Stock_Market_Prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "TPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FoZXMvrcZ5ho"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "\n",
        "import os\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas_datareader as web\n",
        "import datetime as dt\n",
        "\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Dense, Dropout, LSTM\n",
        "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "prices = pd.read_csv('prices.csv', header =0)\n",
        "prices.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "J97OBIdxaL-W",
        "outputId": "48e93e7c-a570-4c11-85cb-2a61d7f826fc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  date symbol        open       close         low        high  \\\n",
              "0  2016-01-05 00:00:00   WLTW  123.430000  125.839996  122.309998  126.250000   \n",
              "1  2016-01-06 00:00:00   WLTW  125.239998  119.980003  119.940002  125.540001   \n",
              "2  2016-01-07 00:00:00   WLTW  116.379997  114.949997  114.930000  119.739998   \n",
              "3  2016-01-08 00:00:00   WLTW  115.480003  116.620003  113.500000  117.440002   \n",
              "4  2016-01-11 00:00:00   WLTW  117.010002  114.970001  114.089996  117.330002   \n",
              "\n",
              "      volume  \n",
              "0  2163600.0  \n",
              "1  2386400.0  \n",
              "2  2489500.0  \n",
              "3  2006300.0  \n",
              "4  1408600.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-04513f56-4cf9-47b7-ab0e-7fc7b71b20e0\">\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>symbol</th>\n",
              "      <th>open</th>\n",
              "      <th>close</th>\n",
              "      <th>low</th>\n",
              "      <th>high</th>\n",
              "      <th>volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2016-01-05 00:00:00</td>\n",
              "      <td>WLTW</td>\n",
              "      <td>123.430000</td>\n",
              "      <td>125.839996</td>\n",
              "      <td>122.309998</td>\n",
              "      <td>126.250000</td>\n",
              "      <td>2163600.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2016-01-06 00:00:00</td>\n",
              "      <td>WLTW</td>\n",
              "      <td>125.239998</td>\n",
              "      <td>119.980003</td>\n",
              "      <td>119.940002</td>\n",
              "      <td>125.540001</td>\n",
              "      <td>2386400.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2016-01-07 00:00:00</td>\n",
              "      <td>WLTW</td>\n",
              "      <td>116.379997</td>\n",
              "      <td>114.949997</td>\n",
              "      <td>114.930000</td>\n",
              "      <td>119.739998</td>\n",
              "      <td>2489500.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2016-01-08 00:00:00</td>\n",
              "      <td>WLTW</td>\n",
              "      <td>115.480003</td>\n",
              "      <td>116.620003</td>\n",
              "      <td>113.500000</td>\n",
              "      <td>117.440002</td>\n",
              "      <td>2006300.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2016-01-11 00:00:00</td>\n",
              "      <td>WLTW</td>\n",
              "      <td>117.010002</td>\n",
              "      <td>114.970001</td>\n",
              "      <td>114.089996</td>\n",
              "      <td>117.330002</td>\n",
              "      <td>1408600.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-04513f56-4cf9-47b7-ab0e-7fc7b71b20e0')\"\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-04513f56-4cf9-47b7-ab0e-7fc7b71b20e0 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-04513f56-4cf9-47b7-ab0e-7fc7b71b20e0');\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": 13
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Data Preparation"
      ],
      "metadata": {
        "id": "KMakyMFJ82Oj"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "yahoo = prices[prices['symbol']=='YHOO']\n",
        "yahoo_prices = yahoo.close.values.astype('float32')\n",
        "yahoo_prices = yahoo_prices.reshape(1762, 1)\n",
        "yahoo_prices.shape\n",
        "plt.plot(yahoo_prices)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 265
        },
        "id": "X6V-d45saqHJ",
        "outputId": "25e2fd25-f6a2-473e-9bda-d019c07138b9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "_brYSHSe89KZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Normalize and split the data into train and test"
      ],
      "metadata": {
        "id": "YlclRWo9dM9Y"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "yahoo_prices = scaler.fit_transform(yahoo_prices)\n",
        "\n",
        "train_size = int(len(yahoo_prices) * 0.80)\n",
        "test_size = len(yahoo_prices) - train_size\n",
        "train, test = yahoo_prices[0:train_size,:], yahoo_prices[train_size:len(yahoo_prices),:]\n",
        "print(len(train), len(test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YUdPA4xZc8kt",
        "outputId": "c315401a-cd1a-42f2-f041-ae8130179764"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1409 353\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# convert an array of values into a dataset matrix\n",
        "def create_dataset(dataset, look_back=1):\n",
        "\tdataX, dataY = [], []\n",
        "\tfor i in range(len(dataset)-look_back-1):\n",
        "\t\ta = dataset[i:(i+look_back), 0]\n",
        "\t\tdataX.append(a)\n",
        "\t\tdataY.append(dataset[i + look_back, 0])\n",
        "\treturn np.array(dataX), np.array(dataY)"
      ],
      "metadata": {
        "id": "a-hCeaJSdaS-"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# reshape into X=t and Y=t+1\n",
        "look_back = 3\n",
        "trainX, trainY = create_dataset(train, look_back)\n",
        "testX, testY = create_dataset(test, look_back)\n",
        "\n",
        "trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))\n",
        "testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))"
      ],
      "metadata": {
        "id": "kMFRdXQtdjN8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "zcvYXQk9d-u5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Model Building"
      ],
      "metadata": {
        "id": "xxNz3aztd_u3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Step 2 Build Model\n",
        "model = Sequential()\n",
        "\n",
        "model.add(LSTM(4,\n",
        "    input_shape=(1, look_back)))\n",
        "model.add(Dense(1))\n",
        "\n",
        "model.compile(loss='mse', optimizer='adam')\n",
        "model.fit(\n",
        "    trainX,\n",
        "    trainY,\n",
        "    batch_size=1,\n",
        "    epochs=5,\n",
        "    validation_split=0.05)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QTCokLatd-yg",
        "outputId": "9486bed6-ff4a-465d-db46-efe72a36b37a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "1334/1334 [==============================] - 8s 4ms/step - loss: 0.0153 - val_loss: 6.3624e-04\n",
            "Epoch 2/5\n",
            "1334/1334 [==============================] - 4s 3ms/step - loss: 3.2277e-04 - val_loss: 8.0133e-04\n",
            "Epoch 3/5\n",
            "1334/1334 [==============================] - 4s 3ms/step - loss: 3.2476e-04 - val_loss: 9.9015e-04\n",
            "Epoch 4/5\n",
            "1334/1334 [==============================] - 4s 3ms/step - loss: 3.1509e-04 - val_loss: 5.2357e-04\n",
            "Epoch 5/5\n",
            "1334/1334 [==============================] - 4s 3ms/step - loss: 3.1311e-04 - val_loss: 6.3708e-04\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f4d0e931be0>"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "Z2eb9yQie8Ez"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Model Evalution"
      ],
      "metadata": {
        "id": "vIRD5VD9e8eB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# make predictions\n",
        "trainPredict = model.predict(trainX)\n",
        "testPredict = model.predict(testX)\n",
        "\n",
        "# invert the predictions\n",
        "trainPredict = scaler.inverse_transform(trainPredict)\n",
        "trainY = scaler.inverse_transform([trainY])\n",
        "testPredict = scaler.inverse_transform(testPredict)\n",
        "testY = scaler.inverse_transform([testY])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tay5SIQ9fH2h",
        "outputId": "08d81041-6dc2-4a6e-a09d-6515b96576e6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "44/44 [==============================] - 0s 2ms/step\n",
            "11/11 [==============================] - 0s 3ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# calculate rmse\n",
        "import math\n",
        "from sklearn.metrics import mean_squared_error\n",
        "\n",
        "trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))\n",
        "print('Train Score: %.2f RMSE' % (trainScore))\n",
        "testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))\n",
        "print('Test Score: %.2f RMSE' % (testScore))"
      ],
      "metadata": {
        "id": "IqRUIeUVgO09",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "774d0f85-73f7-46e6-b837-69a47a7247d2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train Score: 0.71 RMSE\n",
            "Test Score: 0.89 RMSE\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# shift train predictions for plotting\n",
        "trainPredictPlot = np.empty_like(yahoo_prices)\n",
        "trainPredictPlot[:, :] = np.nan\n",
        "trainPredictPlot[look_back:len(trainPredict)+ look_back, :] = trainPredict\n",
        "\n",
        "# shift train \n",
        "testPredictPlot = np.empty_like(yahoo_prices)\n",
        "testPredictPlot[:, :] = np.nan\n",
        "testPredictPlot[(len(trainPredict) + (look_back*2))+1:len(yahoo_prices)-1, :] = testPredict"
      ],
      "metadata": {
        "id": "tpwaNiL9gx4c"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.plot(scaler.inverse_transform(yahoo_prices))\n",
        "plt.plot(trainPredictPlot, label = 'True')\n",
        "plt.plot(testPredictPlot, label = 'LSTM')\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "bOdx3gljg9mU",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 265
        },
        "outputId": "189d2f66-93fb-4dd9-e119-3c0962d67166"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}