DeepLearningForTimeSeriesForecasting/Quiz_RNN_encoder_decoder.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Multi step model (simple encoder-decoder)\n",
    "\n",
    "In this notebook, we demonstrate how to:\n",
    "- prepare time series data for training a RNN forecasting model\n",
    "- get data in the required shape for the keras API\n",
    "- implement a RNN model in keras to predict the next 3 steps ahead (time *t+1* to *t+3*) in the time series. This model uses a simple encoder decoder approach in which the final hidden state of the encoder is replicated across each time step of the decoder. \n",
    "- enable early stopping to reduce the likelihood of model overfitting\n",
    "- evaluate the model on a test dataset\n",
    "\n",
    "The data in this example is taken from the GEFCom2014 forecasting competition<sup>1</sup>. It consists of 3 years of hourly electricity load and temperature values between 2012 and 2014. The task is to forecast future values of electricity load.\n",
    "\n",
    "<sup>1</sup>Tao Hong, Pierre Pinson, Shu Fan, Hamidreza Zareipour, Alberto Troccoli and Rob J. Hyndman, \"Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond\", International Journal of Forecasting, vol.32, no.3, pp 896-913, July-September, 2016."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import warnings\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import datetime as dt\n",
    "from collections import UserDict\n",
    "from IPython.display import Image\n",
    "%matplotlib inline\n",
    "\n",
    "from common.utils import load_data, mape, TimeSeriesTensor, create_evaluation_df\n",
    "\n",
    "pd.options.display.float_format = '{:,.2f}'.format\n",
    "np.set_printoptions(precision=2)\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load data into Pandas dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>load</th>\n",
       "      <th>temp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2012-01-01 00:00:00</th>\n",
       "      <td>2,698.00</td>\n",
       "      <td>32.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 01:00:00</th>\n",
       "      <td>2,558.00</td>\n",
       "      <td>32.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 02:00:00</th>\n",
       "      <td>2,444.00</td>\n",
       "      <td>30.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 03:00:00</th>\n",
       "      <td>2,402.00</td>\n",
       "      <td>31.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 04:00:00</th>\n",
       "      <td>2,403.00</td>\n",
       "      <td>32.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        load  temp\n",
       "2012-01-01 00:00:00 2,698.00 32.00\n",
       "2012-01-01 01:00:00 2,558.00 32.67\n",
       "2012-01-01 02:00:00 2,444.00 30.00\n",
       "2012-01-01 03:00:00 2,402.00 31.00\n",
       "2012-01-01 04:00:00 2,403.00 32.00"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "energy = load_data('data/')\n",
    "energy.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "valid_start_dt = '2014-09-01 00:00:00'\n",
    "test_start_dt = '2014-11-01 00:00:00'\n",
    "\n",
    "T = 6\n",
    "HORIZON = 3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create training set containing only the model features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "train = energy.copy()[energy.index < valid_start_dt][['load', 'temp']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Scale data to be in range (0, 1). This transformation should be calibrated on the training set only. This is to prevent information from the validation or test sets leaking into the training data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "y_scaler = MinMaxScaler()\n",
    "y_scaler.fit(train[['load']])\n",
    "\n",
    "X_scaler = MinMaxScaler()\n",
    "train[['load', 'temp']] = X_scaler.fit_transform(train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Use the TimeSeriesTensor convenience class to:\n",
    "1. Shift the values of the time series to create a Pandas dataframe containing all the data for a single training example\n",
    "2. Discard any samples with missing values\n",
    "3. Transform this Pandas dataframe into a numpy array of shape (samples, time steps, features) for input into Keras\n",
    "\n",
    "The class takes the following parameters:\n",
    "\n",
    "- **dataset**: original time series\n",
    "- **H**: the forecast horizon\n",
    "- **tensor_structure**: a dictionary discribing the tensor structure in the form { 'tensor_name' : (range(max_backward_shift, max_forward_shift), [feature, feature, ...] ) }\n",
    "- **freq**: time series frequency\n",
    "- **drop_incomplete**: (Boolean) whether to drop incomplete samples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "tensor_structure = {'X':(range(-T+1, 1), ['load', 'temp'])}\n",
    "train_inputs = TimeSeriesTensor(train, 'load', HORIZON, {'X':(range(-T+1, 1), ['load', 'temp'])})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>tensor</th>\n",
       "      <th colspan=\"3\" halign=\"left\">target</th>\n",
       "      <th colspan=\"12\" halign=\"left\">X</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>feature</th>\n",
       "      <th colspan=\"3\" halign=\"left\">y</th>\n",
       "      <th colspan=\"6\" halign=\"left\">load</th>\n",
       "      <th colspan=\"6\" halign=\"left\">temp</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time step</th>\n",
       "      <th>t+1</th>\n",
       "      <th>t+2</th>\n",
       "      <th>t+3</th>\n",
       "      <th>t-5</th>\n",
       "      <th>t-4</th>\n",
       "      <th>t-3</th>\n",
       "      <th>t-2</th>\n",
       "      <th>t-1</th>\n",
       "      <th>t</th>\n",
       "      <th>t-5</th>\n",
       "      <th>t-4</th>\n",
       "      <th>t-3</th>\n",
       "      <th>t-2</th>\n",
       "      <th>t-1</th>\n",
       "      <th>t</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2012-01-01 05:00:00</th>\n",
       "      <td>0.18</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.14</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.43</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 06:00:00</th>\n",
       "      <td>0.23</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.35</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.14</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.43</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 07:00:00</th>\n",
       "      <td>0.29</td>\n",
       "      <td>0.35</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.14</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 08:00:00</th>\n",
       "      <td>0.35</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.39</td>\n",
       "      <td>0.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012-01-01 09:00:00</th>\n",
       "      <td>0.37</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.13</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.35</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0.39</td>\n",
       "      <td>0.39</td>\n",
       "      <td>0.43</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "tensor              target              X                                     \\\n",
       "feature                  y           load                          temp        \n",
       "time step              t+1  t+2  t+3  t-5  t-4  t-3  t-2  t-1    t  t-5  t-4   \n",
       "2012-01-01 05:00:00   0.18 0.23 0.29 0.22 0.18 0.14 0.13 0.13 0.15 0.42 0.43   \n",
       "2012-01-01 06:00:00   0.23 0.29 0.35 0.18 0.14 0.13 0.13 0.15 0.18 0.43 0.40   \n",
       "2012-01-01 07:00:00   0.29 0.35 0.37 0.14 0.13 0.13 0.15 0.18 0.23 0.40 0.41   \n",
       "2012-01-01 08:00:00   0.35 0.37 0.37 0.13 0.13 0.15 0.18 0.23 0.29 0.41 0.42   \n",
       "2012-01-01 09:00:00   0.37 0.37 0.37 0.13 0.15 0.18 0.23 0.29 0.35 0.42 0.41   \n",
       "\n",
       "tensor                                   \n",
       "feature                                  \n",
       "time step            t-3  t-2  t-1    t  \n",
       "2012-01-01 05:00:00 0.40 0.41 0.42 0.41  \n",
       "2012-01-01 06:00:00 0.41 0.42 0.41 0.40  \n",
       "2012-01-01 07:00:00 0.42 0.41 0.40 0.39  \n",
       "2012-01-01 08:00:00 0.41 0.40 0.39 0.39  \n",
       "2012-01-01 09:00:00 0.40 0.39 0.39 0.43  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_inputs.dataframe.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Construct validation set (keeping T hours from the training set in order to construct initial features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "look_back_dt = dt.datetime.strptime(valid_start_dt, '%Y-%m-%d %H:%M:%S') - dt.timedelta(hours=T-1)\n",
    "valid = energy.copy()[(energy.index >=look_back_dt) & (energy.index < test_start_dt)][['load', 'temp']]\n",
    "valid[['load', 'temp']] = X_scaler.transform(valid)\n",
    "valid_inputs = TimeSeriesTensor(valid, 'load', HORIZON, tensor_structure)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Quiz: Implement an encoder-decoder RNN"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Implement your RNN model with the data prepared above and the following requirements:\n",
    "1. Use 2 features: past load and temperature\n",
    "2. Stack 2 **LSTM** layers for the encoder RNN\n",
    "3. 12 hidden units in the first LSTM layer\n",
    "4. 6 hidden units in the second LSTM layer\n",
    "5. Repeat the vector output of the second encoder layer 3 times (one for each time step in the forecast horizon)\n",
    "5. Add a decoder LSTM with 6 hidden units\n",
    "6. 5 epochs\n",
    "7. Batch size 32\n",
    "\n",
    "The model will have the following structure:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABzAAAARTCAMAAAFEz3VHAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Image('./images/encoder_decoder_multilayer.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Model, Sequential\n",
    "from keras.layers import LSTM, Dense, RepeatVector, TimeDistributed, Flatten\n",
    "from keras.callbacks import EarlyStopping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ENCODER_LAYER_1_DIM = ?\n",
    "ENCODER_LAYER_2_DIM = ?\n",
    "DECODER_DIM = ?\n",
    "BATCH_SIZE = 32\n",
    "EPOCHS = 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "?\n",
    "?\n",
    "?\n",
    "?\n",
    "model.add(Flatten())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "model.compile(optimizer='RMSprop', loss='mse')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.fit(train_inputs['X'],\n",
    "          train_inputs['target'],\n",
    "          batch_size=BATCH_SIZE,\n",
    "          epochs=EPOCHS,\n",
    "          validation_data=(valid_inputs['X'], valid_inputs['target']),\n",
    "          callbacks=[earlystop],\n",
    "          verbose=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "look_back_dt = dt.datetime.strptime(test_start_dt, '%Y-%m-%d %H:%M:%S') - dt.timedelta(hours=T-1)\n",
    "test = energy.copy()[test_start_dt:][['load', 'temp']]\n",
    "test[['load', 'temp']] = X_scaler.transform(test)\n",
    "test_inputs = TimeSeriesTensor(test, 'load', HORIZON, tensor_structure)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "predictions = model.predict(test_inputs['X'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "eval_df = create_evaluation_df(predictions, test_inputs, HORIZON, y_scaler)\n",
    "eval_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "eval_df['APE'] = (eval_df['prediction'] - eval_df['actual']).abs() / eval_df['actual']\n",
    "eval_df.groupby('h')['APE'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mape(eval_df['prediction'], eval_df['actual'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Plot actuals vs predictions at each horizon for first week of the test period. As is to be expected, predictions for one step ahead (*t+1*) are more accurate than those for 2 or 3 steps ahead"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plot_df = eval_df[(eval_df.timestamp<'2014-11-08') & (eval_df.h=='t+1')][['timestamp', 'actual']]\n",
    "for t in range(1, HORIZON+1):\n",
    "    plot_df['t+'+str(t)] = eval_df[(eval_df.timestamp<'2014-11-08') & (eval_df.h=='t+'+str(t))]['prediction'].values\n",
    "\n",
    "fig = plt.figure(figsize=(15, 8))\n",
    "ax = plt.plot(plot_df['timestamp'], plot_df['actual'], color='red', linewidth=4.0)\n",
    "ax = fig.add_subplot(111)\n",
    "ax.plot(plot_df['timestamp'], plot_df['t+1'], color='blue', linewidth=4.0, alpha=0.75)\n",
    "ax.plot(plot_df['timestamp'], plot_df['t+2'], color='blue', linewidth=3.0, alpha=0.5)\n",
    "ax.plot(plot_df['timestamp'], plot_df['t+3'], color='blue', linewidth=2.0, alpha=0.25)\n",
    "plt.xlabel('timestamp', fontsize=12)\n",
    "plt.ylabel('load', fontsize=12)\n",
    "ax.legend(loc='best')\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}