Predicting_bike_sharing_data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Your first neural network\n",
    "\n",
    "In this project, you'll build your first neural network and use it to predict daily bike rental ridership. We've provided some of the code, but left the implementation of the neural network up to you (for the most part). After you've submitted this project, feel free to explore the data and the model more.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load and prepare the data\n",
    "\n",
    "A critical step in working with neural networks is preparing the data correctly. Variables on different scales make it difficult for the network to efficiently learn the correct weights. Below, we've written the code to load and prepare the data. You'll learn more about this soon!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_path = 'Bike-Sharing-Dataset/hour.csv'\n",
    "\n",
    "rides = pd.read_csv(data_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "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>instant</th>\n",
       "      <th>dteday</th>\n",
       "      <th>season</th>\n",
       "      <th>yr</th>\n",
       "      <th>mnth</th>\n",
       "      <th>hr</th>\n",
       "      <th>holiday</th>\n",
       "      <th>weekday</th>\n",
       "      <th>workingday</th>\n",
       "      <th>weathersit</th>\n",
       "      <th>temp</th>\n",
       "      <th>atemp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>casual</th>\n",
       "      <th>registered</th>\n",
       "      <th>cnt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.81</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8</td>\n",
       "      <td>32</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.2727</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5</td>\n",
       "      <td>27</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>2011-01-01</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.2879</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   instant      dteday  season  yr  mnth  hr  holiday  weekday  workingday  \\\n",
       "0        1  2011-01-01       1   0     1   0        0        6           0   \n",
       "1        2  2011-01-01       1   0     1   1        0        6           0   \n",
       "2        3  2011-01-01       1   0     1   2        0        6           0   \n",
       "3        4  2011-01-01       1   0     1   3        0        6           0   \n",
       "4        5  2011-01-01       1   0     1   4        0        6           0   \n",
       "\n",
       "   weathersit  temp   atemp   hum  windspeed  casual  registered  cnt  \n",
       "0           1  0.24  0.2879  0.81        0.0       3          13   16  \n",
       "1           1  0.22  0.2727  0.80        0.0       8          32   40  \n",
       "2           1  0.22  0.2727  0.80        0.0       5          27   32  \n",
       "3           1  0.24  0.2879  0.75        0.0       3          10   13  \n",
       "4           1  0.24  0.2879  0.75        0.0       0           1    1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rides.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Checking out the data\n",
    "\n",
    "This dataset has the number of riders for each hour of each day from January 1 2011 to December 31 2012. The number of riders is split between casual and registered, summed up in the `cnt` column. You can see the first few rows of the data above.\n",
    "\n",
    "Below is a plot showing the number of bike riders over the first 10 days or so in the data set. (Some days don't have exactly 24 entries in the data set, so it's not exactly 10 days.) You can see the hourly rentals here. This data is pretty complicated! The weekends have lower over all ridership and there are spikes when people are biking to and from work during the week. Looking at the data above, we also have information about temperature, humidity, and windspeed, all of these likely affecting the number of riders. You'll be trying to capture all this with your model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='dteday'>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 261,
       "width": 375
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "rides[:24*10].plot(x='dteday', y='cnt')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dummy variables\n",
    "Here we have some categorical variables like season, weather, month. To include these in our model, we'll need to make binary dummy variables. This is simple to do with Pandas thanks to `get_dummies()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "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>yr</th>\n",
       "      <th>holiday</th>\n",
       "      <th>temp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>casual</th>\n",
       "      <th>registered</th>\n",
       "      <th>cnt</th>\n",
       "      <th>season_1</th>\n",
       "      <th>season_2</th>\n",
       "      <th>...</th>\n",
       "      <th>hr_21</th>\n",
       "      <th>hr_22</th>\n",
       "      <th>hr_23</th>\n",
       "      <th>weekday_0</th>\n",
       "      <th>weekday_1</th>\n",
       "      <th>weekday_2</th>\n",
       "      <th>weekday_3</th>\n",
       "      <th>weekday_4</th>\n",
       "      <th>weekday_5</th>\n",
       "      <th>weekday_6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.81</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>16</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8</td>\n",
       "      <td>32</td>\n",
       "      <td>40</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5</td>\n",
       "      <td>27</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>13</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 59 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   yr  holiday  temp   hum  windspeed  casual  registered  cnt  season_1  \\\n",
       "0   0        0  0.24  0.81        0.0       3          13   16         1   \n",
       "1   0        0  0.22  0.80        0.0       8          32   40         1   \n",
       "2   0        0  0.22  0.80        0.0       5          27   32         1   \n",
       "3   0        0  0.24  0.75        0.0       3          10   13         1   \n",
       "4   0        0  0.24  0.75        0.0       0           1    1         1   \n",
       "\n",
       "   season_2  ...  hr_21  hr_22  hr_23  weekday_0  weekday_1  weekday_2  \\\n",
       "0         0  ...      0      0      0          0          0          0   \n",
       "1         0  ...      0      0      0          0          0          0   \n",
       "2         0  ...      0      0      0          0          0          0   \n",
       "3         0  ...      0      0      0          0          0          0   \n",
       "4         0  ...      0      0      0          0          0          0   \n",
       "\n",
       "   weekday_3  weekday_4  weekday_5  weekday_6  \n",
       "0          0          0          0          1  \n",
       "1          0          0          0          1  \n",
       "2          0          0          0          1  \n",
       "3          0          0          0          1  \n",
       "4          0          0          0          1  \n",
       "\n",
       "[5 rows x 59 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dummy_fields = ['season', 'weathersit', 'mnth', 'hr', 'weekday']\n",
    "for each in dummy_fields:\n",
    "    dummies = pd.get_dummies(rides[each], prefix=each, drop_first=False)\n",
    "    rides = pd.concat([rides, dummies], axis=1)\n",
    "\n",
    "fields_to_drop = ['instant', 'dteday', 'season', 'weathersit', \n",
    "                  'weekday', 'atemp', 'mnth', 'workingday', 'hr']\n",
    "data = rides.drop(fields_to_drop, axis=1)\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Scaling target variables\n",
    "To make training the network easier, we'll standardize each of the continuous variables. That is, we'll shift and scale the variables such that they have zero mean and a standard deviation of 1.\n",
    "\n",
    "The scaling factors are saved so we can go backwards when we use the network for predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save data for approximately the last 21 days \n",
    "test_data = data[-21*24:]\n",
    "\n",
    "# Now remove the test data from the data set \n",
    "data = data[:-21*24]\n",
    "\n",
    "quant_features = ['casual', 'registered', 'cnt', 'temp', 'hum', 'windspeed']\n",
    "# Store scalings in a dictionary so we can convert back later\n",
    "scaled_features = {}\n",
    "for each in quant_features:\n",
    "    mean, std = data[each].mean(), data[each].std()\n",
    "    scaled_features[each] = [mean, std]\n",
    "    data.loc[:, each] = (data[each] - mean)/std\n",
    "    test_data.loc[:, each] = (test_data[each] - mean)/std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "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>yr</th>\n",
       "      <th>holiday</th>\n",
       "      <th>temp</th>\n",
       "      <th>hum</th>\n",
       "      <th>windspeed</th>\n",
       "      <th>casual</th>\n",
       "      <th>registered</th>\n",
       "      <th>cnt</th>\n",
       "      <th>season_1</th>\n",
       "      <th>season_2</th>\n",
       "      <th>...</th>\n",
       "      <th>hr_21</th>\n",
       "      <th>hr_22</th>\n",
       "      <th>hr_23</th>\n",
       "      <th>weekday_0</th>\n",
       "      <th>weekday_1</th>\n",
       "      <th>weekday_2</th>\n",
       "      <th>weekday_3</th>\n",
       "      <th>weekday_4</th>\n",
       "      <th>weekday_5</th>\n",
       "      <th>weekday_6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.370528</td>\n",
       "      <td>0.946639</td>\n",
       "      <td>-1.558407</td>\n",
       "      <td>-0.668796</td>\n",
       "      <td>-0.933742</td>\n",
       "      <td>-0.960480</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.474766</td>\n",
       "      <td>0.894996</td>\n",
       "      <td>-1.558407</td>\n",
       "      <td>-0.568391</td>\n",
       "      <td>-0.808452</td>\n",
       "      <td>-0.828686</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.474766</td>\n",
       "      <td>0.894996</td>\n",
       "      <td>-1.558407</td>\n",
       "      <td>-0.628634</td>\n",
       "      <td>-0.841423</td>\n",
       "      <td>-0.872617</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.370528</td>\n",
       "      <td>0.636780</td>\n",
       "      <td>-1.558407</td>\n",
       "      <td>-0.668796</td>\n",
       "      <td>-0.953525</td>\n",
       "      <td>-0.976954</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.370528</td>\n",
       "      <td>0.636780</td>\n",
       "      <td>-1.558407</td>\n",
       "      <td>-0.729039</td>\n",
       "      <td>-1.012872</td>\n",
       "      <td>-1.042851</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 59 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   yr  holiday      temp       hum  windspeed    casual  registered       cnt  \\\n",
       "0   0        0 -1.370528  0.946639  -1.558407 -0.668796   -0.933742 -0.960480   \n",
       "1   0        0 -1.474766  0.894996  -1.558407 -0.568391   -0.808452 -0.828686   \n",
       "2   0        0 -1.474766  0.894996  -1.558407 -0.628634   -0.841423 -0.872617   \n",
       "3   0        0 -1.370528  0.636780  -1.558407 -0.668796   -0.953525 -0.976954   \n",
       "4   0        0 -1.370528  0.636780  -1.558407 -0.729039   -1.012872 -1.042851   \n",
       "\n",
       "   season_1  season_2  ...  hr_21  hr_22  hr_23  weekday_0  weekday_1  \\\n",
       "0         1         0  ...      0      0      0          0          0   \n",
       "1         1         0  ...      0      0      0          0          0   \n",
       "2         1         0  ...      0      0      0          0          0   \n",
       "3         1         0  ...      0      0      0          0          0   \n",
       "4         1         0  ...      0      0      0          0          0   \n",
       "\n",
       "   weekday_2  weekday_3  weekday_4  weekday_5  weekday_6  \n",
       "0          0          0          0          0          1  \n",
       "1          0          0          0          0          1  \n",
       "2          0          0          0          0          1  \n",
       "3          0          0          0          0          1  \n",
       "4          0          0          0          0          1  \n",
       "\n",
       "[5 rows x 59 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Splitting the data into training, testing, and validation sets\n",
    "\n",
    "We'll save the data for the last approximately 21 days to use as a test set after we've trained the network. We'll use this set to make predictions and compare them with the actual number of riders."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Separate the data into features and targets\n",
    "target_fields = ['cnt', 'casual', 'registered']\n",
    "features, targets = data.drop(target_fields, axis=1), data[target_fields]\n",
    "test_features, test_targets = test_data.drop(target_fields, axis=1), test_data[target_fields]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We'll split the data into two sets, one for training and one for validating as the network is being trained. Since this is time series data, we'll train on historical data, then try to predict on future data (the validation set)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Hold out the last 60 days or so of the remaining data as a validation set\n",
    "train_features, train_targets = features[:-60*24], targets[:-60*24]\n",
    "val_features, val_targets = features[-60*24:], targets[-60*24:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Time to build the network\n",
    "\n",
    "Below you'll build your network. We've built out the structure. You'll implement both the forward pass and backwards pass through the network. You'll also set the hyperparameters: the learning rate, the number of hidden units, and the number of training passes.\n",
    "\n",
    "<img src=\"assets/neural_network.png\" width=300px>\n",
    "\n",
    "The network has two layers, a hidden layer and an output layer. The hidden layer will use the sigmoid function for activations. The output layer has only one node and is used for the regression, the output of the node is the same as the input of the node. That is, the activation function is $f(x)=x$. A function that takes the input signal and generates an output signal, but takes into account the threshold, is called an activation function. We work through each layer of our network calculating the outputs for each neuron. All of the outputs from one layer become inputs to the neurons on the next layer. This process is called *forward propagation*.\n",
    "\n",
    "We use the weights to propagate signals forward from the input to the output layers in a neural network. We use the weights to also propagate error backwards from the output back into the network to update our weights. This is called *backpropagation*.\n",
    "\n",
    "> **Hint:** You'll need the derivative of the output activation function ($f(x) = x$) for the backpropagation implementation. If you aren't familiar with calculus, this function is equivalent to the equation $y = x$. What is the slope of that equation? That is the derivative of $f(x)$.\n",
    "\n",
    "Below, you have these tasks:\n",
    "1. Implement the sigmoid function to use as the activation function. Set `self.activation_function` in `__init__` to your sigmoid function.\n",
    "2. Implement the forward pass in the `train` method.\n",
    "3. Implement the backpropagation algorithm in the `train` method, including calculating the output error.\n",
    "4. Implement the forward pass in the `run` method.\n",
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#############\n",
    "# In the my_answers.py file, fill out the TODO sections as specified\n",
    "#############\n",
    "\n",
    "from my_answers import NeuralNetwork"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def MSE(y, Y):\n",
    "    return np.mean((y-Y)**2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Unit tests\n",
    "\n",
    "Run these unit tests to check the correctness of your network implementation. This will help you be sure your network was implemented correctly before you starting trying to train it. These tests must all be successful to pass the project."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      ".....\n",
      "----------------------------------------------------------------------\n",
      "Ran 5 tests in 0.004s\n",
      "\n",
      "OK\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<unittest.runner.TextTestResult run=5 errors=0 failures=0>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import unittest\n",
    "\n",
    "inputs = np.array([[0.5, -0.2, 0.1]])\n",
    "targets = np.array([[0.4]])\n",
    "test_w_i_h = np.array([[0.1, -0.2],\n",
    "                       [0.4, 0.5],\n",
    "                       [-0.3, 0.2]])\n",
    "test_w_h_o = np.array([[0.3],\n",
    "                       [-0.1]])\n",
    "\n",
    "class TestMethods(unittest.TestCase):\n",
    "    \n",
    "    ##########\n",
    "    # Unit tests for data loading\n",
    "    ##########\n",
    "    \n",
    "    def test_data_path(self):\n",
    "        # Test that file path to dataset has been unaltered\n",
    "        self.assertTrue(data_path.lower() == 'bike-sharing-dataset/hour.csv')\n",
    "        \n",
    "    def test_data_loaded(self):\n",
    "        # Test that data frame loaded\n",
    "        self.assertTrue(isinstance(rides, pd.DataFrame))\n",
    "    \n",
    "    ##########\n",
    "    # Unit tests for network functionality\n",
    "    ##########\n",
    "\n",
    "    def test_activation(self):\n",
    "        network = NeuralNetwork(3, 2, 1, 0.5)\n",
    "        # Test that the activation function is a sigmoid\n",
    "        self.assertTrue(np.all(network.activation_function(0.5) == 1/(1+np.exp(-0.5))))\n",
    "\n",
    "    def test_train(self):\n",
    "        # Test that weights are updated correctly on training\n",
    "        network = NeuralNetwork(3, 2, 1, 0.5)\n",
    "        network.weights_input_to_hidden = test_w_i_h.copy()\n",
    "        network.weights_hidden_to_output = test_w_h_o.copy()\n",
    "        \n",
    "        network.train(inputs, targets)\n",
    "        self.assertTrue(np.allclose(network.weights_hidden_to_output, \n",
    "                                    np.array([[ 0.37275328], \n",
    "                                              [-0.03172939]])))\n",
    "        self.assertTrue(np.allclose(network.weights_input_to_hidden,\n",
    "                                    np.array([[ 0.10562014, -0.20185996], \n",
    "                                              [0.39775194, 0.50074398], \n",
    "                                              [-0.29887597, 0.19962801]])))\n",
    "\n",
    "    def test_run(self):\n",
    "        # Test correctness of run method\n",
    "        network = NeuralNetwork(3, 2, 1, 0.5)\n",
    "        network.weights_input_to_hidden = test_w_i_h.copy()\n",
    "        network.weights_hidden_to_output = test_w_h_o.copy()\n",
    "\n",
    "        self.assertTrue(np.allclose(network.run(inputs), 0.09998924))\n",
    "\n",
    "suite = unittest.TestLoader().loadTestsFromModule(TestMethods())\n",
    "unittest.TextTestRunner().run(suite)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training the network\n",
    "\n",
    "Here you'll set the hyperparameters for the network. The strategy here is to find hyperparameters such that the error on the training set is low, but you're not overfitting to the data. If you train the network too long or have too many hidden nodes, it can become overly specific to the training set and will fail to generalize to the validation set. That is, the loss on the validation set will start increasing as the training set loss drops.\n",
    "\n",
    "You'll also be using a method known as Stochastic Gradient Descent (SGD) to train the network. The idea is that for each training pass, you grab a random sample of the data instead of using the whole data set. You use many more training passes than with normal gradient descent, but each pass is much faster. This ends up training the network more efficiently. You'll learn more about SGD later.\n",
    "\n",
    "### Choose the number of iterations\n",
    "This is the number of batches of samples from the training data we'll use to train the network. The more iterations you use, the better the model will fit the data. However, this process can have sharply diminishing returns and can waste computational resources if you use too many iterations.  You want to find a number here where the network has a low training loss, and the validation loss is at a minimum. The ideal number of iterations would be a level that stops shortly after the validation loss is no longer decreasing.\n",
    "\n",
    "### Choose the learning rate\n",
    "This scales the size of weight updates. If this is too big, the weights tend to explode and the network fails to fit the data. Normally a good choice to start at is 0.1; however, if you effectively divide the learning rate by n_records, try starting out with a learning rate of 1. In either case, if the network has problems fitting the data, try reducing the learning rate. Note that the lower the learning rate, the smaller the steps are in the weight updates and the longer it takes for the neural network to converge.\n",
    "\n",
    "### Choose the number of hidden nodes\n",
    "In a model where all the weights are optimized, the more hidden nodes you have, the more accurate the predictions of the model will be.  (A fully optimized model could have weights of zero, after all.) However, the more hidden nodes you have, the harder it will be to optimize the weights of the model, and the more likely it will be that suboptimal weights will lead to overfitting. With overfitting, the model will memorize the training data instead of learning the true pattern, and won't generalize well to unseen data.  \n",
    "\n",
    "Try a few different numbers and see how it affects the performance. You can look at the losses dictionary for a metric of the network performance. If the number of hidden units is too low, then the model won't have enough space to learn and if it is too high there are too many options for the direction that the learning can take. The trick here is to find the right balance in number of hidden units you choose.  You'll generally find that the best number of hidden nodes to use ends up being between the number of input and output nodes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Progress: 100.0% ... Training loss: 0.072 ... Validation loss: 0.170"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "\n",
    "####################\n",
    "### Set the hyperparameters in you myanswers.py file ###\n",
    "####################\n",
    "\n",
    "from my_answers import iterations, learning_rate, hidden_nodes, output_nodes\n",
    "\n",
    "\n",
    "N_i = train_features.shape[1]\n",
    "network = NeuralNetwork(N_i, hidden_nodes, output_nodes, learning_rate)\n",
    "\n",
    "losses = {'train':[], 'validation':[]}\n",
    "for ii in range(iterations):\n",
    "    # Go through a random batch of 128 records from the training data set\n",
    "    batch = np.random.choice(train_features.index, size=128)\n",
    "    X, y = train_features.iloc[batch].values, train_targets.iloc[batch]['cnt']\n",
    "                             \n",
    "    network.train(X, y)\n",
    "    \n",
    "    # Printing out the training progress\n",
    "    train_loss = MSE(np.array(network.run(train_features)).T, train_targets['cnt'].values)\n",
    "    val_loss = MSE(np.array(network.run(val_features)).T, val_targets['cnt'].values)\n",
    "    sys.stdout.write(\"\\rProgress: {:2.1f}\".format(100 * ii/float(iterations)) \\\n",
    "                     + \"% ... Training loss: \" + str(train_loss)[:5] \\\n",
    "                     + \" ... Validation loss: \" + str(val_loss)[:5])\n",
    "    sys.stdout.flush()\n",
    "    \n",
    "    losses['train'].append(train_loss)\n",
    "    losses['validation'].append(val_loss)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.plot(losses['train'], label='Training loss')\n",
    "plt.plot(losses['validation'], label='Validation loss')\n",
    "plt.legend()\n",
    "_ = plt.ylim()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Check out your predictions\n",
    "\n",
    "Here, use the test data to view how well your network is modeling the data. If something is completely wrong here, make sure each step in your network is implemented correctly."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, ax = plt.subplots(figsize=(8,4))\n",
    "\n",
    "mean, std = scaled_features['cnt']\n",
    "predictions = np.array(network.run(test_features)).T*std + mean\n",
    "ax.plot(predictions[0], label='Prediction')\n",
    "ax.plot((test_targets['cnt']*std + mean).values, label='Data')\n",
    "ax.set_xlim(right=len(predictions))\n",
    "ax.legend()\n",
    "\n",
    "dates = pd.to_datetime(rides.iloc[test_data.index]['dteday'])\n",
    "dates = dates.apply(lambda d: d.strftime('%b %d'))\n",
    "ax.set_xticks(np.arange(len(dates))[12::24])\n",
    "_ = ax.set_xticklabels(dates[12::24], rotation=45)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## OPTIONAL: Thinking about your results(this question will not be evaluated in the rubric).\n",
    " \n",
    "Answer these questions about your results. How well does the model predict the data? Where does it fail? Why does it fail where it does?\n",
    "\n",
    "> **Note:** You can edit the text in this cell by double clicking on it. When you want to render the text, press control + enter\n",
    "\n",
    "#### Your answer below"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}