LSTM_DSE_FORECAST.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Set The Model Here"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "def Stock_Forecast(Instrument, TRIAL, PATIENCE, Back):\n",
    "    \n",
    "    # importing required libraries\n",
    "    from sklearn.preprocessing import MinMaxScaler\n",
    "    from keras.models import Sequential\n",
    "    from keras.layers import Dense, Dropout, LSTM\n",
    "    import pandas as pd\n",
    "    import numpy as np\n",
    "    import datetime\n",
    "    import tensorflow as tf\n",
    "    import random as rn\n",
    "    import os\n",
    "\n",
    "    os.environ[\"PYTHONHASHSEED\"] = \"0\"\n",
    "    \n",
    "    # I hate the tensorflow warnings\n",
    "    import tensorflow.python.util.deprecation as deprecation\n",
    "    deprecation._PRINT_DEPRECATION_WARNINGS = False\n",
    "\n",
    "    # Setting the seed for numpy-generated random numbers\n",
    "    np.random.seed(37)\n",
    "\n",
    "    # Setting the seed for python random numbers\n",
    "    rn.seed(1254)\n",
    "\n",
    "    # Setting the graph-level random seed.\n",
    "    tf.set_random_seed(89)\n",
    "\n",
    "    from keras import backend as K\n",
    "\n",
    "    session_conf = tf.ConfigProto(\n",
    "        intra_op_parallelism_threads=1, inter_op_parallelism_threads=1\n",
    "    )\n",
    "\n",
    "    # Force Tensorflow to use a single thread\n",
    "    sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)\n",
    "\n",
    "    K.set_session(sess)\n",
    "\n",
    "    # read the data\n",
    "    d = pd.read_excel(\"Book3.xlsx\")\n",
    "\n",
    "    # remove leading and trainling blank spaces from column names\n",
    "    d.columns = d.columns.str.strip()\n",
    "\n",
    "    # remove leanding and trailing blank spaces from TRADING.CODEs\n",
    "    d[\"TRADING.CODE\"] = d[\"TRADING.CODE\"].str.strip()\n",
    "\n",
    "    # select the Instrument of your interest\n",
    "    df = d[d[\"TRADING.CODE\"] == Instrument]\n",
    "\n",
    "    # remove rows with invalid values\n",
    "    df = df[\n",
    "        ~(df[\"LTP\"] == 0)\n",
    "        | (df[\"HIGH\"] == 0)\n",
    "        | (df[\"LOW\"] == 0)\n",
    "        | (df[\"OPENP\"] == 0)\n",
    "        | (df[\"CLOSEP\"] == 0)\n",
    "    ]\n",
    "\n",
    "    # sort the data as per date\n",
    "    df = df.sort_values([\"DATE\"], ascending=True)\n",
    "\n",
    "    # keep only the required columns\n",
    "    clean_data = df[[\"DATE\", \"CLOSEP\"]]\n",
    "\n",
    "    # set the date column as index\n",
    "    clean_data.set_index([\"DATE\"], inplace=True)\n",
    "\n",
    "    # turn the column into a numpy array\n",
    "    close_price = clean_data.values\n",
    "\n",
    "    # set first 75% values as training data and the rest as test data\n",
    "    train = close_price[: int(len(close_price) * 0.85), :]\n",
    "    valid = close_price[int(len(close_price) * 0.85) :, :]\n",
    "\n",
    "    # scaling the values\n",
    "    scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "    scaled_data = scaler.fit_transform(close_price)\n",
    "\n",
    "    # creating x_train and y_train, seeting the array as 0 dimensional, each time x_train.append is giving 'Back' values with 0 dimension,then set each as\n",
    "    # rows\n",
    "    x_train, y_train = [], []\n",
    "    for i in range(Back, len(train)):\n",
    "        x_train.append(scaled_data[i - Back : i, 0])\n",
    "        y_train.append(scaled_data[i, 0])\n",
    "    x_train, y_train = np.array(x_train), np.array(y_train)\n",
    "\n",
    "    # turn x_train as three dimensional\n",
    "    x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
    "\n",
    "    # create and fit the LSTM network\n",
    "    model = Sequential()\n",
    "    model.add(LSTM(units=50, return_sequences=True, input_shape=(x_train.shape[1], 1)))\n",
    "    model.add(LSTM(units=50))\n",
    "    model.add(Dense(1))\n",
    "\n",
    "    # compile the model\n",
    "    import keras\n",
    "    from keras.models import load_model\n",
    "\n",
    "    # set the model saved file name\n",
    "    saved_model = Instrument + \"weights.hdf5\"\n",
    "    model.compile(\n",
    "        loss=\"mean_absolute_percentage_error\", optimizer=\"adam\"\n",
    "    )  # model will try to minimize mape\n",
    "    ks = keras.callbacks.EarlyStopping(\n",
    "        monitor=\"val_loss\", mode=\"auto\", verbose=1, patience=PATIENCE\n",
    "    )  # model will wait for the next 200 model, if no improvement, stop\n",
    "    checkpointer = keras.callbacks.ModelCheckpoint(\n",
    "        filepath=saved_model, monitor=\"loss\", verbose=0, save_best_only=True\n",
    "    )  # best model so far will be saved\n",
    "    model.fit(\n",
    "        x_train,\n",
    "        y_train,\n",
    "        epochs=TRIAL,\n",
    "        validation_split=0.1,\n",
    "        verbose=0,\n",
    "        callbacks=[ks, checkpointer],\n",
    "    )  # now the fitted model will run 4000 trials for best model\n",
    "    model = load_model(saved_model)  # now the best model will be loaded from saved file\n",
    "\n",
    "    # predicting values, using past 'Back' from the train data\n",
    "    inputs = clean_data.values[len(clean_data) - len(valid) - Back :]\n",
    "    inputs = inputs.reshape(-1, 1)\n",
    "    inputs = scaler.transform(inputs)\n",
    "\n",
    "    # creating X_test\n",
    "    X_test = []\n",
    "    for i in range(Back, inputs.shape[0]):\n",
    "        X_test.append(inputs[i - Back : i, 0])\n",
    "    X_test = np.array(X_test)\n",
    "\n",
    "    # turn X_test into 3 dimensional\n",
    "    X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))\n",
    "\n",
    "    # forecasting future values ie calculating y_test\n",
    "    closing_price = model.predict(X_test)\n",
    "    cl = closing_price\n",
    "\n",
    "    # turning the forecasting values back to original scale\n",
    "    closing_price = scaler.inverse_transform(closing_price)\n",
    "\n",
    "    # model evaluate\n",
    "    train_acc = model.evaluate(x_train, y_train, verbose=0)\n",
    "    test_acc = model.evaluate(X_test, cl, verbose=0)\n",
    "    # print('Train: %.3f, Test: %.3f' % (train_acc, test_acc))\n",
    "\n",
    "    # calculating MAPE\n",
    "    rms = np.sqrt(np.mean(np.power((valid - closing_price), 2)))\n",
    "    mape = sum(abs(valid - closing_price) / abs(valid)) * 100 * (1 / len(valid))\n",
    "\n",
    "    # to plot within notebook\n",
    "    import matplotlib.pyplot as plt\n",
    "\n",
    "    %matplotlib inline\n",
    "\n",
    "    # for plotting\n",
    "    plt.figure(figsize=(20, 10))\n",
    "    train = clean_data[: int(len(close_price) * 0.85)]\n",
    "    valid = clean_data[int(len(close_price) * 0.85) :]\n",
    "    valid[\"Predictions\"] = closing_price\n",
    "    plt.plot(train[\"CLOSEP\"])\n",
    "    plt.plot(valid[[\"CLOSEP\", \"Predictions\"]])\n",
    "\n",
    "    print(\"The Root Mean Squared of the Model is: %.3f\" % (rms))\n",
    "    print(\"The Mean Absolute Percentage Error of the Model is: %.3f\" % (mape))\n",
    "\n",
    "    # out of sample forecast, next 30 business days\n",
    "    last_values = scaled_data[-Back:]  # take last 'Back' values\n",
    "    last_values = last_values.reshape((1, Back, 1))  # reshape\n",
    "    yhat = np.zeros(shape=(30, 1))\n",
    "\n",
    "    # run for loop for creating one forecast at a time and then use it to forecast the next\n",
    "    for i in range(0, 30):\n",
    "        yhat[i] = model.predict(last_values, verbose=0)\n",
    "        last_values = np.append(last_values, yhat[i])[-Back:].reshape(1, Back, 1)\n",
    "\n",
    "    yx = scaler.inverse_transform(yhat)  # inverse the variable transformation\n",
    "    yx = np.concatenate(yx).ravel().tolist()  # unlist the forecast data\n",
    "    yx = [round(w, 1) for w in yx]  # rounding the data to .10\n",
    "\n",
    "    # create the date index of the forecasted values\n",
    "    weekmask = \"Sun Mon Tue Wed Thu\"\n",
    "    custombday = pd.offsets.CustomBusinessDay(weekmask=weekmask)\n",
    "    pday = pd.bdate_range(\n",
    "        start=df.iloc[clean_data.shape[0] - 1, 0] + datetime.timedelta(days=1),\n",
    "        end=df.iloc[clean_data.shape[0] - 1, 0] + datetime.timedelta(days=365),\n",
    "        freq=custombday,\n",
    "    ).tolist()[0:30]\n",
    "\n",
    "    # turn the forecasted values into a dataframe\n",
    "    forecast_data = pd.DataFrame({\"Date\": pday, \"Forecast\": yx})\n",
    "    forecast_data.set_index(\"Date\", inplace=True)\n",
    "\n",
    "    # plot the forecast\n",
    "    plt.figure(figsize=(20, 10))\n",
    "    plt.plot(forecast_data[\"Forecast\"])\n",
    "\n",
    "    # now plot the forecast along with the original data\n",
    "    comb_data = pd.merge(\n",
    "        valid, forecast_data, left_index=True, right_index=True, how=\"outer\"\n",
    "    )\n",
    "    plt.figure(figsize=(20, 10))\n",
    "    plt.plot(comb_data[[\"CLOSEP\", \"Forecast\"]])\n",
    "\n",
    "    # the forecasted data as a output\n",
    "    return forecast_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Now set the Parameters and Run"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorboard\\compat\\tensorflow_stub\\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\ProgramData\\Anaconda3\\lib\\site-packages\\keras\\backend\\tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
      "\n",
      "Epoch 00830: early stopping\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:160: 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"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Root Mean Squared of the Model is: 0.913\n",
      "The Mean Absolute Percentage Error of the Model is: 2.156\n"
     ]
    },
    {
     "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>Forecast</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2020-03-26</th>\n",
       "      <td>29.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-29</th>\n",
       "      <td>27.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-30</th>\n",
       "      <td>27.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-31</th>\n",
       "      <td>28.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-01</th>\n",
       "      <td>32.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-02</th>\n",
       "      <td>40.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-05</th>\n",
       "      <td>42.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-06</th>\n",
       "      <td>26.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-07</th>\n",
       "      <td>20.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-08</th>\n",
       "      <td>24.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-09</th>\n",
       "      <td>27.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-12</th>\n",
       "      <td>33.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-13</th>\n",
       "      <td>43.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-14</th>\n",
       "      <td>50.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-15</th>\n",
       "      <td>38.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-16</th>\n",
       "      <td>32.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-19</th>\n",
       "      <td>38.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-20</th>\n",
       "      <td>40.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-21</th>\n",
       "      <td>40.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-22</th>\n",
       "      <td>39.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-23</th>\n",
       "      <td>38.7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-26</th>\n",
       "      <td>37.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-27</th>\n",
       "      <td>37.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-28</th>\n",
       "      <td>36.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-29</th>\n",
       "      <td>35.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-30</th>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-03</th>\n",
       "      <td>34.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-04</th>\n",
       "      <td>34.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-05</th>\n",
       "      <td>34.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-06</th>\n",
       "      <td>33.7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Forecast\n",
       "Date                \n",
       "2020-03-26      29.3\n",
       "2020-03-29      27.6\n",
       "2020-03-30      27.1\n",
       "2020-03-31      28.2\n",
       "2020-04-01      32.4\n",
       "2020-04-02      40.1\n",
       "2020-04-05      42.5\n",
       "2020-04-06      26.5\n",
       "2020-04-07      20.1\n",
       "2020-04-08      24.7\n",
       "2020-04-09      27.5\n",
       "2020-04-12      33.6\n",
       "2020-04-13      43.8\n",
       "2020-04-14      50.6\n",
       "2020-04-15      38.3\n",
       "2020-04-16      32.4\n",
       "2020-04-19      38.6\n",
       "2020-04-20      40.6\n",
       "2020-04-21      40.3\n",
       "2020-04-22      39.6\n",
       "2020-04-23      38.7\n",
       "2020-04-26      37.8\n",
       "2020-04-27      37.0\n",
       "2020-04-28      36.2\n",
       "2020-04-29      35.5\n",
       "2020-04-30      35.0\n",
       "2020-05-03      34.6\n",
       "2020-05-04      34.3\n",
       "2020-05-05      34.0\n",
       "2020-05-06      33.7"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# input Instrument Name\n",
    "# number of Epoch (trials),\n",
    "# after how many trials without any improvement in result the system should stop trial\n",
    "# number of previous data points to use for forecasting\n",
    "Stock_Forecast(Instrument=\"EBL\", TRIAL=5000, PATIENCE=500, Back=60)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}