test-LSTM.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "LSTM.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPI0mcSpaGnhQS/wBydRCZD",
      "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/yashaswi2311/IBM-Stock-Prediction/blob/master/test-LSTM.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z4YXfcesEJO5",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "c88740e0-f852-4d2c-8386-f41e80178c38"
      },
      "source": [
        "# Recurrent Neural Network\n",
        "\n",
        "\n",
        "\n",
        "# Part 1 - Data Preprocessing\n",
        "\n",
        "# Importing the libraries\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas_datareader.data as web\n",
        "import datetime as dt\n",
        "import pandas as pd\n",
        "\n",
        "\n",
        "start = dt.datetime(2019,1,1)\n",
        "end = dt.datetime(2020,2,26)\n",
        "dates = pd.date_range(start, end)\n",
        "\n",
        "# Importing the training set\n",
        "dataset_train = web.DataReader('IBM', 'yahoo', start, end)\n",
        "training_set = dataset_train.iloc[:, 1:2].values\n",
        "\n",
        "# Feature Scaling\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "sc = MinMaxScaler(feature_range = (0, 1))\n",
        "training_set_scaled = sc.fit_transform(training_set)\n",
        "\n",
        "# Creating a data structure with 20 timesteps and 1 output\n",
        "X_train = []\n",
        "y_train = []\n",
        "for i in range(60, 290 ):\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",
        "# Reshaping\n",
        "X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))\n",
        "\n",
        "\n",
        "\n",
        "# Part 2 - Building the RNN\n",
        "\n",
        "# Importing the Keras libraries and packages\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "from keras.layers import LSTM\n",
        "from keras.layers import Dropout\n",
        "\n",
        "# Initialising the RNN\n",
        "regressor = Sequential()\n",
        "\n",
        "# Adding the first LSTM layer and some Dropout regularisation\n",
        "regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))\n",
        "regressor.add(Dropout(0.2))\n",
        "\n",
        "# Adding a second LSTM layer and some Dropout regularisation\n",
        "regressor.add(LSTM(units = 50, return_sequences = True))\n",
        "regressor.add(Dropout(0.2))\n",
        "\n",
        "# Adding a third LSTM layer and some Dropout regularisation\n",
        "regressor.add(LSTM(units = 50, return_sequences = True))\n",
        "regressor.add(Dropout(0.2))\n",
        "\n",
        "# Adding a fourth LSTM layer and some Dropout regularisation\n",
        "regressor.add(LSTM(units = 50))\n",
        "regressor.add(Dropout(0.2))\n",
        "\n",
        "# Adding the output layer\n",
        "regressor.add(Dense(units = 1))\n",
        "\n",
        "# Compiling the RNN\n",
        "regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')\n",
        "\n",
        "# Fitting the RNN to the Training set\n",
        "regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)\n",
        "\n",
        "\n",
        "\n",
        "# Part 3 - Making the predictions and visualising the results\n",
        "\n",
        "# Getting the real stock price\n",
        "dataset_test = web.DataReader('IBM', 'yahoo', start, end)\n",
        "real_stock_price = dataset_test.iloc[:, 1:2].values\n",
        "\n",
        "# Getting the predicted stock price of 2017\n",
        "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, 80):\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 = regressor.predict(X_test)\n",
        "predicted_stock_price = sc.inverse_transform(predicted_stock_price)\n",
        "\n",
        "# Visualising the results\n",
        "plt.plot(real_stock_price, color = 'red', label = 'Real Stock Price')\n",
        "plt.plot(predicted_stock_price, color = 'blue', label = 'Predicted Stock Price')\n",
        "plt.title('IBM Stock Price Prediction')\n",
        "plt.xlabel('Time')\n",
        "plt.ylabel(' Stock Price')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "230/230 [==============================] - 6s 24ms/step - loss: 0.1868\n",
            "Epoch 2/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0460\n",
            "Epoch 3/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0310\n",
            "Epoch 4/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0265\n",
            "Epoch 5/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0214\n",
            "Epoch 6/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0210\n",
            "Epoch 7/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0207\n",
            "Epoch 8/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0180\n",
            "Epoch 9/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0186\n",
            "Epoch 10/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0185\n",
            "Epoch 11/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0190\n",
            "Epoch 12/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0195\n",
            "Epoch 13/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0193\n",
            "Epoch 14/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0195\n",
            "Epoch 15/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0171\n",
            "Epoch 16/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0169\n",
            "Epoch 17/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0190\n",
            "Epoch 18/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0177\n",
            "Epoch 19/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0167\n",
            "Epoch 20/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0162\n",
            "Epoch 21/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0167\n",
            "Epoch 22/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0201\n",
            "Epoch 23/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0180\n",
            "Epoch 24/100\n",
            "230/230 [==============================] - 1s 6ms/step - loss: 0.0166\n",
            "Epoch 25/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0157\n",
            "Epoch 26/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0150\n",
            "Epoch 27/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0140\n",
            "Epoch 28/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0135\n",
            "Epoch 29/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0130\n",
            "Epoch 30/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0128\n",
            "Epoch 31/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0136\n",
            "Epoch 32/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0134\n",
            "Epoch 33/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0120\n",
            "Epoch 34/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0104\n",
            "Epoch 35/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0138\n",
            "Epoch 36/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0123\n",
            "Epoch 37/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0126\n",
            "Epoch 38/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0107\n",
            "Epoch 39/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0125\n",
            "Epoch 40/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0127\n",
            "Epoch 41/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0156\n",
            "Epoch 42/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0116\n",
            "Epoch 43/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0105\n",
            "Epoch 44/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0121\n",
            "Epoch 45/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0125\n",
            "Epoch 46/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0102\n",
            "Epoch 47/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0099\n",
            "Epoch 48/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0116\n",
            "Epoch 49/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0103\n",
            "Epoch 50/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0095\n",
            "Epoch 51/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0107\n",
            "Epoch 52/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0098\n",
            "Epoch 53/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0108\n",
            "Epoch 54/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0093\n",
            "Epoch 55/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0102\n",
            "Epoch 56/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0086\n",
            "Epoch 57/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0094\n",
            "Epoch 58/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0090\n",
            "Epoch 59/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0098\n",
            "Epoch 60/100\n",
            "230/230 [==============================] - 1s 6ms/step - loss: 0.0119\n",
            "Epoch 61/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0108\n",
            "Epoch 62/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0086\n",
            "Epoch 63/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0101\n",
            "Epoch 64/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0096\n",
            "Epoch 65/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0079\n",
            "Epoch 66/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0091\n",
            "Epoch 67/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0095\n",
            "Epoch 68/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0092\n",
            "Epoch 69/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0086\n",
            "Epoch 70/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0089\n",
            "Epoch 71/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0078\n",
            "Epoch 72/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0098\n",
            "Epoch 73/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0092\n",
            "Epoch 74/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0080\n",
            "Epoch 75/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0072\n",
            "Epoch 76/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0077\n",
            "Epoch 77/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0083\n",
            "Epoch 78/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0078\n",
            "Epoch 79/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0081\n",
            "Epoch 80/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0087\n",
            "Epoch 81/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0080\n",
            "Epoch 82/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0081\n",
            "Epoch 83/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0084\n",
            "Epoch 84/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0083\n",
            "Epoch 85/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0097\n",
            "Epoch 86/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0094\n",
            "Epoch 87/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0078\n",
            "Epoch 88/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0082\n",
            "Epoch 89/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0079\n",
            "Epoch 90/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0073\n",
            "Epoch 91/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0069\n",
            "Epoch 92/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0072\n",
            "Epoch 93/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0077\n",
            "Epoch 94/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0086\n",
            "Epoch 95/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0088\n",
            "Epoch 96/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0075\n",
            "Epoch 97/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0081\n",
            "Epoch 98/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0071\n",
            "Epoch 99/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0074\n",
            "Epoch 100/100\n",
            "230/230 [==============================] - 2s 7ms/step - loss: 0.0081\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEWCAYAAAB42tAoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nExMKwzAMIyb/D7bqWEBEoUTnAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}