</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>469033600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1980-12-15</th>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>175884800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1980-12-16</th>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>105728000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1980-12-17</th>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090729</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>86441600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1980-12-18</th>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.093347</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>73449600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</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>2022-04-18</th>\n",
              "      <td>163.919998</td>\n",
              "      <td>166.600006</td>\n",
              "      <td>163.570007</td>\n",
              "      <td>165.070007</td>\n",
              "      <td>69023900</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-19</th>\n",
              "      <td>165.020004</td>\n",
              "      <td>167.820007</td>\n",
              "      <td>163.910004</td>\n",
              "      <td>167.399994</td>\n",
              "      <td>67723800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-20</th>\n",
              "      <td>168.759995</td>\n",
              "      <td>168.880005</td>\n",
              "      <td>166.100006</td>\n",
              "      <td>167.229996</td>\n",
              "      <td>67929800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-21</th>\n",
              "      <td>168.910004</td>\n",
              "      <td>171.529999</td>\n",
              "      <td>165.910004</td>\n",
              "      <td>166.419998</td>\n",
              "      <td>87227800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-22</th>\n",
              "      <td>166.460007</td>\n",
              "      <td>167.869995</td>\n",
              "      <td>161.500000</td>\n",
              "      <td>161.789993</td>\n",
              "      <td>84775200</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>10429 rows × 7 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ed43b1a0-7c7b-482a-8f55-7b96dbf4c804')\"\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-ed43b1a0-7c7b-482a-8f55-7b96dbf4c804 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-ed43b1a0-7c7b-482a-8f55-7b96dbf4c804');\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": 3
        }
      ],
      "source": [
        "stock = yf.Ticker('AAPL')\n",
        "df = stock.history(period=\"max\", auto_adjust=True)\n",
        "df"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        },
        "id": "GkHBws7K2aBZ",
        "outputId": "23df1465-2d5a-4de5-d2a5-61cc9537d2e2"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  Open        High         Low       Close    Volume  \\\n",
              "Date                                                                   \n",
              "2022-04-18  163.919998  166.600006  163.570007  165.070007  69023900   \n",
              "2022-04-19  165.020004  167.820007  163.910004  167.399994  67723800   \n",
              "2022-04-20  168.759995  168.880005  166.100006  167.229996  67929800   \n",
              "2022-04-21  168.910004  171.529999  165.910004  166.419998  87227800   \n",
              "2022-04-22  166.460007  167.869995  161.500000  161.789993  84775200   \n",
              "\n",
              "            Dividends  Stock Splits  \n",
              "Date                                 \n",
              "2022-04-18        0.0           0.0  \n",
              "2022-04-19        0.0           0.0  \n",
              "2022-04-20        0.0           0.0  \n",
              "2022-04-21        0.0           0.0  \n",
              "2022-04-22        0.0           0.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c0416521-57f6-4d09-af72-1f671495e153\">\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>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Close</th>\n",
              "      <th>Volume</th>\n",
              "      <th>Dividends</th>\n",
              "      <th>Stock Splits</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",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2022-04-18</th>\n",
              "      <td>163.919998</td>\n",
              "      <td>166.600006</td>\n",
              "      <td>163.570007</td>\n",
              "      <td>165.070007</td>\n",
              "      <td>69023900</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-19</th>\n",
              "      <td>165.020004</td>\n",
              "      <td>167.820007</td>\n",
              "      <td>163.910004</td>\n",
              "      <td>167.399994</td>\n",
              "      <td>67723800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-20</th>\n",
              "      <td>168.759995</td>\n",
              "      <td>168.880005</td>\n",
              "      <td>166.100006</td>\n",
              "      <td>167.229996</td>\n",
              "      <td>67929800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-21</th>\n",
              "      <td>168.910004</td>\n",
              "      <td>171.529999</td>\n",
              "      <td>165.910004</td>\n",
              "      <td>166.419998</td>\n",
              "      <td>87227800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2022-04-22</th>\n",
              "      <td>166.460007</td>\n",
              "      <td>167.869995</td>\n",
              "      <td>161.500000</td>\n",
              "      <td>161.789993</td>\n",
              "      <td>84775200</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c0416521-57f6-4d09-af72-1f671495e153')\"\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-c0416521-57f6-4d09-af72-1f671495e153 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-c0416521-57f6-4d09-af72-1f671495e153');\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": 4
        }
      ],
      "source": [
        "df.tail()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "xKv_SAb633o1",
        "outputId": "a50c5f3a-af87-4b53-e82c-832e7a595c16"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "        Date      Open      High       Low     Close     Volume  Dividends  \\\n",
              "0 1980-12-12  0.100326  0.100762  0.100326  0.100326  469033600        0.0   \n",
              "1 1980-12-15  0.095528  0.095528  0.095092  0.095092  175884800        0.0   \n",
              "2 1980-12-16  0.088548  0.088548  0.088112  0.088112  105728000        0.0   \n",
              "3 1980-12-17  0.090293  0.090729  0.090293  0.090293   86441600        0.0   \n",
              "4 1980-12-18  0.092911  0.093347  0.092911  0.092911   73449600        0.0   \n",
              "\n",
              "   Stock Splits  \n",
              "0           0.0  \n",
              "1           0.0  \n",
              "2           0.0  \n",
              "3           0.0  \n",
              "4           0.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-15a36ab7-6d49-4d18-8f31-707509a3820b\">\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>Volume</th>\n",
              "      <th>Dividends</th>\n",
              "      <th>Stock Splits</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1980-12-12</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100762</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>469033600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1980-12-15</td>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>175884800</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1980-12-16</td>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>105728000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1980-12-17</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090729</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>86441600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1980-12-18</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.093347</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>73449600</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-15a36ab7-6d49-4d18-8f31-707509a3820b')\"\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-15a36ab7-6d49-4d18-8f31-707509a3820b 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-15a36ab7-6d49-4d18-8f31-707509a3820b');\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": 5
        }
      ],
      "source": [
        "df=df.reset_index()\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "l7Su0c334JeB",
        "outputId": "40e851e4-90cb-4363-c254-d5ca17eb5589"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "        Date      Open      High       Low     Close     Volume\n",
              "0 1980-12-12  0.100326  0.100762  0.100326  0.100326  469033600\n",
              "1 1980-12-15  0.095528  0.095528  0.095092  0.095092  175884800\n",
              "2 1980-12-16  0.088548  0.088548  0.088112  0.088112  105728000\n",
              "3 1980-12-17  0.090293  0.090729  0.090293  0.090293   86441600\n",
              "4 1980-12-18  0.092911  0.093347  0.092911  0.092911   73449600"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a25d6d93-0793-4264-899d-bdc7f79516ac\">\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>Volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1980-12-12</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100762</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>0.100326</td>\n",
              "      <td>469033600</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1980-12-15</td>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095528</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>0.095092</td>\n",
              "      <td>175884800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1980-12-16</td>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088548</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>0.088112</td>\n",
              "      <td>105728000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1980-12-17</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090729</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>0.090293</td>\n",
              "      <td>86441600</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1980-12-18</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.093347</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>0.092911</td>\n",
              "      <td>73449600</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a25d6d93-0793-4264-899d-bdc7f79516ac')\"\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-a25d6d93-0793-4264-899d-bdc7f79516ac 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-a25d6d93-0793-4264-899d-bdc7f79516ac');\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": 6
        }
      ],
      "source": [
        "df=df.drop(['Dividends','Stock Splits'],axis=1)\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 364
        },
        "id": "5_kSpHyj45pJ",
        "outputId": "00a111fc-9862-4c04-b1e7-2d69de3f8063"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7f61cf05a990>]"
            ]
          },
          "metadata": {},
          "execution_count": 7
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.plot(df.Close)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_ruFQ6rq6DB5",
        "outputId": "743544ee-2f6f-4322-8249-e145d13c5f5d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0               NaN\n",
              "1               NaN\n",
              "2               NaN\n",
              "3               NaN\n",
              "4               NaN\n",
              "            ...    \n",
              "10424    169.151678\n",
              "10425    169.213631\n",
              "10426    169.268592\n",
              "10427    169.366687\n",
              "10428    169.384226\n",
              "Name: Close, Length: 10429, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ],
      "source": [
        "ma100=df.Close.rolling(100).mean()\n",
        "ma100"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 364
        },
        "id": "2g8bP37B6mI_",
        "outputId": "b9f740b4-0ef8-4bec-f7e3-41e70ff1086f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7f61cf00f710>]"
            ]
          },
          "metadata": {},
          "execution_count": 9
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.plot(df.Close)\n",
        "plt.plot(ma100,'r')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kULlkPsq7A8d",
        "outputId": "7414c902-a709-4c87-d201-7793b9af7d97"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0               NaN\n",
              "1               NaN\n",
              "2               NaN\n",
              "3               NaN\n",
              "4               NaN\n",
              "            ...    \n",
              "10424    158.239100\n",
              "10425    158.379253\n",
              "10426    158.508300\n",
              "10427    158.620600\n",
              "10428    158.716372\n",
              "Name: Close, Length: 10429, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ],
      "source": [
        "ma200=df.Close.rolling(200).mean()\n",
        "ma200"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 446
        },
        "id": "oRWzmBhS7b0R",
        "outputId": "6d93afe2-a141-4687-d821-c3acc62b890f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7f61cef65850>]"
            ]
          },
          "metadata": {},
          "execution_count": 11
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1080x504 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.figure(figsize=(15,7))\n",
        "plt.plot(df.Close)\n",
        "plt.plot(ma100,'r')\n",
        "plt.plot(ma200,'g')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9_aHgOP89Qzj",
        "outputId": "3d1dcf07-7faf-4e81-8fb4-2db90884a056"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(10429, 6)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ],
      "source": [
        "df.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "760JZlj7QTcU",
        "outputId": "8ae204bd-313e-4657-9a93-9f866beeded0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(7300,)\n",
            "(3129,)\n"
          ]
        }
      ],
      "source": [
        "# splitting and testing\n",
        "data_training=df['Close'][0:int(len(df)*0.70)]\n",
        "data_testing=df['Close'][int(len(df)*0.70):int(len(df))]\n",
        "print(data_training.shape)\n",
        "print(data_testing.shape)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FOWYTsjjRofH",
        "outputId": "4a4c42de-1443-40e1-fa45-65ae0ddd5a14"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00986213],\n",
              "       [0.00902876],\n",
              "       [0.00791748],\n",
              "       ...,\n",
              "       [0.97740741],\n",
              "       [0.98938541],\n",
              "       [1.        ]])"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ],
      "source": [
        "scaler=MinMaxScaler(feature_range=(0,1))\n",
        "data_training_array=scaler.fit_transform(data_training.values.reshape(-1,1))\n",
        "data_training_array"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "id": "jrImbJ0titn3"
      },
      "outputs": [],
      "source": [
        "x_train=[]         #previous data\n",
        "y_train=[]         #predicted data value\n",
        "\n",
        "for i in range(100,data_training.shape[0]):             #101th day dependent on previous 100 days\n",
        "  x_train.append(data_training_array[i-100:i])\n",
        "  y_train.append(data_training_array[i,0])\n",
        "x_train,y_train=np.array(x_train),np.array(y_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 54,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vAAhHBRUlN1m",
        "outputId": "647776ee-867d-4f39-9f30-46ec9a25f386"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7200, 100, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 54
        }
      ],
      "source": [
        "x_train.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 55,
      "metadata": {
        "id": "UjQB7lIh2jKg"
      },
      "outputs": [],
      "source": [
        "# ML Model\n",
        "from keras.layers import Dense, Dropout, LSTM # Keras models offer a simple, user-friendly way to define a neural network. It is a neural network API for Python that is tightly integrated with TensorFlow, which is used to build machine learning models\n",
        "# dense layer is a classic fully connected neural network layer : each input node is connected to each output node.\n",
        "# dropout layer is similar except that when the layer is used, the activations are set to zero for some random nodes. This is a way to prevent overfitting.\n",
        "# Long Short-Term Memory (LSTM) networks are a type of recurrent neural network capable of learning order dependence in sequence prediction problems.\n",
        "from keras.models import Sequential  #Sequential model is a linear stack of layers.\n",
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 56,
      "metadata": {
        "id": "esJG3uyb28Uc"
      },
      "outputs": [],
      "source": [
        "model = Sequential()  \n",
        "model.add(LSTM(units = 50, activation = 'relu', return_sequences = True, input_shape = (x_train.shape[1], 1)))  #layer1\n",
        "#activation function of a node defines the output of that node given an input or set of inputs.      \n",
        "#RELU: most commonly used activation function in deep learning models. The function returns 0 if it receives any negative input, but for any positive value x it returns that value back.\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(LSTM(units = 60, activation = 'relu', return_sequences = True))   # layer 2\n",
        "model.add(Dropout(0.3))\n",
        "\n",
        "model.add(LSTM(units = 80, activation = 'relu', return_sequences = True))   # layer 3\n",
        "model.add(Dropout(0.4))\n",
        "\n",
        "model.add(LSTM(units = 120, activation = 'relu'))  #layer 4\n",
        "model.add(Dropout(0.5))\n",
        "\n",
        "model.add(Dense(units = 1))    #dense layer combines all"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 57,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "f5SYf_b24R3L",
        "outputId": "947aaea7-ac80-4add-8087-5048f33867f6"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " lstm_4 (LSTM)               (None, 100, 50)           10400     \n",
            "                                                                 \n",
            " dropout_4 (Dropout)         (None, 100, 50)           0         \n",
            "                                                                 \n",
            " lstm_5 (LSTM)               (None, 100, 60)           26640     \n",
            "                                                                 \n",
            " dropout_5 (Dropout)         (None, 100, 60)           0         \n",
            "                                                                 \n",
            " lstm_6 (LSTM)               (None, 100, 80)           45120     \n",
            "                                                                 \n",
            " dropout_6 (Dropout)         (None, 100, 80)           0         \n",
            "                                                                 \n",
            " lstm_7 (LSTM)               (None, 120)               96480     \n",
            "                                                                 \n",
            " dropout_7 (Dropout)         (None, 120)               0         \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 1)                 121       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 178,761\n",
            "Trainable params: 178,761\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "model.summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 58,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IbO_LIO34cV4",
        "outputId": "29355148-361f-44fe-ad21-c6b6413d3a04"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "225/225 [==============================] - 52s 215ms/step - loss: 0.0057\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f6160c62950>"
            ]
          },
          "metadata": {},
          "execution_count": 58
        }
      ],
      "source": [
        "model.compile(optimizer = 'adam', loss = 'mean_squared_error')\n",
        "# Optimizer that implements the Adam algorithm. Adam optimization is a stochastic gradient descent method that is based on adaptive estimation of first-order and second-order moments.\n",
        "# Mean squared error: Difference between our model's predictions and the ground truth, square it, and average it out across the whole dataset.\n",
        "model.fit(x_train, y_train, epochs = 1)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.save('keras_model.h5')"
      ],
      "metadata": {
        "id": "EgmKjYvrSG40"
      },
      "execution_count": 59,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_testing.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JNbGONEVfeVn",
        "outputId": "8522adf7-69ba-4210-f2ac-19706aa223aa"
      },
      "execution_count": 60,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "7300    6.330312\n",
              "7301    6.298508\n",
              "7302    6.131839\n",
              "7303    6.113798\n",
              "7304    6.296062\n",
              "Name: Close, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 60
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "past_100_days=data_training.tail(100)"
      ],
      "metadata": {
        "id": "TZKA8FFwfxWo"
      },
      "execution_count": 61,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "final_df=past_100_days.append(data_testing,ignore_index=True)\n",
        "final_df.head()"
      ],
      "metadata": {
        "id": "vR8QOBOcgGqZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2f7d7f07-2a09-4f9b-de26-002d63aec261"
      },
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    4.355989\n",
              "1    4.341617\n",
              "2    4.355682\n",
              "3    4.367916\n",
              "4    4.281982\n",
              "Name: Close, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 62
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "input_data=scaler.fit_transform(final_df.values.reshape(-1,1))\n",
        "input_data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mBBc6eupGQaL",
        "outputId": "9067a403-f3da-4cbb-d1f8-747a8b1f78b9"
      },
      "execution_count": 71,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00121198],\n",
              "       [0.00113106],\n",
              "       [0.00121024],\n",
              "       ...,\n",
              "       [0.91810071],\n",
              "       [0.91354088],\n",
              "       [0.88747657]])"
            ]
          },
          "metadata": {},
          "execution_count": 71
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "input_data.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-LfDvbJLGu5T",
        "outputId": "c4aacac5-de77-4e7a-d56b-8d4eb68b55e8"
      },
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(3229, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_test=[]\n",
        "y_test=[]\n",
        "for i in range(100,input_data.shape[0]):\n",
        "  x_test.append(input_data[i-100:i])\n",
        "  y_test.append(input_data[i,0])"
      ],
      "metadata": {
        "id": "PETylHO9GxfH"
      },
      "execution_count": 80,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_test,y_test=np.array(x_test),np.array(y_test)\n",
        "print(x_test.shape)\n",
        "print(y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DT13gdUnHGLt",
        "outputId": "fff50238-9ac5-4509-8478-6be5d278729d"
      },
      "execution_count": 81,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(3129, 100, 1)\n",
            "(3129,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Making predictions\n",
        "\n",
        "y_predicted = model.predict(x_test)"
      ],
      "metadata": {
        "id": "9Q3_TMKUHSvc"
      },
      "execution_count": 83,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y_predicted.shape"
      ],
      "metadata": {
        "id": "43wO-vg2HeId",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9cc12828-cd6e-424e-a114-9ba1cdd71cbe"
      },
      "execution_count": 84,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(3129, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 84
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_test"
      ],
      "metadata": {
        "id": "tHVSwqGxHg_W",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "46088256-cab5-470a-86be-cda6c1c9131a"
      },
      "execution_count": 85,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.0123263 , 0.01214726, 0.01120901, ..., 0.91810071, 0.91354088,\n",
              "       0.88747657])"
            ]
          },
          "metadata": {},
          "execution_count": 85
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_predicted"
      ],
      "metadata": {
        "id": "kvpio3KYHil7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e4d85399-704a-4ae9-8741-f8b4311c924f"
      },
      "execution_count": 86,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.02251566],\n",
              "       [0.02251566],\n",
              "       [0.02251567],\n",
              "       ...,\n",
              "       [0.8668557 ],\n",
              "       [0.86746573],\n",
              "       [0.86763555]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 86
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "scaler.scale_"
      ],
      "metadata": {
        "id": "NUaLaYacHqHi",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ea08ce20-ddfb-4d52-bccb-b4a99c402e53"
      },
      "execution_count": 87,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.00562944])"
            ]
          },
          "metadata": {},
          "execution_count": 87
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "scale_factor=1/0.00562944\n",
        "y_predicted=y_predicted*scale_factor\n",
        "y_test=y_test*scale_factor"
      ],
      "metadata": {
        "id": "ZicfGhXDHucT"
      },
      "execution_count": 89,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(12,6))\n",
        "plt.plot(y_test,'b',label='Original Price')\n",
        "plt.plot(y_predicted,'r',label='Predicted price')\n",
        "plt.xlabel('Time')\n",
        "plt.ylabel('Price')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "yu5qIJjMHymQ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 388
        },
        "outputId": "61849038-4793-4eaa-8c80-12401eb30a89"
      },
      "execution_count": 90,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [],
      "name": "Stock trend prediction.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}