stock_price_prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "mount_file_id": "1PpjZkXi6YJFRMjsEp47fovdfoqwsnAdT",
      "authorship_tag": "ABX9TyPocpbqSWFYIVJccmNoHJbR",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/smth-27/Stock_Price_Prediction/blob/main/stock_price_prediction.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "0Ypy-HY5z2o0"
      },
      "outputs": [],
      "source": [
        "import math\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from google.colab import drive\n",
        "import io\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.metrics import r2_score\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, LSTM\n",
        "import matplotlib.pyplot as plt\n",
        "plt.style.use('fivethirtyeight')\n",
        "path = '/content/drive/MyDrive/dataset/1613615-Stock_Price_data_set.csv'"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(path)\n",
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "bKOOhI1w6H-w",
        "outputId": "02c50be9-e739-4724-8da2-43d5845fe381"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Date        Open        High         Low       Close   Adj Close  \\\n",
              "0     2018-02-05  262.000000  267.899994  250.029999  254.259995  254.259995   \n",
              "1     2018-02-06  247.699997  266.700012  245.000000  265.720001  265.720001   \n",
              "2     2018-02-07  266.579987  272.450012  264.329987  264.559998  264.559998   \n",
              "3     2018-02-08  267.079987  267.619995  250.000000  250.100006  250.100006   \n",
              "4     2018-02-09  253.850006  255.800003  236.110001  249.470001  249.470001   \n",
              "...          ...         ...         ...         ...         ...         ...   \n",
              "1004  2022-01-31  401.970001  427.700012  398.200012  427.140015  427.140015   \n",
              "1005  2022-02-01  432.959991  458.480011  425.540009  457.130005  457.130005   \n",
              "1006  2022-02-02  448.250000  451.980011  426.480011  429.480011  429.480011   \n",
              "1007  2022-02-03  421.440002  429.260010  404.279999  405.600006  405.600006   \n",
              "1008  2022-02-04  407.309998  412.769989  396.640015  410.170013  410.170013   \n",
              "\n",
              "        Volume  \n",
              "0     11896100  \n",
              "1     12595800  \n",
              "2      8981500  \n",
              "3      9306700  \n",
              "4     16906900  \n",
              "...        ...  \n",
              "1004  20047500  \n",
              "1005  22542300  \n",
              "1006  14346000  \n",
              "1007   9905200  \n",
              "1008   7782400  \n",
              "\n",
              "[1009 rows x 7 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-135cb9c3-5883-43c1-9292-5def3fcc1e5b\">\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>2018-02-05</td>\n",
              "      <td>262.000000</td>\n",
              "      <td>267.899994</td>\n",
              "      <td>250.029999</td>\n",
              "      <td>254.259995</td>\n",
              "      <td>254.259995</td>\n",
              "      <td>11896100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2018-02-06</td>\n",
              "      <td>247.699997</td>\n",
              "      <td>266.700012</td>\n",
              "      <td>245.000000</td>\n",
              "      <td>265.720001</td>\n",
              "      <td>265.720001</td>\n",
              "      <td>12595800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2018-02-07</td>\n",
              "      <td>266.579987</td>\n",
              "      <td>272.450012</td>\n",
              "      <td>264.329987</td>\n",
              "      <td>264.559998</td>\n",
              "      <td>264.559998</td>\n",
              "      <td>8981500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2018-02-08</td>\n",
              "      <td>267.079987</td>\n",
              "      <td>267.619995</td>\n",
              "      <td>250.000000</td>\n",
              "      <td>250.100006</td>\n",
              "      <td>250.100006</td>\n",
              "      <td>9306700</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2018-02-09</td>\n",
              "      <td>253.850006</td>\n",
              "      <td>255.800003</td>\n",
              "      <td>236.110001</td>\n",
              "      <td>249.470001</td>\n",
              "      <td>249.470001</td>\n",
              "      <td>16906900</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>1004</th>\n",
              "      <td>2022-01-31</td>\n",
              "      <td>401.970001</td>\n",
              "      <td>427.700012</td>\n",
              "      <td>398.200012</td>\n",
              "      <td>427.140015</td>\n",
              "      <td>427.140015</td>\n",
              "      <td>20047500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1005</th>\n",
              "      <td>2022-02-01</td>\n",
              "      <td>432.959991</td>\n",
              "      <td>458.480011</td>\n",
              "      <td>425.540009</td>\n",
              "      <td>457.130005</td>\n",
              "      <td>457.130005</td>\n",
              "      <td>22542300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1006</th>\n",
              "      <td>2022-02-02</td>\n",
              "      <td>448.250000</td>\n",
              "      <td>451.980011</td>\n",
              "      <td>426.480011</td>\n",
              "      <td>429.480011</td>\n",
              "      <td>429.480011</td>\n",
              "      <td>14346000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1007</th>\n",
              "      <td>2022-02-03</td>\n",
              "      <td>421.440002</td>\n",
              "      <td>429.260010</td>\n",
              "      <td>404.279999</td>\n",
              "      <td>405.600006</td>\n",
              "      <td>405.600006</td>\n",
              "      <td>9905200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1008</th>\n",
              "      <td>2022-02-04</td>\n",
              "      <td>407.309998</td>\n",
              "      <td>412.769989</td>\n",
              "      <td>396.640015</td>\n",
              "      <td>410.170013</td>\n",
              "      <td>410.170013</td>\n",
              "      <td>7782400</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1009 rows × 7 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-135cb9c3-5883-43c1-9292-5def3fcc1e5b')\"\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-135cb9c3-5883-43c1-9292-5def3fcc1e5b 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-135cb9c3-5883-43c1-9292-5def3fcc1e5b');\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
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WAH17-y56wAK",
        "outputId": "8f2860b8-8541-4fd8-e875-f827954d3e88"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1009, 7)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#closing price history\n",
        "plt.figure(figsize=(8,4))\n",
        "plt.title('Close Price History')\n",
        "plt.plot(df['Close'])\n",
        "plt.xlabel('Date',fontsize=18)\n",
        "plt.ylabel('Close Price',fontsize=18)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 325
        },
        "id": "xX7r7AlB67wx",
        "outputId": "6cc15f6e-9308-4ed1-8696-d546f99ee95c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 576x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = df.filter(['Close']) #new dataframe with only close cloumn\n",
        "dataset = data.values       #convert thedataframe into a numpy array\n",
        "training_data_len = math.ceil(len(dataset) * .8 )\n",
        "training_data_len"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CCU-wLkJ8Ejc",
        "outputId": "9a427eea-c002-41c5-d226-1f59d3acee6b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "808"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#scale the data\n",
        "scaler = MinMaxScaler(feature_range=(0,1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "scaled_data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "V5SjP-3b8wrS",
        "outputId": "83357404-4bd4-43c2-d0c5-fe2374478c16"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.04451626],\n",
              "       [0.06954849],\n",
              "       [0.06701469],\n",
              "       ...,\n",
              "       [0.4272515 ],\n",
              "       [0.37509011],\n",
              "       [0.38507243]])"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#create training dataset\n",
        "train_data = scaled_data[0:training_data_len, :]\n",
        "#spliting the data into two datasets\n",
        "x_train=[]\n",
        "y_train=[]\n",
        "for i in range(60, len(train_data)):\n",
        "  x_train.append(train_data[i-60:i,0])\n",
        "  y_train.append(train_data[i, 0])\n",
        "  if i<=61:\n",
        "    print(x_train)\n",
        "    print(y_train)\n",
        "    print()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sfzg2hYG9OyG",
        "outputId": "d0aa6cb7-9d39-464f-a600-fd1911e6c29e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[array([0.04451626, 0.06954849, 0.06701469, 0.03542955, 0.03405342,\n",
            "       0.05257641, 0.05327534, 0.0701601 , 0.10133021, 0.09750767,\n",
            "       0.09757319, 0.10301218, 0.09667768, 0.11369343, 0.13167034,\n",
            "       0.12391599, 0.12559796, 0.12343551, 0.14672022, 0.1771914 ,\n",
            "       0.19951508, 0.19064677, 0.18156003, 0.2131015 , 0.19095254,\n",
            "       0.17911361, 0.19149862, 0.19049385, 0.18472731, 0.17387127,\n",
            "       0.18265218, 0.18042421, 0.15906164, 0.14647998, 0.18887749,\n",
            "       0.1459339 , 0.11334393, 0.13426968, 0.10137394, 0.10875693,\n",
            "       0.12026823, 0.13125532, 0.12007165, 0.12243068, 0.14021101,\n",
            "       0.15244317, 0.16463161, 0.16987394, 0.16142066, 0.22319301,\n",
            "       0.21982915, 0.21585376, 0.20508505, 0.18525152, 0.15976057,\n",
            "       0.15700838, 0.17496343, 0.17011425, 0.17164323, 0.17347804])]\n",
            "[0.17360909661393864]\n",
            "\n",
            "[array([0.04451626, 0.06954849, 0.06701469, 0.03542955, 0.03405342,\n",
            "       0.05257641, 0.05327534, 0.0701601 , 0.10133021, 0.09750767,\n",
            "       0.09757319, 0.10301218, 0.09667768, 0.11369343, 0.13167034,\n",
            "       0.12391599, 0.12559796, 0.12343551, 0.14672022, 0.1771914 ,\n",
            "       0.19951508, 0.19064677, 0.18156003, 0.2131015 , 0.19095254,\n",
            "       0.17911361, 0.19149862, 0.19049385, 0.18472731, 0.17387127,\n",
            "       0.18265218, 0.18042421, 0.15906164, 0.14647998, 0.18887749,\n",
            "       0.1459339 , 0.11334393, 0.13426968, 0.10137394, 0.10875693,\n",
            "       0.12026823, 0.13125532, 0.12007165, 0.12243068, 0.14021101,\n",
            "       0.15244317, 0.16463161, 0.16987394, 0.16142066, 0.22319301,\n",
            "       0.21982915, 0.21585376, 0.20508505, 0.18525152, 0.15976057,\n",
            "       0.15700838, 0.17496343, 0.17011425, 0.17164323, 0.17347804]), array([0.06954849, 0.06701469, 0.03542955, 0.03405342, 0.05257641,\n",
            "       0.05327534, 0.0701601 , 0.10133021, 0.09750767, 0.09757319,\n",
            "       0.10301218, 0.09667768, 0.11369343, 0.13167034, 0.12391599,\n",
            "       0.12559796, 0.12343551, 0.14672022, 0.1771914 , 0.19951508,\n",
            "       0.19064677, 0.18156003, 0.2131015 , 0.19095254, 0.17911361,\n",
            "       0.19149862, 0.19049385, 0.18472731, 0.17387127, 0.18265218,\n",
            "       0.18042421, 0.15906164, 0.14647998, 0.18887749, 0.1459339 ,\n",
            "       0.11334393, 0.13426968, 0.10137394, 0.10875693, 0.12026823,\n",
            "       0.13125532, 0.12007165, 0.12243068, 0.14021101, 0.15244317,\n",
            "       0.16463161, 0.16987394, 0.16142066, 0.22319301, 0.21982915,\n",
            "       0.21585376, 0.20508505, 0.18525152, 0.15976057, 0.15700838,\n",
            "       0.17496343, 0.17011425, 0.17164323, 0.17347804, 0.1736091 ])]\n",
            "[0.17360909661393864, 0.16996133223364263]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#convert train datasets to numpy array\n",
        "x_train= np.array(x_train)\n",
        "y_train= np.array(y_train)\n",
        "x_train\n",
        "y_train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W4fkupnKNf4X",
        "outputId": "9a897f2f-ec37-4dd2-88e9-d8c9ceaa8d3d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.1736091 , 0.16996133, 0.18830954, 0.20178678, 0.20316291,\n",
              "       0.21061135, 0.20908237, 0.2022236 , 0.20674514, 0.20150281,\n",
              "       0.20600248, 0.19951508, 0.19724337, 0.21393155, 0.21349466,\n",
              "       0.24210916, 0.25209149, 0.25646011, 0.25305259, 0.26137482,\n",
              "       0.25713724, 0.27533254, 0.27943906, 0.28815444, 0.29175861,\n",
              "       0.27854348, 0.27673053, 0.27865273, 0.28385134, 0.31901878,\n",
              "       0.34728379, 0.34533979, 0.34188853, 0.37373584, 0.39946704,\n",
              "       0.39658373, 0.38708196, 0.32895744, 0.36152555, 0.34186674,\n",
              "       0.35285382, 0.34413837, 0.35888248, 0.34215064, 0.35934124,\n",
              "       0.38087852, 0.40429435, 0.39699876, 0.40359536, 0.39234616,\n",
              "       0.35368381, 0.36390644, 0.31803588, 0.30853411, 0.28472512,\n",
              "       0.27777896, 0.28129573, 0.26963151, 0.28175442, 0.28223497,\n",
              "       0.26502258, 0.22079026, 0.22622924, 0.22826063, 0.24162861,\n",
              "       0.23854872, 0.25565193, 0.25763959, 0.24842179, 0.25224434,\n",
              "       0.24462111, 0.23466065, 0.22631656, 0.20209255, 0.19344269,\n",
              "       0.18107948, 0.20499772, 0.22747425, 0.24149756, 0.22998626,\n",
              "       0.27290798, 0.28548958, 0.29403024, 0.29304734, 0.29946923,\n",
              "       0.29226096, 0.28334899, 0.23437668, 0.24590985, 0.25075902,\n",
              "       0.25016928, 0.26659529, 0.29721939, 0.29328759, 0.28544591,\n",
              "       0.25440685, 0.29219543, 0.29068825, 0.28719334, 0.27808479,\n",
              "       0.29647666, 0.2960835 , 0.31454097, 0.32072254, 0.3063498 ,\n",
              "       0.32229525, 0.3129246 , 0.31272795, 0.28345818, 0.25659117,\n",
              "       0.25167646, 0.26611473, 0.2009786 , 0.19051572, 0.23083811,\n",
              "       0.21679299, 0.24577879, 0.28575175, 0.24645592, 0.21578823,\n",
              "       0.20895132, 0.21685852, 0.14842398, 0.17253881, 0.14405536,\n",
              "       0.11131253, 0.11343132, 0.14831479, 0.18239008, 0.16430397,\n",
              "       0.1781525 , 0.16810465, 0.20449531, 0.18356962, 0.15200628,\n",
              "       0.13147376, 0.13219456, 0.11544092, 0.12271465, 0.11430503,\n",
              "       0.08020795, 0.07230075, 0.06170682, 0.05447675, 0.06017778,\n",
              "       0.07153623, 0.10652889, 0.1198532 , 0.11413032, 0.12323886,\n",
              "       0.0905397 , 0.1070313 , 0.06828162, 0.07824208, 0.06867478,\n",
              "       0.0895568 , 0.09204688, 0.07199491, 0.06317027, 0.08095061,\n",
              "       0.071842  , 0.0583211 , 0.02732573, 0.        , 0.04322752,\n",
              "       0.04737774, 0.04849169, 0.07378607, 0.07378607, 0.08151855,\n",
              "       0.13911885, 0.17793406, 0.1887027 , 0.18802557, 0.19829187,\n",
              "       0.22653501, 0.21637797, 0.26377757, 0.25667856, 0.26061029,\n",
              "       0.22983334, 0.19938402, 0.19245972, 0.20268235, 0.22753977,\n",
              "       0.2223193 , 0.20755333, 0.23324086, 0.23070705, 0.23147157,\n",
              "       0.2565693 , 0.26633318, 0.25842598, 0.2420873 , 0.24833447,\n",
              "       0.24431534, 0.27541993, 0.25750854, 0.27345406, 0.26864855,\n",
              "       0.27967936, 0.27528887, 0.26886699, 0.28208205, 0.28402612,\n",
              "       0.28634149, 0.28175442, 0.27133527, 0.26963151, 0.25591404,\n",
              "       0.26303485, 0.27463354, 0.25932156, 0.25276862, 0.27299531,\n",
              "       0.26733795, 0.27812845, 0.27290798, 0.27867453, 0.28299949,\n",
              "       0.27282059, 0.30873069, 0.3145191 , 0.27769163, 0.28909374,\n",
              "       0.27541993, 0.26100345, 0.26371198, 0.26797142, 0.29068825,\n",
              "       0.29234835, 0.2967825 , 0.29269785, 0.28747731, 0.27856534,\n",
              "       0.28577355, 0.28404799, 0.29219543, 0.25613248, 0.25117405,\n",
              "       0.27430591, 0.26399595, 0.27624998, 0.31336142, 0.32330008,\n",
              "       0.30656824, 0.29368075, 0.3079225 , 0.30132584, 0.29850813,\n",
              "       0.31657236, 0.31711844, 0.33015879, 0.31626659, 0.29833334,\n",
              "       0.28503089, 0.28149231, 0.27775716, 0.24328871, 0.24405317,\n",
              "       0.26454203, 0.27397827, 0.26336255, 0.24951395, 0.26296932,\n",
              "       0.27489571, 0.25846964, 0.2632315 , 0.26469495, 0.25187304,\n",
              "       0.25768332, 0.23896375, 0.22443809, 0.26106898, 0.26615846,\n",
              "       0.26921649, 0.2773858 , 0.25803282, 0.25641638, 0.24394398,\n",
              "       0.23929138, 0.23120947, 0.25499659, 0.26919462, 0.28317421,\n",
              "       0.2868657 , 0.29560295, 0.29960028, 0.27614072, 0.28029097,\n",
              "       0.29737224, 0.29147464, 0.30737643, 0.30918938, 0.32292872,\n",
              "       0.32037305, 0.31078395, 0.31901878, 0.32135601, 0.31807954,\n",
              "       0.30442759, 0.28990193, 0.28856946, 0.28081518, 0.19949321,\n",
              "       0.17740985, 0.1676241 , 0.16037217, 0.18361328, 0.2022236 ,\n",
              "       0.22258141, 0.21585376, 0.20106592, 0.19464403, 0.18702081,\n",
              "       0.18555729, 0.16109303, 0.16648828, 0.15379744, 0.17915727,\n",
              "       0.16393261, 0.16808279, 0.17125007, 0.14248265, 0.13516526,\n",
              "       0.15054277, 0.16491558, 0.14222054, 0.13964307, 0.13772086,\n",
              "       0.12572901, 0.13346149, 0.12483343, 0.1264498 , 0.13739323,\n",
              "       0.13077477, 0.12103275, 0.12590373, 0.12968261, 0.12295496,\n",
              "       0.1320635 , 0.1181931 , 0.11880471, 0.12009345, 0.13164848,\n",
              "       0.13195431, 0.14136869, 0.12599112, 0.11515695, 0.08053558,\n",
              "       0.06998538, 0.04523709, 0.06742971, 0.0642843 , 0.06378188,\n",
              "       0.07369867, 0.07797991, 0.07459425, 0.07485636, 0.0849916 ,\n",
              "       0.08863936, 0.08047006, 0.0735021 , 0.10178897, 0.10714049,\n",
              "       0.11281972, 0.1100238 , 0.11445795, 0.12990105, 0.09047418,\n",
              "       0.09648104, 0.07166728, 0.0816714 , 0.08217382, 0.09379437,\n",
              "       0.10480326, 0.10338347, 0.12575087, 0.11692623, 0.11561563,\n",
              "       0.12883069, 0.1182805 , 0.11950371, 0.12164436, 0.12601298,\n",
              "       0.131714  , 0.12697408, 0.10753365, 0.12175354, 0.13357068,\n",
              "       0.15004042, 0.15010594, 0.15569778, 0.16996133, 0.16731833,\n",
              "       0.17839275, 0.17170876, 0.1792228 , 0.17644874, 0.16624798,\n",
              "       0.15788209, 0.15386296, 0.15067382, 0.16048143, 0.1498875 ,\n",
              "       0.12939864, 0.14208949, 0.14101919, 0.14115025, 0.15362265,\n",
              "       0.1782399 , 0.18986039, 0.21480526, 0.22502783, 0.21672747,\n",
              "       0.21694591, 0.21570084, 0.20796835, 0.19534303, 0.19591097,\n",
              "       0.20954106, 0.20100039, 0.2226906 , 0.21159432, 0.23018284,\n",
              "       0.2223193 , 0.20788096, 0.22944018, 0.22893776, 0.22976781,\n",
              "       0.22878485, 0.23107841, 0.22767083, 0.20121884, 0.25276862,\n",
              "       0.26054477, 0.23809004, 0.25040953, 0.23870164, 0.24870576,\n",
              "       0.24291735, 0.27111683, 0.29516613, 0.29660778, 0.29066645,\n",
              "       0.29027322, 0.29966581, 0.30538869, 0.31919356, 0.32222972,\n",
              "       0.32004541, 0.33616565, 0.3326926 , 0.33227757, 0.31932462,\n",
              "       0.294489  , 0.27568203, 0.3175116 , 0.30106373, 0.29520979,\n",
              "       0.3214652 , 0.29464185, 0.32745026, 0.30340096, 0.29507874,\n",
              "       0.24597537, 0.28450667, 0.25346761, 0.17773748, 0.22371723,\n",
              "       0.14189291, 0.18756688, 0.17821803, 0.21439024, 0.21613766,\n",
              "       0.27607519, 0.26963151, 0.23701975, 0.28201653, 0.26919462,\n",
              "       0.2994255 , 0.30934229, 0.28439742, 0.29750329, 0.27932987,\n",
              "       0.31908431, 0.30230881, 0.299775  , 0.29890128, 0.3556934 ,\n",
              "       0.39245535, 0.4212883 , 0.44841749, 0.41300974, 0.44474779,\n",
              "       0.4367532 , 0.40964594, 0.42117911, 0.41744389, 0.40955855,\n",
              "       0.37122383, 0.38882945, 0.40621656, 0.39621237, 0.42434632,\n",
              "       0.41676676, 0.43769251, 0.44265087, 0.44051022, 0.45136626,\n",
              "       0.43236278, 0.44645155, 0.45448987, 0.48122583, 0.47770906,\n",
              "       0.47434526, 0.46698414, 0.44203927, 0.426902  , 0.39512021,\n",
              "       0.40630395, 0.39221511, 0.40595445, 0.41947535, 0.42251151,\n",
              "       0.41084729, 0.39415911, 0.40567048, 0.40543017, 0.43723375,\n",
              "       0.43817306, 0.41868896, 0.40232848, 0.41855791, 0.44177716,\n",
              "       0.46720252, 0.47178959, 0.4801992 , 0.51147857, 0.5075905 ,\n",
              "       0.48922042, 0.50682598, 0.45765709, 0.46604484, 0.48308251,\n",
              "       0.54992248, 0.53080975, 0.56776828, 0.56634849, 0.58736156,\n",
              "       0.59823946, 0.68773067, 0.63698914, 0.63563487, 0.6320963 ,\n",
              "       0.64111752, 0.56597712, 0.58655338, 0.5596645 , 0.55905289,\n",
              "       0.53231686, 0.5385859 , 0.5717874 , 0.55619145, 0.54738867,\n",
              "       0.55027191, 0.55699963, 0.57827481, 0.60234598, 0.58589804,\n",
              "       0.6011227 , 0.56977787, 0.54498591, 0.50905395, 0.527708  ,\n",
              "       0.54050804, 0.54345687, 0.54273608, 0.5635307 , 0.54749786,\n",
              "       0.57670211, 0.56449181, 0.55684672, 0.56071292, 0.6851096 ,\n",
              "       0.6386711 , 0.63347243, 0.64585744, 0.70481201, 0.69670829,\n",
              "       0.63753522, 0.61634736, 0.59662302, 0.5817042 , 0.53906645,\n",
              "       0.54203708, 0.52943362, 0.57253006, 0.54603434, 0.51619669,\n",
              "       0.51567241, 0.55365764, 0.56200172, 0.5170922 , 0.52248746,\n",
              "       0.54389376, 0.56086584, 0.56704748, 0.5813547 , 0.64137963,\n",
              "       0.58797317, 0.62639528, 0.59411108, 0.65699738, 0.65072841,\n",
              "       0.66743845, 0.66824664, 0.69943868, 0.67182894, 0.67289924,\n",
              "       0.6485441 , 0.64839118, 0.63681436, 0.55737093, 0.54902691,\n",
              "       0.55568903, 0.55560164, 0.55710882, 0.55123302, 0.59048511,\n",
              "       0.52829774, 0.54660228, 0.55337367, 0.57462705, 0.61134533,\n",
              "       0.61346405, 0.51685196, 0.53812714, 0.56110615, 0.5523907 ,\n",
              "       0.54380637, 0.53563706, 0.53897906, 0.54151287, 0.5478037 ,\n",
              "       0.55560164, 0.53021994, 0.54389376, 0.54852449, 0.56241668,\n",
              "       0.5609751 , 0.5912933 , 0.58867216, 0.57587206, 0.57759768,\n",
              "       0.61575769, 0.60894251, 0.56730959, 0.58367007, 0.58832266,\n",
              "       0.63026142, 0.62449493, 0.63552569, 0.6531531 , 0.65653876,\n",
              "       0.64443758, 0.64098647, 0.61291797, 0.61180395, 0.62305321,\n",
              "       0.64871888, 0.63500147, 0.67025617, 0.63122252, 0.62672284,\n",
              "       0.58235947, 0.60070774, 0.60400601, 0.57932331, 0.56872938,\n",
              "       0.59830499, 0.58316765, 0.57687689, 0.58515538, 0.76988276,\n",
              "       0.75568473, 0.72364077, 0.70531449, 0.71656362, 0.63214003,\n",
              "       0.66560358, 0.65203908, 0.66656468, 0.68648559, 0.66746032,\n",
              "       0.69522284, 0.69223035, 0.68596138, 0.71031652, 0.72018965,\n",
              "       0.70708378, 0.70474655, 0.70640664, 0.69343183, 0.68661665,\n",
              "       0.66914215, 0.65507531, 0.68209524, 0.69795323, 0.68329658,\n",
              "       0.66614965, 0.69190278, 0.685743  , 0.62650446, 0.60595008,\n",
              "       0.61709009, 0.56671978, 0.59535615, 0.59120597, 0.63165941,\n",
              "       0.62065053, 0.6255215 , 0.63377826, 0.63467377, 0.59175205,\n",
              "       0.60789408, 0.6317686 , 0.65793675, 0.62674471, 0.58753627,\n",
              "       0.59887286, 0.61176036, 0.61053715, 0.62860132, 0.66739473,\n",
              "       0.67012512, 0.67855666, 0.68392999, 0.70050898, 0.70210348,\n",
              "       0.69657724, 0.69865223, 0.6687054 , 0.68880096, 0.68294702,\n",
              "       0.70020314, 0.68956555, 0.60072954])"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_train= np.reshape(x_train, (x_train.shape[0],x_train.shape[1],1))\n",
        "x_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "695T0lRVPBL-",
        "outputId": "46d361ac-b0fd-4223-aa07-2bf3cf2a44ef"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(748, 60, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#LSTM model\n",
        "model = Sequential()\n",
        "model.add(LSTM(50,return_sequences=True,input_shape=(x_train.shape[1],1)))\n",
        "model.add(LSTM(50,return_sequences=False))\n",
        "model.add(Dense(25))\n",
        "model.add(Dense(1))"
      ],
      "metadata": {
        "id": "DLA1JU22PYny"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#compile the model\n",
        "model.compile(optimizer='adam',loss='mean_squared_error')"
      ],
      "metadata": {
        "id": "2UplNsUpRIqt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#train the model\n",
        "model.fit(x_train,y_train,batch_size=1,epochs=1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N-KHZAClRcU-",
        "outputId": "b87acf27-40fb-441a-8a66-d0c506921a4b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "748/748 [==============================] - 29s 34ms/step - loss: 0.0034\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f0f34245dc0>"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#create the test dataset\n",
        "#new array containing scaled values from 748 to 1009\n",
        "test_data = scaled_data[training_data_len - 60: , :]\n",
        "x_test = []\n",
        "y_test = dataset[training_data_len:, :]\n",
        "for i in range(60, len(test_data)):\n",
        "  x_test.append(test_data[i-60:i,0])"
      ],
      "metadata": {
        "id": "ZwTqDi3GR3aB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#convert data into numpy array\n",
        "x_test = np.array(x_test)"
      ],
      "metadata": {
        "id": "QWsemlIPS-8X"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#reshape the data\n",
        "x_test= np.reshape(x_test, (x_test.shape[0],x_test.shape[1],1))"
      ],
      "metadata": {
        "id": "_DXElio_TOE5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#get the models predicted price values\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)"
      ],
      "metadata": {
        "id": "f29_ItzVTzX8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "467abcec-5acc-4a41-950d-a006e62db19b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "7/7 [==============================] - 2s 25ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#RMS error\n",
        "rmse = np.sqrt(np.mean(predictions - y_test)**2)\n",
        "rmse"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "x9rD1RWMUKGZ",
        "outputId": "2fbbe776-fd11-4d00-982d-0ec80e372f95"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "17.792027541482042"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#plot the graph\n",
        "train = data[:training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions']= predictions"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1nRU4_i8UdrW",
        "outputId": "a119643d-3586-4970-8493-a56f13bcb674"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-18-dce1cd2ed6a8>:4: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  valid['Predictions']= predictions\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#visualize the data\n",
        "plt.figure(figsize=(8,4))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date',fontsize=18)\n",
        "plt.ylabel('Close Price',fontsize=18)\n",
        "plt.plot(train['Close'])\n",
        "plt.plot(valid[['Close','Predictions']])\n",
        "plt.legend(['Train','Val','Predictions'],loc='lower right')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 343
        },
        "id": "d3S8m7GTfvAs",
        "outputId": "52fb904b-4d2a-4294-f033-4f054bed6acc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7f0f34726eb0>"
            ]
          },
          "metadata": {},
          "execution_count": 19
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 576x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#valid and predicted prices\n",
        "valid"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "Nbtz83E7V5N-",
        "outputId": "46a9d060-2e66-4870-be83-45ea39fc29b1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           Close  Predictions\n",
              "808   508.779999   560.100769\n",
              "809   505.549988   554.037415\n",
              "810   510.299988   547.365051\n",
              "811   505.549988   541.651672\n",
              "812   506.519989   536.510925\n",
              "...          ...          ...\n",
              "1004  427.140015   425.877197\n",
              "1005  457.130005   420.703857\n",
              "1006  429.480011   423.526489\n",
              "1007  405.600006   427.368713\n",
              "1008  410.170013   428.851105\n",
              "\n",
              "[201 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fc8e9c54-2fd1-44d1-9262-ad2c45691eab\">\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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>808</th>\n",
              "      <td>508.779999</td>\n",
              "      <td>560.100769</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>809</th>\n",
              "      <td>505.549988</td>\n",
              "      <td>554.037415</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>810</th>\n",
              "      <td>510.299988</td>\n",
              "      <td>547.365051</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>811</th>\n",
              "      <td>505.549988</td>\n",
              "      <td>541.651672</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>812</th>\n",
              "      <td>506.519989</td>\n",
              "      <td>536.510925</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1004</th>\n",
              "      <td>427.140015</td>\n",
              "      <td>425.877197</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1005</th>\n",
              "      <td>457.130005</td>\n",
              "      <td>420.703857</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1006</th>\n",
              "      <td>429.480011</td>\n",
              "      <td>423.526489</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1007</th>\n",
              "      <td>405.600006</td>\n",
              "      <td>427.368713</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1008</th>\n",
              "      <td>410.170013</td>\n",
              "      <td>428.851105</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>201 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fc8e9c54-2fd1-44d1-9262-ad2c45691eab')\"\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-fc8e9c54-2fd1-44d1-9262-ad2c45691eab 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-fc8e9c54-2fd1-44d1-9262-ad2c45691eab');\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": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#quote\n",
        "stock_quote = pd.read_csv(path)\n",
        "#new dataframe\n",
        "new_df =stock_quote.filter(['Close'])\n",
        "#convert last 60 days closing price values into numpy array\n",
        "last_60_days = new_df[-60:].values\n",
        "last_60_days_scaled= scaler.transform(last_60_days)\n",
        "X_test= []\n",
        "X_test.append(last_60_days_scaled)\n",
        "X_test = np.array(X_test)\n",
        "X_test = np.reshape(X_test,(X_test.shape[0], X_test.shape[1],1))\n",
        "#predicted scaled price\n",
        "pred_price = model.predict(X_test)\n",
        "#undo scaling\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "#predicted price for the next day to the last day in the data set\n",
        "pred_price"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v3S59-AjWFcH",
        "outputId": "b92dfbc9-fca0-47ab-9f43-19f9b46b14ab"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 72ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[429.38016]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_test_prediction = model.predict(X_test)\n",
        "test_data_accuracy = r2_score(y_test, predictions)\n",
        "print(test_data_accuracy)"
      ],
      "metadata": {
        "id": "Sk0u9pp2cp8J",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "089a6f08-b5e4-49ab-a699-630b2dcfa264"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 52ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "ENHANCED VERSION\n",
        "improvements:\n",
        "\n",
        "Updated import statements for the latest TensorFlow library.\n",
        "\n",
        "Uses the Adam optimizer with a learning rate of 0.001 for better optimization.\n",
        "\n",
        "Uses model.fit instead of model.compile and model.fit separately.\n",
        "\n",
        "Uses the latest TensorFlow naming conventions for the optimizer.\n",
        "\n",
        "Adds comments to clarify the purpose of different code sections."
      ],
      "metadata": {
        "id": "OJXnKa2UY9K6"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import math\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.metrics import r2_score\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import LSTM, Dense\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "# Load the dataset\n",
        "path = '/content/drive/MyDrive/dataset/1613615-Stock_Price_data_set.csv'\n",
        "df = pd.read_csv(path)\n",
        "\n",
        "# Preprocess the data\n",
        "data = df.filter(['Close'])\n",
        "dataset = data.values\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "\n",
        "# Split the data into train and test sets\n",
        "training_data_len = math.ceil(len(dataset) * 0.8)\n",
        "train_data = scaled_data[:training_data_len, :]\n",
        "test_data = scaled_data[training_data_len - 60:, :]\n",
        "\n",
        "# Prepare the training data\n",
        "x_train, y_train = [], []\n",
        "for i in range(60, len(train_data)):\n",
        "    x_train.append(train_data[i - 60:i, 0])\n",
        "    y_train.append(train_data[i, 0])\n",
        "x_train, y_train = np.array(x_train), np.array(y_train)\n",
        "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
        "\n",
        "# Create and train the LSTM model\n",
        "model = Sequential()\n",
        "model.add(LSTM(50, return_sequences=True, input_shape=(x_train.shape[1], 1)))\n",
        "model.add(LSTM(50, return_sequences=False))\n",
        "model.add(Dense(25))\n",
        "model.add(Dense(1))\n",
        "\n",
        "model.compile(optimizer=Adam(learning_rate=0.001), loss='mean_squared_error')\n",
        "model.fit(x_train, y_train, batch_size=1, epochs=1)\n",
        "\n",
        "# Prepare the test data\n",
        "x_test, y_test = [], []\n",
        "for i in range(60, len(test_data)):\n",
        "    x_test.append(test_data[i - 60:i, 0])\n",
        "    y_test.append(dataset[training_data_len , 0])\n",
        "x_test = np.array(x_test)\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))\n",
        "\n",
        "# Make predictions on the test data\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)\n",
        "\n",
        "# Calculate RMSE\n",
        "rmse = np.sqrt(np.mean((predictions - y_test)**2))\n",
        "print(\"Root Mean Squared Error (RMSE):\", rmse)\n",
        "\n",
        "# Plot the predictions and actual prices\n",
        "train = data[:training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions'] = predictions\n",
        "\n",
        "plt.figure(figsize=(8, 4))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price', fontsize=18)\n",
        "plt.plot(train['Close'])\n",
        "plt.plot(valid[['Close', 'Predictions']])\n",
        "plt.legend(['Train', 'Val', 'Predictions'], loc='lower right')\n",
        "plt.show()\n",
        "\n",
        "# Predict the next day's closing price\n",
        "last_60_days = scaled_data[-60:]\n",
        "X_test = np.array([last_60_days])\n",
        "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
        "\n",
        "pred_price = model.predict(X_test)\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "print(\"Predicted price for the next day:\", pred_price[0][0])\n",
        "\n",
        "# Calculate R-squared for test data\n",
        "test_data_accuracy = r2_score(y_test, predictions)\n",
        "print(\"R-squared for test data:\", test_data_accuracy)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 654
        },
        "id": "Sg0DLM__Y8Wc",
        "outputId": "0add4c6b-8561-4fde-fd41-b363c462aaea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "748/748 [==============================] - 26s 25ms/step - loss: 0.0040\n",
            "7/7 [==============================] - 1s 13ms/step\n",
            "Root Mean Squared Error (RMSE): 83.93176572469822\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-2-eaefe3564aa2>:63: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  valid['Predictions'] = predictions\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 22ms/step\n",
            "Predicted price for the next day: 416.8009\n",
            "R-squared for test data: -2.1801799326949178e+30\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "stock_quote = pd.read_csv(path)\n",
        "#new dataframe\n",
        "new_df =stock_quote.filter(['Close'])\n",
        "#convert last 60 days closing price values into numpy array\n",
        "last_60_days = new_df[-60:].values\n",
        "last_60_days_scaled= scaler.transform(last_60_days)\n",
        "X_test= []\n",
        "X_test.append(last_60_days_scaled)\n",
        "X_test = np.array(X_test)\n",
        "X_test = np.reshape(X_test,(X_test.shape[0], X_test.shape[1],1))\n",
        "#predicted scaled price\n",
        "pred_price = model.predict(X_test)\n",
        "#undo scaling\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "#predicted price for the next day to the last day in the data set\n",
        "pred_price"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "duy9IoQrtA_W",
        "outputId": "44910b83-96cc-4b2b-ba5f-d09745adb5ee"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 29ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[419.191]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import yfinance as yf\n",
        "\n",
        "# Fetch historical data for AAPL\n",
        "df = yf.download('AAPL', start='2010-01-01', end='2023-05-28')\n",
        "\n",
        "# Save the data to a CSV file\n",
        "df.to_csv('AAPL_Stock_Price.csv')\n",
        "# Preprocess the data\n",
        "data = df.filter(['Close'])\n",
        "dataset = data.values\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "\n",
        "# Split the data into train and test sets\n",
        "training_data_len = math.ceil(len(dataset) * 0.8)\n",
        "train_data = scaled_data[:training_data_len, :]\n",
        "test_data = scaled_data[training_data_len - 60:, :]\n",
        "\n",
        "# Prepare the training data\n",
        "x_train, y_train = [], []\n",
        "for i in range(60, len(train_data)):\n",
        "    x_train.append(train_data[i - 60:i, 0])\n",
        "    y_train.append(train_data[i, 0])\n",
        "x_train, y_train = np.array(x_train), np.array(y_train)\n",
        "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
        "\n",
        "# Create and train the LSTM model\n",
        "model = Sequential()\n",
        "model.add(LSTM(50, return_sequences=True, input_shape=(x_train.shape[1], 1)))\n",
        "model.add(LSTM(50, return_sequences=False))\n",
        "model.add(Dense(25))\n",
        "model.add(Dense(1))\n",
        "\n",
        "model.compile(optimizer=Adam(learning_rate=0.001), loss='mean_squared_error')\n",
        "model.fit(x_train, y_train, batch_size=1, epochs=1)\n",
        "\n",
        "# Prepare the test data\n",
        "x_test, y_test = [], []\n",
        "for i in range(60, len(test_data)):\n",
        "    x_test.append(test_data[i - 60:i, 0])\n",
        "    y_test.append(dataset[training_data_len , 0])\n",
        "x_test = np.array(x_test)\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))\n",
        "\n",
        "# Make predictions on the test data\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)\n",
        "\n",
        "# Calculate RMSE\n",
        "rmse = np.sqrt(np.mean((predictions - y_test)**2))\n",
        "print(\"Root Mean Squared Error (RMSE):\", rmse)\n",
        "\n",
        "# Plot the predictions and actual prices\n",
        "train = data[:training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions'] = predictions\n",
        "\n",
        "plt.figure(figsize=(8, 4))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price', fontsize=18)\n",
        "plt.plot(train['Close'])\n",
        "plt.plot(valid[['Close', 'Predictions']])\n",
        "plt.legend(['Train', 'Val', 'Predictions'], loc='lower right')\n",
        "plt.show()\n",
        "\n",
        "# Predict the next day's closing price\n",
        "last_60_days = scaled_data[-60:]\n",
        "X_test = np.array([last_60_days])\n",
        "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
        "\n",
        "pred_price = model.predict(X_test)\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "print(\"Predicted price for the next day:\", pred_price[0][0])\n",
        "\n",
        "# Calculate R-squared for test data\n",
        "test_data_accuracy = r2_score(y_test, predictions)\n",
        "print(\"R-squared for test data:\", test_data_accuracy)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 672
        },
        "id": "PatTLRg2qDQ0",
        "outputId": "f3d1a51f-1879-4080-d1be-f0b540378ab9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[*********************100%***********************]  1 of 1 completed\n",
            "2639/2639 [==============================] - 67s 25ms/step - loss: 5.1810e-04\n",
            "22/22 [==============================] - 1s 14ms/step\n",
            "Root Mean Squared Error (RMSE): 35.68893258884714\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-3-519e2804a08b>:56: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  valid['Predictions'] = predictions\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 25ms/step\n",
            "Predicted price for the next day: 161.60358\n",
            "R-squared for test data: 0.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 455
        },
        "id": "hOzxbGWZsgQW",
        "outputId": "1b87e7d8-1e26-42fa-8092-9e1eedfa4ef1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  Open        High         Low       Close   Adj Close  \\\n",
              "Date                                                                     \n",
              "2010-01-04    7.622500    7.660714    7.585000    7.643214    6.496294   \n",
              "2010-01-05    7.664286    7.699643    7.616071    7.656429    6.507526   \n",
              "2010-01-06    7.656429    7.686786    7.526786    7.534643    6.404014   \n",
              "2010-01-07    7.562500    7.571429    7.466071    7.520714    6.392176   \n",
              "2010-01-08    7.510714    7.571429    7.466429    7.570714    6.434672   \n",
              "...                ...         ...         ...         ...         ...   \n",
              "2023-05-22  173.979996  174.710007  173.449997  174.199997  174.199997   \n",
              "2023-05-23  173.130005  173.380005  171.279999  171.559998  171.559998   \n",
              "2023-05-24  171.089996  172.419998  170.520004  171.839996  171.839996   \n",
              "2023-05-25  172.410004  173.899994  171.690002  172.990005  172.990005   \n",
              "2023-05-26  173.320007  175.770004  173.110001  175.429993  175.429993   \n",
              "\n",
              "               Volume  \n",
              "Date                   \n",
              "2010-01-04  493729600  \n",
              "2010-01-05  601904800  \n",
              "2010-01-06  552160000  \n",
              "2010-01-07  477131200  \n",
              "2010-01-08  447610800  \n",
              "...               ...  \n",
              "2023-05-22   43570900  \n",
              "2023-05-23   50747300  \n",
              "2023-05-24   45143500  \n",
              "2023-05-25   56058300  \n",
              "2023-05-26   54835000  \n",
              "\n",
              "[3373 rows x 6 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-68e64eca-6b97-4a99-95be-f931d002b3fb\">\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>Adj Close</th>\n",
              "      <th>Volume</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2010-01-04</th>\n",
              "      <td>7.622500</td>\n",
              "      <td>7.660714</td>\n",
              "      <td>7.585000</td>\n",
              "      <td>7.643214</td>\n",
              "      <td>6.496294</td>\n",
              "      <td>493729600</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-01-05</th>\n",
              "      <td>7.664286</td>\n",
              "      <td>7.699643</td>\n",
              "      <td>7.616071</td>\n",
              "      <td>7.656429</td>\n",
              "      <td>6.507526</td>\n",
              "      <td>601904800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-01-06</th>\n",
              "      <td>7.656429</td>\n",
              "      <td>7.686786</td>\n",
              "      <td>7.526786</td>\n",
              "      <td>7.534643</td>\n",
              "      <td>6.404014</td>\n",
              "      <td>552160000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-01-07</th>\n",
              "      <td>7.562500</td>\n",
              "      <td>7.571429</td>\n",
              "      <td>7.466071</td>\n",
              "      <td>7.520714</td>\n",
              "      <td>6.392176</td>\n",
              "      <td>477131200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-01-08</th>\n",
              "      <td>7.510714</td>\n",
              "      <td>7.571429</td>\n",
              "      <td>7.466429</td>\n",
              "      <td>7.570714</td>\n",
              "      <td>6.434672</td>\n",
              "      <td>447610800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-05-22</th>\n",
              "      <td>173.979996</td>\n",
              "      <td>174.710007</td>\n",
              "      <td>173.449997</td>\n",
              "      <td>174.199997</td>\n",
              "      <td>174.199997</td>\n",
              "      <td>43570900</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-05-23</th>\n",
              "      <td>173.130005</td>\n",
              "      <td>173.380005</td>\n",
              "      <td>171.279999</td>\n",
              "      <td>171.559998</td>\n",
              "      <td>171.559998</td>\n",
              "      <td>50747300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-05-24</th>\n",
              "      <td>171.089996</td>\n",
              "      <td>172.419998</td>\n",
              "      <td>170.520004</td>\n",
              "      <td>171.839996</td>\n",
              "      <td>171.839996</td>\n",
              "      <td>45143500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-05-25</th>\n",
              "      <td>172.410004</td>\n",
              "      <td>173.899994</td>\n",
              "      <td>171.690002</td>\n",
              "      <td>172.990005</td>\n",
              "      <td>172.990005</td>\n",
              "      <td>56058300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2023-05-26</th>\n",
              "      <td>173.320007</td>\n",
              "      <td>175.770004</td>\n",
              "      <td>173.110001</td>\n",
              "      <td>175.429993</td>\n",
              "      <td>175.429993</td>\n",
              "      <td>54835000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>3373 rows × 6 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-68e64eca-6b97-4a99-95be-f931d002b3fb')\"\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-68e64eca-6b97-4a99-95be-f931d002b3fb 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-68e64eca-6b97-4a99-95be-f931d002b3fb');\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
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RXtq2Ew_w-DJ",
        "outputId": "1fd83939-ef22-4c5b-b795-98049b372fa1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(3373, 6)"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#closing price history\n",
        "plt.figure(figsize=(8,4))\n",
        "plt.title('Close Price History')\n",
        "plt.plot(df['Close'])\n",
        "plt.xlabel('Date',fontsize=18)\n",
        "plt.ylabel('Close Price',fontsize=18)\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "IGbGUF1pxE1y",
        "outputId": "a3809cc8-a2b0-42f5-ddc6-6c964eb19f45",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 420
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import math\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.metrics import r2_score\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, LSTM\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.style.use('fivethirtyeight')\n",
        "\n",
        "# Load the dataset\n",
        "path = 'AAPL_Stock_Price.csv'\n",
        "df = pd.read_csv(path)\n",
        "\n",
        "# Select the 'Close' column as the target variable\n",
        "data = df.filter(['Close'])\n",
        "\n",
        "# Convert the dataframe to a numpy array\n",
        "dataset = data.values\n",
        "\n",
        "# Scale the data\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "\n",
        "# Create training dataset\n",
        "training_data_len = math.ceil(len(dataset) * 0.8)\n",
        "train_data = scaled_data[0:training_data_len, :]\n",
        "\n",
        "# Split the data into input (x) and output (y) sets\n",
        "x_train = []\n",
        "y_train = []\n",
        "for i in range(60, len(train_data)):\n",
        "    x_train.append(train_data[i-60:i, 0])\n",
        "    y_train.append(train_data[i, 0])\n",
        "\n",
        "# Convert the x_train and y_train to numpy arrays\n",
        "x_train = np.array(x_train)\n",
        "y_train = np.array(y_train)\n",
        "\n",
        "# Reshape the data for LSTM model (input shape [samples, time steps, features])\n",
        "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
        "\n",
        "# Create the LSTM model\n",
        "model = Sequential()\n",
        "model.add(LSTM(50, return_sequences=True, input_shape=(x_train.shape[1], 1)))\n",
        "model.add(LSTM(50, return_sequences=False))\n",
        "model.add(Dense(25))\n",
        "model.add(Dense(1))\n",
        "\n",
        "# Compile the model\n",
        "model.compile(optimizer='adam', loss='mean_squared_error')\n",
        "\n",
        "# Train the model\n",
        "model.fit(x_train, y_train, batch_size=1, epochs=10)\n",
        "\n",
        "# Prepare the test dataset\n",
        "test_data = scaled_data[training_data_len - 60:, :]\n",
        "x_test = []\n",
        "y_test = dataset[training_data_len:, :]\n",
        "for i in range(60, len(test_data)):\n",
        "    x_test.append(test_data[i-60:i, 0])\n",
        "\n",
        "# Convert the test data to numpy array and reshape\n",
        "x_test = np.array(x_test)\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))\n",
        "\n",
        "# Get the model's predicted price values\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)\n",
        "\n",
        "# Calculate the RMSE\n",
        "rmse = np.sqrt(np.mean((predictions - y_test) ** 2))\n",
        "print(\"Root Mean Squared Error (RMSE):\", rmse)\n",
        "\n",
        "# Plot the graph\n",
        "train = data[:training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions'] = predictions\n",
        "\n",
        "plt.figure(figsize=(8, 4))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price', fontsize=18)\n",
        "plt.plot(train['Close'],linewidth = '1')\n",
        "plt.plot(valid[['Close', 'Predictions']],linewidth = '1')\n",
        "plt.legend(['Train', 'Val', 'Predictions'], loc='lower right')\n",
        "plt.show()\n",
        "\n",
        "# Predict the next day's closing price\n",
        "last_60_days = scaled_data[-60:]\n",
        "X_test = np.array([last_60_days])\n",
        "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
        "\n",
        "pred_price = model.predict(X_test)\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "print(\"Predicted price for the next day:\", pred_price[0][0])\n",
        "\n",
        "# Evaluate the model on the test data\n",
        "test_data_accuracy = r2_score(y_test, predictions)\n",
        "print(\"Test Data Accuracy (R-squared):\", test_data_accuracy)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "r-nWpOGAtnX1",
        "outputId": "fcbcb023-ae3d-4dbc-d6e9-752161d0050d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "2639/2639 [==============================] - 112s 41ms/step - loss: 3.9189e-04\n",
            "Epoch 2/10\n",
            "2639/2639 [==============================] - 100s 38ms/step - loss: 1.9015e-04\n",
            "Epoch 3/10\n",
            "2639/2639 [==============================] - 102s 39ms/step - loss: 1.5462e-04\n",
            "Epoch 4/10\n",
            "2639/2639 [==============================] - 101s 38ms/step - loss: 1.2974e-04\n",
            "Epoch 5/10\n",
            "2639/2639 [==============================] - 103s 39ms/step - loss: 1.4042e-04\n",
            "Epoch 6/10\n",
            "2639/2639 [==============================] - 105s 40ms/step - loss: 9.3847e-05\n",
            "Epoch 7/10\n",
            "2639/2639 [==============================] - 109s 41ms/step - loss: 1.0829e-04\n",
            "Epoch 8/10\n",
            "2639/2639 [==============================] - 108s 41ms/step - loss: 8.7658e-05\n",
            "Epoch 9/10\n",
            "2639/2639 [==============================] - 108s 41ms/step - loss: 7.7999e-05\n",
            "Epoch 10/10\n",
            "2639/2639 [==============================] - 110s 42ms/step - loss: 7.1715e-05\n",
            "22/22 [==============================] - 1s 22ms/step\n",
            "Root Mean Squared Error (RMSE): 5.003868841515291\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-4-97f0b22d7a04>:79: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  valid['Predictions'] = predictions\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 35ms/step\n",
            "Predicted price for the next day: 178.63593\n",
            "Test Data Accuracy (R-squared): 0.9160845714484847\n"
          ]
        }
      ]
    }
  ]
}