Stock_Price_prediction_using_LSTM.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Ruchir1218/Portfolio_Projects/blob/main/Stock_Price_prediction_using_LSTM.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_qTK4Ajv3qRz"
      },
      "source": [
        "In this Colab, we will use a keras Long Short-Term Memory (LSTM) model to predict the stock price of Tata Global Beverages\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rs-XEsB86weU"
      },
      "source": [
        "Here are some imports we need to make: numpy for scientific computation, matplotlib for graphing, and pandas for manipulating data."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2SoQJk5BYOas"
      },
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BD3hdApP7gNi"
      },
      "source": [
        "Load training data set with the \"Open\" and \"High\" columns to use in our modeling."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VU6ve06iDV5Q"
      },
      "source": [
        "url = 'https://raw.githubusercontent.com/mwitiderrick/stockprice/master/NSE-TATAGLOBAL.csv'\n",
        "dataset_train = pd.read_csv(url)\n",
        "training_set = dataset_train.iloc[:, 1:2].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RsLbMJ1072EY"
      },
      "source": [
        "Let's take a look at the first five rows of our dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AqiQMcfCLh6K",
        "outputId": "d4eafdac-9c79-4e59-f205-9abd09998cb6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "dataset_train.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Date</th>\n",
              "      <th>Open</th>\n",
              "      <th>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Last</th>\n",
              "      <th>Close</th>\n",
              "      <th>Total Trade Quantity</th>\n",
              "      <th>Turnover (Lacs)</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2018-09-28</td>\n",
              "      <td>234.05</td>\n",
              "      <td>235.95</td>\n",
              "      <td>230.20</td>\n",
              "      <td>233.50</td>\n",
              "      <td>233.75</td>\n",
              "      <td>3069914</td>\n",
              "      <td>7162.35</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2018-09-27</td>\n",
              "      <td>234.55</td>\n",
              "      <td>236.80</td>\n",
              "      <td>231.10</td>\n",
              "      <td>233.80</td>\n",
              "      <td>233.25</td>\n",
              "      <td>5082859</td>\n",
              "      <td>11859.95</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2018-09-26</td>\n",
              "      <td>240.00</td>\n",
              "      <td>240.00</td>\n",
              "      <td>232.50</td>\n",
              "      <td>235.00</td>\n",
              "      <td>234.25</td>\n",
              "      <td>2240909</td>\n",
              "      <td>5248.60</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2018-09-25</td>\n",
              "      <td>233.30</td>\n",
              "      <td>236.75</td>\n",
              "      <td>232.00</td>\n",
              "      <td>236.25</td>\n",
              "      <td>236.10</td>\n",
              "      <td>2349368</td>\n",
              "      <td>5503.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2018-09-24</td>\n",
              "      <td>233.55</td>\n",
              "      <td>239.20</td>\n",
              "      <td>230.75</td>\n",
              "      <td>234.00</td>\n",
              "      <td>233.30</td>\n",
              "      <td>3423509</td>\n",
              "      <td>7999.55</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         Date    Open    High  ...   Close  Total Trade Quantity  Turnover (Lacs)\n",
              "0  2018-09-28  234.05  235.95  ...  233.75               3069914          7162.35\n",
              "1  2018-09-27  234.55  236.80  ...  233.25               5082859         11859.95\n",
              "2  2018-09-26  240.00  240.00  ...  234.25               2240909          5248.60\n",
              "3  2018-09-25  233.30  236.75  ...  236.10               2349368          5503.90\n",
              "4  2018-09-24  233.55  239.20  ...  233.30               3423509          7999.55\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ii6nZaDI7-20"
      },
      "source": [
        "Import MinMaxScaler from scikit-learn to scale our dataset into numbers between 0 and 1"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ub32hsA4MIXz"
      },
      "source": [
        "from sklearn.preprocessing import MinMaxScaler\n",
        "sc = MinMaxScaler(feature_range=(0,1))\n",
        "training_set_scaled = sc.fit_transform(training_set)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "aqze-4Is8Rb_"
      },
      "source": [
        "We want our data to be in the form of a 3D array for our LSTM model. First, we create data in 60 timesteps and convert it into an array using NumPy. Then, we convert the data into a 3D array with X_train samples, 60 timestamps, and one feature at each step."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qo7K06T2Mi_e"
      },
      "source": [
        "X_train = []\n",
        "y_train = []\n",
        "for i in range(60, 2035):\n",
        "    X_train.append(training_set_scaled[i-60:i, 0])\n",
        "    y_train.append(training_set_scaled[i, 0])\n",
        "X_train, y_train = np.array(X_train), np.array(y_train)\n",
        "\n",
        "X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "anIlTzKO-r74"
      },
      "source": [
        "Make the necessary imports from keras"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TP9GVtb9Q-C9"
      },
      "source": [
        "from keras.models import Sequential\n",
        "from keras.layers import LSTM\n",
        "from keras.layers import Dropout\n",
        "from keras.layers import Dense"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hJrFWnOd-x2t"
      },
      "source": [
        "Add LSTM layer along with dropout layers to prevent overfitting. After that, we add a Dense layer that specifies a one unit output. Next, we compile the model using the adam optimizer and set the loss as the mean_squarred_error"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CMKVOwBnRcOc",
        "outputId": "56b2022c-7ea4-4bf0-9f21-8b0a22d8c52a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "model = Sequential()\n",
        "\n",
        "model.add(LSTM(units=50,return_sequences=True,input_shape=(X_train.shape[1], 1)))\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(LSTM(units=50,return_sequences=True))\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(LSTM(units=50,return_sequences=True))\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(LSTM(units=50))\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(Dense(units=1))\n",
        "\n",
        "model.compile(optimizer='adam',loss='mean_squared_error')\n",
        "\n",
        "model.fit(X_train,y_train,epochs=100,batch_size=32)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "1975/1975 [==============================] - 16s 8ms/step - loss: 0.0142\n",
            "Epoch 2/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0032\n",
            "Epoch 3/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0031\n",
            "Epoch 4/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0024\n",
            "Epoch 5/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0026\n",
            "Epoch 6/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0023\n",
            "Epoch 7/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0020\n",
            "Epoch 8/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0019\n",
            "Epoch 9/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0024\n",
            "Epoch 10/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0020\n",
            "Epoch 11/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0020\n",
            "Epoch 12/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0019\n",
            "Epoch 13/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0018\n",
            "Epoch 14/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0018\n",
            "Epoch 15/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0016\n",
            "Epoch 16/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0013\n",
            "Epoch 17/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0016\n",
            "Epoch 18/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0013\n",
            "Epoch 19/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0015\n",
            "Epoch 20/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0015\n",
            "Epoch 21/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0013\n",
            "Epoch 22/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0015\n",
            "Epoch 23/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0013\n",
            "Epoch 24/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0012\n",
            "Epoch 25/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0013\n",
            "Epoch 26/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0016\n",
            "Epoch 27/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0012\n",
            "Epoch 28/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0013\n",
            "Epoch 29/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0012\n",
            "Epoch 30/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0010\n",
            "Epoch 31/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0012\n",
            "Epoch 32/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0012\n",
            "Epoch 33/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0011\n",
            "Epoch 34/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0011\n",
            "Epoch 35/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 0.0011\n",
            "Epoch 36/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0011\n",
            "Epoch 37/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0012\n",
            "Epoch 38/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 0.0010\n",
            "Epoch 39/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.9825e-04\n",
            "Epoch 40/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 0.0010\n",
            "Epoch 41/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.9635e-04\n",
            "Epoch 42/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.2451e-04\n",
            "Epoch 43/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.5933e-04\n",
            "Epoch 44/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 9.2699e-04\n",
            "Epoch 45/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 8.2947e-04\n",
            "Epoch 46/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 8.2260e-04\n",
            "Epoch 47/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 9.0822e-04\n",
            "Epoch 48/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 8.6241e-04\n",
            "Epoch 49/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 8.8776e-04\n",
            "Epoch 50/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 8.1270e-04\n",
            "Epoch 51/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.7384e-04\n",
            "Epoch 52/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.4085e-04\n",
            "Epoch 53/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 9.4244e-04\n",
            "Epoch 54/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.8353e-04\n",
            "Epoch 55/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 8.6989e-04\n",
            "Epoch 56/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 7.8139e-04\n",
            "Epoch 57/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 8.3654e-04\n",
            "Epoch 58/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.9018e-04\n",
            "Epoch 59/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.5839e-04\n",
            "Epoch 60/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.1182e-04\n",
            "Epoch 61/100\n",
            "1975/1975 [==============================] - 11s 6ms/step - loss: 7.1238e-04\n",
            "Epoch 62/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.8813e-04\n",
            "Epoch 63/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.6849e-04\n",
            "Epoch 64/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.9854e-04\n",
            "Epoch 65/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 6.5454e-04\n",
            "Epoch 66/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 9.7882e-04\n",
            "Epoch 67/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 7.4597e-04\n",
            "Epoch 68/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.5262e-04\n",
            "Epoch 69/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.3974e-04\n",
            "Epoch 70/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.2937e-04\n",
            "Epoch 71/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 7.1008e-04\n",
            "Epoch 72/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 8.3312e-04\n",
            "Epoch 73/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.5148e-04\n",
            "Epoch 74/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 8.7905e-04\n",
            "Epoch 75/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 6.8884e-04\n",
            "Epoch 76/100\n",
            "1975/1975 [==============================] - 14s 7ms/step - loss: 6.5543e-04\n",
            "Epoch 77/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 8.0628e-04\n",
            "Epoch 78/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 6.6255e-04\n",
            "Epoch 79/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 5.8123e-04\n",
            "Epoch 80/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.0392e-04\n",
            "Epoch 81/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.2067e-04\n",
            "Epoch 82/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.8039e-04\n",
            "Epoch 83/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.6438e-04\n",
            "Epoch 84/100\n",
            "1975/1975 [==============================] - 14s 7ms/step - loss: 7.1402e-04\n",
            "Epoch 85/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.0351e-04\n",
            "Epoch 86/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.7213e-04\n",
            "Epoch 87/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.4522e-04\n",
            "Epoch 88/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 7.4621e-04\n",
            "Epoch 89/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 5.6065e-04\n",
            "Epoch 90/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 7.2136e-04\n",
            "Epoch 91/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.8760e-04\n",
            "Epoch 92/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.2799e-04\n",
            "Epoch 93/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.5257e-04\n",
            "Epoch 94/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.6454e-04\n",
            "Epoch 95/100\n",
            "1975/1975 [==============================] - 13s 6ms/step - loss: 6.3161e-04\n",
            "Epoch 96/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 6.4054e-04\n",
            "Epoch 97/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 6.9562e-04\n",
            "Epoch 98/100\n",
            "1975/1975 [==============================] - 13s 7ms/step - loss: 7.1236e-04\n",
            "Epoch 99/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.2855e-04\n",
            "Epoch 100/100\n",
            "1975/1975 [==============================] - 12s 6ms/step - loss: 6.2628e-04\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7fabaf58bf60>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "N7_w_7x-A44v"
      },
      "source": [
        "Import the test set for the model to make predictions on"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ns2TngWrUaz5"
      },
      "source": [
        "url = 'https://raw.githubusercontent.com/mwitiderrick/stockprice/master/tatatest.csv'\n",
        "dataset_test = pd.read_csv(url)\n",
        "real_stock_price = dataset_test.iloc[:, 1:2].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WXGKvoo6BAyd"
      },
      "source": [
        "Before predicting future stock prices, we have to manipulate the training set; we merge the training set and the test set on the 0 axis, set the time step to 60, use minmaxscaler, and reshape the dataset as done previously. After making predictions, we use inverse_transform to get back the stock prices in normal readable format.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pBbdst_BV_PB"
      },
      "source": [
        "dataset_total = pd.concat((dataset_train['Open'], dataset_test['Open']), axis = 0)\n",
        "inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values\n",
        "inputs = inputs.reshape(-1,1)\n",
        "inputs = sc.transform(inputs)\n",
        "X_test = []\n",
        "for i in range(60, 76):\n",
        "    X_test.append(inputs[i-60:i, 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",
        "predicted_stock_price = model.predict(X_test)\n",
        "predicted_stock_price = sc.inverse_transform(predicted_stock_price)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BAj_a3n0B3nz"
      },
      "source": [
        "Plot our predicted stock prices and the actual stock price"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "czWvnIANYSqI",
        "outputId": "253ea65c-9b91-4812-c75e-605d2199b783",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 295
        }
      },
      "source": [
        "plt.plot(real_stock_price, color = 'black', label = 'TATA Stock Price')\n",
        "plt.plot(predicted_stock_price, color = 'green', label = 'Predicted TATA Stock Price')\n",
        "plt.title('TATA Stock Price Prediction')\n",
        "plt.xlabel('Time')\n",
        "plt.ylabel('TATA Stock Price')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}