StockPrediction_LSTM_model.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "StockPrediction_LSTM_model.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyPeUUi+H/Bbl09VQehxngQD",
      "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/LuffyAnshul/StockMarketLSTM/blob/master/StockPrediction_LSTM_model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ot031Yw5n3wc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Description: This program uses an artificial recurrent neyral network called\n",
        "# Long Short Term Memory (LSTM) to predict the closing stock price of a\n",
        "# corporation (Apple Inc.) using the past 60 days stock price."
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pMhaQmcEoQ_i",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 90
        },
        "outputId": "49364732-28ef-462e-9233-b74aab692c95"
      },
      "source": [
        "# Importing libraries\n",
        "import math\n",
        "import pandas_datareader as web\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, LSTM\n",
        "import matplotlib.pyplot as plt\n",
        "plt.style.use('fivethirtyeight')"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/pandas_datareader/compat/__init__.py:7: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
            "  from pandas.util.testing import assert_frame_equal\n",
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JA7Q-zvSoSnu",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 431
        },
        "outputId": "04a7b2f4-9d2b-4bf0-caf0-bb4769043e27"
      },
      "source": [
        "# get the stock quote\n",
        "\n",
        "df = web.DataReader('AAPL', data_source='yahoo', start='2012-01-01', end='2019-12-17')\n",
        "\n",
        "# show data\n",
        "df"
      ],
      "execution_count": 4,
      "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>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Open</th>\n",
              "      <th>Close</th>\n",
              "      <th>Volume</th>\n",
              "      <th>Adj Close</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>2012-01-03</th>\n",
              "      <td>58.928570</td>\n",
              "      <td>58.428570</td>\n",
              "      <td>58.485714</td>\n",
              "      <td>58.747143</td>\n",
              "      <td>75555200.0</td>\n",
              "      <td>50.857235</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-04</th>\n",
              "      <td>59.240002</td>\n",
              "      <td>58.468571</td>\n",
              "      <td>58.571430</td>\n",
              "      <td>59.062859</td>\n",
              "      <td>65005500.0</td>\n",
              "      <td>51.130558</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-05</th>\n",
              "      <td>59.792858</td>\n",
              "      <td>58.952858</td>\n",
              "      <td>59.278572</td>\n",
              "      <td>59.718571</td>\n",
              "      <td>67817400.0</td>\n",
              "      <td>51.698215</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-06</th>\n",
              "      <td>60.392857</td>\n",
              "      <td>59.888573</td>\n",
              "      <td>59.967144</td>\n",
              "      <td>60.342857</td>\n",
              "      <td>79573200.0</td>\n",
              "      <td>52.238651</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-01-09</th>\n",
              "      <td>61.107143</td>\n",
              "      <td>60.192856</td>\n",
              "      <td>60.785713</td>\n",
              "      <td>60.247143</td>\n",
              "      <td>98506100.0</td>\n",
              "      <td>52.155792</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>2019-12-11</th>\n",
              "      <td>271.100006</td>\n",
              "      <td>268.500000</td>\n",
              "      <td>268.809998</td>\n",
              "      <td>270.769989</td>\n",
              "      <td>19689200.0</td>\n",
              "      <td>269.399658</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-12</th>\n",
              "      <td>272.559998</td>\n",
              "      <td>267.320007</td>\n",
              "      <td>267.779999</td>\n",
              "      <td>271.459991</td>\n",
              "      <td>34327600.0</td>\n",
              "      <td>270.086151</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-13</th>\n",
              "      <td>275.299988</td>\n",
              "      <td>270.929993</td>\n",
              "      <td>271.459991</td>\n",
              "      <td>275.149994</td>\n",
              "      <td>33396900.0</td>\n",
              "      <td>273.757477</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-16</th>\n",
              "      <td>280.790009</td>\n",
              "      <td>276.980011</td>\n",
              "      <td>277.000000</td>\n",
              "      <td>279.859985</td>\n",
              "      <td>32046500.0</td>\n",
              "      <td>278.443604</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-17</th>\n",
              "      <td>281.769989</td>\n",
              "      <td>278.799988</td>\n",
              "      <td>279.570007</td>\n",
              "      <td>280.410004</td>\n",
              "      <td>28539600.0</td>\n",
              "      <td>278.990875</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2003 rows × 6 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                  High         Low  ...      Volume   Adj Close\n",
              "Date                                ...                        \n",
              "2012-01-03   58.928570   58.428570  ...  75555200.0   50.857235\n",
              "2012-01-04   59.240002   58.468571  ...  65005500.0   51.130558\n",
              "2012-01-05   59.792858   58.952858  ...  67817400.0   51.698215\n",
              "2012-01-06   60.392857   59.888573  ...  79573200.0   52.238651\n",
              "2012-01-09   61.107143   60.192856  ...  98506100.0   52.155792\n",
              "...                ...         ...  ...         ...         ...\n",
              "2019-12-11  271.100006  268.500000  ...  19689200.0  269.399658\n",
              "2019-12-12  272.559998  267.320007  ...  34327600.0  270.086151\n",
              "2019-12-13  275.299988  270.929993  ...  33396900.0  273.757477\n",
              "2019-12-16  280.790009  276.980011  ...  32046500.0  278.443604\n",
              "2019-12-17  281.769989  278.799988  ...  28539600.0  278.990875\n",
              "\n",
              "[2003 rows x 6 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KE8rHafSo4v_",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "0edfbdc0-8b1c-4877-e8fc-5a2c293ef1b3"
      },
      "source": [
        "# Get the number fo rows and column in dataset\n",
        "\n",
        "df.shape"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2003, 6)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yz8Sg5hJpLu0",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 558
        },
        "outputId": "f654a1ba-0397-4122-904c-6263c5a2a384"
      },
      "source": [
        "# Visualize the closing price history\n",
        "plt.figure(figsize=(16, 8))\n",
        "plt.title('Close Price Histroy')\n",
        "plt.plot(df['Close'])\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price USD ($)', fontsize=18)\n",
        "plt.show()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rt60jTh_poFN",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "2988f98f-0763-43a1-c446-9904ba054b6f"
      },
      "source": [
        "# Create a new dataframe with only the 'Close' column\n",
        "data = df.filter(['Close'])\n",
        "\n",
        "# Convert the dataframe to a nupy array\n",
        "dataset = data.values\n",
        "\n",
        "# get the number of rows to train the model\n",
        "training_data_len = math.ceil(len(dataset)* .8)\n",
        "\n",
        "training_data_len"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1603"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zx8ALCWnqfpA",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 140
        },
        "outputId": "519797be-bb57-4d72-cec4-057941ad8ef4"
      },
      "source": [
        "# Scale the data\n",
        "scaler = MinMaxScaler(feature_range=(0, 1))\n",
        "scaled_data = scaler.fit_transform(dataset)\n",
        "\n",
        "scaled_data"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.01316509],\n",
              "       [0.01457064],\n",
              "       [0.01748985],\n",
              "       ...,\n",
              "       [0.97658263],\n",
              "       [0.99755134],\n",
              "       [1.        ]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Vz0iXrVSq_ks",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 263
        },
        "outputId": "8009b682-ffce-4132-e437-5871c65c1d25"
      },
      "source": [
        "# Create the training dataset, create the scaled training dataset\n",
        "train_data = scaled_data[0: training_data_len, :]\n",
        "\n",
        "#Split the data into x_train and y_train dataset\n",
        "x_train = []\n",
        "y_train = []\n",
        "\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<=60:\n",
        "    print(x_train)\n",
        "    print(y_train)\n",
        "    print()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[array([0.01316509, 0.01457064, 0.01748985, 0.02026915, 0.01984303,\n",
            "       0.02080338, 0.02036454, 0.01962679, 0.01862193, 0.02173194,\n",
            "       0.02453668, 0.02367172, 0.01893356, 0.02345548, 0.01900352,\n",
            "       0.03569838, 0.03440731, 0.0360927 , 0.03973694, 0.04194384,\n",
            "       0.0417594 , 0.0410789 , 0.04397903, 0.04670744, 0.04979839,\n",
            "       0.05479095, 0.0652785 , 0.06543749, 0.07127594, 0.07563885,\n",
            "       0.06814046, 0.07102789, 0.07097066, 0.07906688, 0.07791571,\n",
            "       0.08004628, 0.08387497, 0.08600558, 0.09214292, 0.09661397,\n",
            "       0.09790501, 0.09835659, 0.09071194, 0.08886753, 0.08914103,\n",
            "       0.09632775, 0.09835024, 0.10269405, 0.11293358, 0.12659476,\n",
            "       0.12403805, 0.1240444 , 0.13392141, 0.13701233, 0.13481179,\n",
            "       0.13280207, 0.13070964, 0.13766105, 0.14243103, 0.14442805])]\n",
            "[0.13949272033425864]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HCscB9gUryqh",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Convert x_train and y_train to numpy array \n",
        "x_train, y_train = np.array(x_train), np.array(y_train)"
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "j5HxCr9jsXd5",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "4230a1dd-2bf4-4925-a11b-9d2eab707019"
      },
      "source": [
        "# reshape the data\n",
        "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
        "x_train.shape"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1543, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XTObIT1UtAVP",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Build the LSTM model\n",
        "\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))"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PxcqAa9ntqTm",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Complile the model\n",
        "model.compile(optimizer='adam', loss='mean_squared_error')"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yHeHSdz83v5f",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 298
        },
        "outputId": "7e21a0f9-2fe2-4117-bab4-c50c5ff33bfc"
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "lstm_1 (LSTM)                (None, 60, 50)            10400     \n",
            "_________________________________________________________________\n",
            "lstm_2 (LSTM)                (None, 50)                20200     \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 25)                1275      \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 1)                 26        \n",
            "=================================================================\n",
            "Total params: 31,901\n",
            "Trainable params: 31,901\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RLMZKq7P3v_9",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "outputId": "bb55d45d-dc8a-4de1-9539-6fdcedb7f43d"
      },
      "source": [
        "import pydot\n",
        "from keras import utils\n",
        "\n",
        "utils.plot_model(model)"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jUX4KgiJt6yd",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "outputId": "e4d6a361-257c-42eb-c57a-faae1c7684e1"
      },
      "source": [
        "# train the model\n",
        "model.fit(x_train, y_train, batch_size=1, epochs=1)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/1\n",
            "1543/1543 [==============================] - 64s 42ms/step - loss: 0.0011\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.callbacks.History at 0x7f1510d9efd0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0Fve0BVTuGyI",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Create the testing dataset, create a new array from index 1543 to 2003\n",
        "test_data = scaled_data[training_data_len - 60: , :]\n",
        "\n",
        "# Create the datasets x_test and y_test\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"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zEnXSgnWu8An",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# convert the data into numpy array\n",
        "x_test = np.array(x_test)"
      ],
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PdFx1owgvLF8",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d523136f-2447-41db-ec1e-0265ef058a43"
      },
      "source": [
        "# reshape the data\n",
        "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))\n",
        "x_test.shape"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(400, 60, 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CXvZb2dlvaVc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Get the models predicted price values\n",
        "predictions = model.predict(x_test)\n",
        "predictions = scaler.inverse_transform(predictions)"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "61ShxZxxv93M",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "1862eedc-921a-492e-c9da-2f825490e0bd"
      },
      "source": [
        "# Get the root-mean-squared-error (RMSE)\n",
        "rmse = np.sqrt(np.mean(predictions-y_test)**2)\n",
        "rmse"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "5.949259185791016"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Oj7DXfgxwUcq",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        },
        "outputId": "feb07d70-3cf8-4520-d6a9-1935980dbdfd"
      },
      "source": [
        "# Plot the data\n",
        "train = data[: training_data_len]\n",
        "valid = data[training_data_len:]\n",
        "valid['Predictions'] = predictions"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py: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",
            "  after removing the cwd from sys.path.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Lzix5gO6xVyS",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 558
        },
        "outputId": "4a6c447c-17f6-4701-9eba-44f5a38ff026"
      },
      "source": [
        "# Visualize the data\n",
        "plt.figure(figsize=(16, 8))\n",
        "plt.title('Model')\n",
        "plt.xlabel('Date', fontsize=18)\n",
        "plt.ylabel('Close Price USD ($)', 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()"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1152x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qN4JFVQOyZLI",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 431
        },
        "outputId": "76a76688-d9af-43e7-8af8-f9b2d974c603"
      },
      "source": [
        "# Show the valid and predicted price\n",
        "valid"
      ],
      "execution_count": 25,
      "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>Close</th>\n",
              "      <th>Predictions</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2018-05-17</th>\n",
              "      <td>186.990005</td>\n",
              "      <td>182.614792</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-05-18</th>\n",
              "      <td>186.309998</td>\n",
              "      <td>183.021835</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-05-21</th>\n",
              "      <td>187.630005</td>\n",
              "      <td>183.145752</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-05-22</th>\n",
              "      <td>187.160004</td>\n",
              "      <td>183.231506</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-05-23</th>\n",
              "      <td>188.360001</td>\n",
              "      <td>183.237183</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-11</th>\n",
              "      <td>270.769989</td>\n",
              "      <td>257.066559</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-12</th>\n",
              "      <td>271.459991</td>\n",
              "      <td>257.859375</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-13</th>\n",
              "      <td>275.149994</td>\n",
              "      <td>258.733154</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-16</th>\n",
              "      <td>279.859985</td>\n",
              "      <td>259.925018</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-12-17</th>\n",
              "      <td>280.410004</td>\n",
              "      <td>261.606903</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>400 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                 Close  Predictions\n",
              "Date                               \n",
              "2018-05-17  186.990005   182.614792\n",
              "2018-05-18  186.309998   183.021835\n",
              "2018-05-21  187.630005   183.145752\n",
              "2018-05-22  187.160004   183.231506\n",
              "2018-05-23  188.360001   183.237183\n",
              "...                ...          ...\n",
              "2019-12-11  270.769989   257.066559\n",
              "2019-12-12  271.459991   257.859375\n",
              "2019-12-13  275.149994   258.733154\n",
              "2019-12-16  279.859985   259.925018\n",
              "2019-12-17  280.410004   261.606903\n",
              "\n",
              "[400 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7GGJqjmJzDDn",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "c8b64f41-49d3-4b1f-e9bf-ff2e139a2c55"
      },
      "source": [
        "# Get the quote\n",
        "apple_quote = web.DataReader('AAPL', data_source='yahoo', start='2012-01-01', end='2019-12-17')\n",
        "\n",
        "# Create new dataframe\n",
        "new_df = apple_quote.filter(['Close'])\n",
        "\n",
        "# Get the last 60 days closing price values and convert to dataframe to array\n",
        "last_60_days = new_df[-60:].values\n",
        "\n",
        "# Scale the data to be values between 0 and 1\n",
        "last_60_days_scaled = scaler.transform(last_60_days)\n",
        "\n",
        "# Create an empty list\n",
        "X_test = []\n",
        "\n",
        "# append the past 60 days\n",
        "X_test.append(last_60_days_scaled)\n",
        "\n",
        "# Convert the X_test dataset to numpy array\n",
        "X_test = np.array(X_test)\n",
        "\n",
        "# reshape the data\n",
        "X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
        "\n",
        "# Get the predicted scaled price\n",
        "pred_price = model.predict(X_test)\n",
        "\n",
        "# Undo the scaling\n",
        "pred_price = scaler.inverse_transform(pred_price)\n",
        "print(pred_price)"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[263.40103]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gzdBiveg0kDD",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "outputId": "63073107-e0f5-43a8-f109-0c3e4ac2091e"
      },
      "source": [
        "apple_quote2 = web.DataReader('AAPL', data_source='yahoo', start='2019-12-18', end='2019-12-18')\n",
        "print(apple_quote2['Close'])"
      ],
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Date\n",
            "2019-12-18    279.73999\n",
            "Name: Close, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TSA-ulx72hSh",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 27,
      "outputs": []
    }
  ]
}