03-merging-data-and-EDA.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Notebook III - Merging Data & EDA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.formula.api import ols\n",
    "\n",
    "# graphing\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read trips data\n",
    "trips = pd.read_csv('./cleaned_data/trips_cleaned_aggregated.csv')\n",
    "\n",
    "# read weather data\n",
    "weather = pd.read_csv('./cleaned_data/weather_cleaned.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "#### NOTE: \n",
    "The original goal of this notebook was to merge cleaned trips and weather data to create a full dataset that I would use to compare/contrast the effects of several metrics on trip data (duration, revenue, count). However, upon fixing the trips dataset in Notebook I after the epiphany I had (section 1e), I realize that there are **many more caveats** that need to be addressed prior to conducting any EDA and examining relationships between proposed independent variables and the intended outcome variable, daily revenue. <br><br>\n",
    "\n",
    "For example, below I read in the cleaned dataset with aggregated trip data. The data is set up to have daily rows (730) from 2014-2015 for every station and aggregated trip information (0 if no trips were taken). The issue is that, as it stands, there is no way to confirm whether the station just had no demand for consecutive \"0-count\" days, or if the station had simply not been active at that time. Please refer to the below preview of \"6th and Navasota St.\":\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "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>date</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>year</th>\n",
       "      <th>duration_minutes</th>\n",
       "      <th>trip_revenue</th>\n",
       "      <th>trip_count</th>\n",
       "      <th>day_of_week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>2014-01-29</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>29</td>\n",
       "      <td>2014</td>\n",
       "      <td>14.0</td>\n",
       "      <td>2.4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>2014-01-30</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>2014</td>\n",
       "      <td>41.0</td>\n",
       "      <td>7.1</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>2014-01-31</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>31</td>\n",
       "      <td>2014</td>\n",
       "      <td>49.0</td>\n",
       "      <td>8.9</td>\n",
       "      <td>4.0</td>\n",
       "      <td>Friday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>2014-02-01</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2014</td>\n",
       "      <td>1271.0</td>\n",
       "      <td>141.1</td>\n",
       "      <td>14.0</td>\n",
       "      <td>Saturday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>2014-02-04</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2014</td>\n",
       "      <td>209.0</td>\n",
       "      <td>21.9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Tuesday</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>176</th>\n",
       "      <td>2014-06-26</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>6</td>\n",
       "      <td>26</td>\n",
       "      <td>2014</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>2014-06-27</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>6</td>\n",
       "      <td>27</td>\n",
       "      <td>2014</td>\n",
       "      <td>124.0</td>\n",
       "      <td>21.4</td>\n",
       "      <td>9.0</td>\n",
       "      <td>Friday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>178</th>\n",
       "      <td>2014-06-28</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>6</td>\n",
       "      <td>28</td>\n",
       "      <td>2014</td>\n",
       "      <td>520.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>Saturday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>179</th>\n",
       "      <td>2014-06-29</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>6</td>\n",
       "      <td>29</td>\n",
       "      <td>2014</td>\n",
       "      <td>679.0</td>\n",
       "      <td>70.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>Sunday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>180</th>\n",
       "      <td>2014-06-30</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>6</td>\n",
       "      <td>30</td>\n",
       "      <td>2014</td>\n",
       "      <td>17.0</td>\n",
       "      <td>3.7</td>\n",
       "      <td>2.0</td>\n",
       "      <td>Monday</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>137 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date  start_station_id  start_station_name  month  day  year  \\\n",
       "28   2014-01-29              1002  6th & Navasota St.      1   29  2014   \n",
       "29   2014-01-30              1002  6th & Navasota St.      1   30  2014   \n",
       "30   2014-01-31              1002  6th & Navasota St.      1   31  2014   \n",
       "31   2014-02-01              1002  6th & Navasota St.      2    1  2014   \n",
       "34   2014-02-04              1002  6th & Navasota St.      2    4  2014   \n",
       "..          ...               ...                 ...    ...  ...   ...   \n",
       "176  2014-06-26              1002  6th & Navasota St.      6   26  2014   \n",
       "177  2014-06-27              1002  6th & Navasota St.      6   27  2014   \n",
       "178  2014-06-28              1002  6th & Navasota St.      6   28  2014   \n",
       "179  2014-06-29              1002  6th & Navasota St.      6   29  2014   \n",
       "180  2014-06-30              1002  6th & Navasota St.      6   30  2014   \n",
       "\n",
       "     duration_minutes  trip_revenue  trip_count day_of_week  \n",
       "28               14.0           2.4         1.0   Wednesday  \n",
       "29               41.0           7.1         3.0    Thursday  \n",
       "30               49.0           8.9         4.0      Friday  \n",
       "31             1271.0         141.1        14.0    Saturday  \n",
       "34              209.0          21.9         1.0     Tuesday  \n",
       "..                ...           ...         ...         ...  \n",
       "176               5.0           1.5         1.0    Thursday  \n",
       "177             124.0          21.4         9.0      Friday  \n",
       "178             520.0          59.0         7.0    Saturday  \n",
       "179             679.0          70.9         3.0      Sunday  \n",
       "180              17.0           3.7         2.0      Monday  \n",
       "\n",
       "[137 rows x 10 columns]"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trips[(trips['start_station_id'] == 1002) & (trips['duration_minutes'] > 0)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here, I have filtered on all non-0 data for this station. This means that this station had no rides until January 29th, 2014, and basically ceased getting rides after June 30th, 2014. On all other days in the 2-year time frame, there were no trips taken from \"6th & Navasota\". It is highly unlikely that the station remained that unpopular for all other days. What is more likely is that the bike company either installed it at a certain time, or removed it at another time. This same assumption can be stretched to all 60 stations in our dataset. We simply do not know what is causing gaps, however, longer gaps we can assume are caused by deactivation of the station and not a decline in demand. A gap or a day or two is more reasonable, however. <br><br>\n",
    "\n",
    "That being said, for a lot of the data where stations had no rides for long stretches, there is still daily weather data that I merged below. When conducting EDA to extract relationships between these independent variables and the outcome, revenue, we cannot draw any meaningful conclusions since this data is associated with other factors not being picked up by our dataset. It's not necessary that some kind of weather metric affected the \\$0 revenue that 6th & Navasota had on 1/1/2014. It simply could just not have been an active station at that point and was installed by the company later on. <br><br>\n",
    "\n",
    "I would love to discuss this further on how to better capture such relationships with panel data. My current thought process would be to filter on some station individually, effectively reducing the dataset to a time-series and filtering further on dates when the station became active. I will attempt to do so in place of my initial EDA analysis below. However, for modeling purposes for now, I will forego adding other metrics until I am more comfortable on how to obtain meaningful insights without the confounding any associations as I outlined above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [],
   "source": [
    "##### TO DO - Future action list: ##### \n",
    "\n",
    "### filter on 1-2 different stations (in predictions) separately and conduct brief EDA there --> see if correlations differ\n",
    "\n",
    "### try to filter the dates on when we think the data might begin \n",
    "\n",
    "### provide suggestions on how to do this uniformly for other stations"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "### 3a. Merge Weather Data with Trips"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "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>date</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>year</th>\n",
       "      <th>duration_minutes</th>\n",
       "      <th>trip_revenue</th>\n",
       "      <th>trip_count</th>\n",
       "      <th>day_of_week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2014-01-02</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014-01-03</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Friday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014-01-04</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Saturday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014-01-05</td>\n",
       "      <td>1002</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sunday</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date  start_station_id  start_station_name  month  day  year  \\\n",
       "0  2014-01-01              1002  6th & Navasota St.      1    1  2014   \n",
       "1  2014-01-02              1002  6th & Navasota St.      1    2  2014   \n",
       "2  2014-01-03              1002  6th & Navasota St.      1    3  2014   \n",
       "3  2014-01-04              1002  6th & Navasota St.      1    4  2014   \n",
       "4  2014-01-05              1002  6th & Navasota St.      1    5  2014   \n",
       "\n",
       "   duration_minutes  trip_revenue  trip_count day_of_week  \n",
       "0               0.0           0.0         0.0   Wednesday  \n",
       "1               0.0           0.0         0.0    Thursday  \n",
       "2               0.0           0.0         0.0      Friday  \n",
       "3               0.0           0.0         0.0    Saturday  \n",
       "4               0.0           0.0         0.0      Sunday  "
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trips.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "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>date</th>\n",
       "      <th>temphigh_f</th>\n",
       "      <th>tempavg_f</th>\n",
       "      <th>templow_f</th>\n",
       "      <th>humidityhigh_percent</th>\n",
       "      <th>humidityavg_percent</th>\n",
       "      <th>humiditylow_percent</th>\n",
       "      <th>visibilityhigh_miles</th>\n",
       "      <th>visibilityavg_miles</th>\n",
       "      <th>visibilitylow_miles</th>\n",
       "      <th>windhigh_mph</th>\n",
       "      <th>windavg_mph</th>\n",
       "      <th>windgust_mph</th>\n",
       "      <th>precipitation_inches</th>\n",
       "      <th>fog</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>thunderstorm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>69.0</td>\n",
       "      <td>54.0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2014-01-02</td>\n",
       "      <td>55.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>31.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014-01-03</td>\n",
       "      <td>58.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014-01-04</td>\n",
       "      <td>71.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>47.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014-01-05</td>\n",
       "      <td>59.0</td>\n",
       "      <td>47.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>31.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date  temphigh_f  tempavg_f  templow_f  humidityhigh_percent  \\\n",
       "0  2014-01-01        69.0       54.0       39.0                  83.0   \n",
       "1  2014-01-02        55.0       44.0       33.0                  83.0   \n",
       "2  2014-01-03        58.0       43.0       28.0                  75.0   \n",
       "3  2014-01-04        71.0       57.0       42.0                  89.0   \n",
       "4  2014-01-05        59.0       47.0       34.0                  87.0   \n",
       "\n",
       "   humidityavg_percent  humiditylow_percent  visibilityhigh_miles  \\\n",
       "0                 68.0                 52.0                  10.0   \n",
       "1                 55.0                 26.0                  10.0   \n",
       "2                 49.0                 22.0                  10.0   \n",
       "3                 68.0                 47.0                  10.0   \n",
       "4                 59.0                 31.0                  10.0   \n",
       "\n",
       "   visibilityavg_miles  visibilitylow_miles  windhigh_mph  windavg_mph  \\\n",
       "0                 10.0                  8.0          13.0          4.0   \n",
       "1                 10.0                  9.0          21.0          8.0   \n",
       "2                 10.0                 10.0          14.0          4.0   \n",
       "3                 10.0                  8.0          16.0          7.0   \n",
       "4                 10.0                  4.0          21.0         10.0   \n",
       "\n",
       "   windgust_mph  precipitation_inches  fog  rain  snow  thunderstorm  \n",
       "0          22.0                   0.0    0     0     0             0  \n",
       "1          31.0                   0.0    0     0     0             0  \n",
       "2          21.0                   0.0    0     0     0             0  \n",
       "3          28.0                   0.0    0     0     0             0  \n",
       "4          34.0                   0.0    0     0     0             0  "
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(43800, 10) (1096, 18)\n"
     ]
    }
   ],
   "source": [
    "print(trips.shape, weather.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "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>date</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>year</th>\n",
       "      <th>duration_minutes</th>\n",
       "      <th>trip_revenue</th>\n",
       "      <th>trip_count</th>\n",
       "      <th>day_of_week</th>\n",
       "      <th>...</th>\n",
       "      <th>visibilityavg_miles</th>\n",
       "      <th>visibilitylow_miles</th>\n",
       "      <th>windhigh_mph</th>\n",
       "      <th>windavg_mph</th>\n",
       "      <th>windgust_mph</th>\n",
       "      <th>precipitation_inches</th>\n",
       "      <th>fog</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>thunderstorm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1002.0</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1003.0</td>\n",
       "      <td>8th &amp; Guadalupe</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1005.0</td>\n",
       "      <td>State Parking Garage @ Brazos &amp; 18th</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1006.0</td>\n",
       "      <td>Zilker Park West</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1007.0</td>\n",
       "      <td>Lavaca &amp; 6th</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44161</th>\n",
       "      <td>2016-12-27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44162</th>\n",
       "      <td>2016-12-28</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>9.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44163</th>\n",
       "      <td>2016-12-29</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44164</th>\n",
       "      <td>2016-12-30</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44165</th>\n",
       "      <td>2016-12-31</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>44166 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             date  start_station_id                    start_station_name  \\\n",
       "0      2014-01-01            1002.0                    6th & Navasota St.   \n",
       "1      2014-01-01            1003.0                       8th & Guadalupe   \n",
       "2      2014-01-01            1005.0  State Parking Garage @ Brazos & 18th   \n",
       "3      2014-01-01            1006.0                      Zilker Park West   \n",
       "4      2014-01-01            1007.0                          Lavaca & 6th   \n",
       "...           ...               ...                                   ...   \n",
       "44161  2016-12-27               NaN                                   NaN   \n",
       "44162  2016-12-28               NaN                                   NaN   \n",
       "44163  2016-12-29               NaN                                   NaN   \n",
       "44164  2016-12-30               NaN                                   NaN   \n",
       "44165  2016-12-31               NaN                                   NaN   \n",
       "\n",
       "       month  day    year  duration_minutes  trip_revenue  trip_count  \\\n",
       "0        1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "1        1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "2        1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "3        1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "4        1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "...      ...  ...     ...               ...           ...         ...   \n",
       "44161    NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44162    NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44163    NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44164    NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44165    NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "\n",
       "      day_of_week  ...  visibilityavg_miles  visibilitylow_miles  \\\n",
       "0       Wednesday  ...                 10.0                  8.0   \n",
       "1       Wednesday  ...                 10.0                  8.0   \n",
       "2       Wednesday  ...                 10.0                  8.0   \n",
       "3       Wednesday  ...                 10.0                  8.0   \n",
       "4       Wednesday  ...                 10.0                  8.0   \n",
       "...           ...  ...                  ...                  ...   \n",
       "44161         NaN  ...                 10.0                 10.0   \n",
       "44162         NaN  ...                  9.0                  4.0   \n",
       "44163         NaN  ...                 10.0                 10.0   \n",
       "44164         NaN  ...                 10.0                 10.0   \n",
       "44165         NaN  ...                 10.0                  4.0   \n",
       "\n",
       "       windhigh_mph  windavg_mph  windgust_mph  precipitation_inches  fog  \\\n",
       "0              13.0          4.0          22.0                   0.0    0   \n",
       "1              13.0          4.0          22.0                   0.0    0   \n",
       "2              13.0          4.0          22.0                   0.0    0   \n",
       "3              13.0          4.0          22.0                   0.0    0   \n",
       "4              13.0          4.0          22.0                   0.0    0   \n",
       "...             ...          ...           ...                   ...  ...   \n",
       "44161           7.0          1.0          11.0                   0.0    0   \n",
       "44162          12.0          3.0          20.0                   0.0    0   \n",
       "44163          18.0          9.0          30.0                   0.0    0   \n",
       "44164          12.0          4.0          16.0                   0.0    0   \n",
       "44165          10.0          3.0          18.0                   0.0    0   \n",
       "\n",
       "       rain  snow  thunderstorm  \n",
       "0         0     0             0  \n",
       "1         0     0             0  \n",
       "2         0     0             0  \n",
       "3         0     0             0  \n",
       "4         0     0             0  \n",
       "...     ...   ...           ...  \n",
       "44161     0     0             0  \n",
       "44162     0     0             0  \n",
       "44163     0     0             0  \n",
       "44164     0     0             0  \n",
       "44165     1     0             0  \n",
       "\n",
       "[44166 rows x 27 columns]"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# merge\n",
    "    # how = 'right' --> this will ensure data for 2016 is pulled from weather\n",
    "merged_data = pd.merge(trips, weather, on = 'date', how = 'right')\n",
    "merged_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "# move date column to the beginning\n",
    "date_col = merged_data.pop('date')\n",
    "merged_data.insert(0, 'date', date_col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "# fixing column data types again\n",
    "merged_data[['start_station_id','month','day','year']] = merged_data[['start_station_id','month','day','year']].astype(object) \n",
    "\n",
    "# the 'type' will be changed to object, but cannot convert to int first to rid of the decimal (NaNs present for 2016 data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "### 3b. EDA on Numeric Features\n",
    "\n",
    "The goal of this section is to determine which numeric variables are most closely associated with our intended outcome, `trip_revenue`. Creating a correlation matrix to check the correlation between the independent variables will also give us a better idea of which variables are strongly correlated with one another. This will allow us to drop features and keep the ones we feel can best assist in forecasting `trip_revenue`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['duration_minutes',\n",
       " 'trip_revenue',\n",
       " 'trip_count',\n",
       " 'temphigh_f',\n",
       " 'tempavg_f',\n",
       " 'templow_f',\n",
       " 'humidityhigh_percent',\n",
       " 'humidityavg_percent',\n",
       " 'humiditylow_percent',\n",
       " 'visibilityhigh_miles',\n",
       " 'visibilityavg_miles',\n",
       " 'visibilitylow_miles',\n",
       " 'windhigh_mph',\n",
       " 'windavg_mph',\n",
       " 'windgust_mph',\n",
       " 'precipitation_inches',\n",
       " 'fog',\n",
       " 'rain',\n",
       " 'snow',\n",
       " 'thunderstorm']"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# identifying numeric columns\n",
    "numeric_cols = [var for var in merged_data.columns if merged_data[var].dtype != 'O']\n",
    "numeric_cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [],
   "source": [
    "# corr matrix\n",
    "corr_on_trips = merged_data[numeric_cols].corr()[['duration_minutes', 'trip_revenue', 'trip_count']]\n",
    "\n",
    "# making a mask for matrix\n",
    "mask = np.triu(np.ones_like(corr_on_trips, dtype = bool))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plotting corr matrix\n",
    "plt.figure(figsize = (8,6))\n",
    "sns.heatmap(corr_on_trips, mask = mask, cmap = 'coolwarm', annot = True, vmin = -1, vmax = 1)\n",
    "plt.title('Correlation Matrix: Weather vs. Trip Data');\n",
    "\n",
    "plt.savefig('./graphs/correlation_matrix.jpeg', dpi = 1080)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### ***Disclaimer***\n",
    "To reiterate, the correlations here cannot be relied upon nor provide us with an accurate sense of the relationship between these variables. I have outlined this in the opening section of this notebook. <br><br>\n",
    "\n",
    "#### Future To Do: \n",
    "- Redo correlation matrix, and filter only on one station\n",
    "- Figure out way to conduct this analysis for all stations\n",
    "- Need to factor in different start dates for stations (some stations do not have any data for several months)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "### 3c. EDA on Categorical Features\n",
    "\n",
    "#### ***Disclaimer***\n",
    "The EDA here is also affected by the fix in the dataset. There are many days with no trips, but some of these values should not affect averages if the stations simply didn't exist at the time. I will leave the conducted EDA to inspire ideas on how to examine the data in the future. Again, looking at the data after filtering on a specific station may prove insightful and allow comparison between two stations. <br>\n",
    "\n",
    "#### Other EDA Ideas I'd Like to Do:\n",
    "1. Rush hour times? - Examining rides by hour of day (requires bucketing of the `start_time` variable in raw trips data\n",
    "2. Downtown vs. College vs. Recreational - Comparing trip metrics by assigning and evaluating station type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "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>date</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>month</th>\n",
       "      <th>day</th>\n",
       "      <th>year</th>\n",
       "      <th>duration_minutes</th>\n",
       "      <th>trip_revenue</th>\n",
       "      <th>trip_count</th>\n",
       "      <th>day_of_week</th>\n",
       "      <th>...</th>\n",
       "      <th>visibilityavg_miles</th>\n",
       "      <th>visibilitylow_miles</th>\n",
       "      <th>windhigh_mph</th>\n",
       "      <th>windavg_mph</th>\n",
       "      <th>windgust_mph</th>\n",
       "      <th>precipitation_inches</th>\n",
       "      <th>fog</th>\n",
       "      <th>rain</th>\n",
       "      <th>snow</th>\n",
       "      <th>thunderstorm</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1002.0</td>\n",
       "      <td>6th &amp; Navasota St.</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1003.0</td>\n",
       "      <td>8th &amp; Guadalupe</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1005.0</td>\n",
       "      <td>State Parking Garage @ Brazos &amp; 18th</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1006.0</td>\n",
       "      <td>Zilker Park West</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2014-01-01</td>\n",
       "      <td>1007.0</td>\n",
       "      <td>Lavaca &amp; 6th</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2014.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Wednesday</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44161</th>\n",
       "      <td>2016-12-27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44162</th>\n",
       "      <td>2016-12-28</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>9.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44163</th>\n",
       "      <td>2016-12-29</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44164</th>\n",
       "      <td>2016-12-30</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44165</th>\n",
       "      <td>2016-12-31</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>44166 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             date start_station_id                    start_station_name  \\\n",
       "0      2014-01-01           1002.0                    6th & Navasota St.   \n",
       "1      2014-01-01           1003.0                       8th & Guadalupe   \n",
       "2      2014-01-01           1005.0  State Parking Garage @ Brazos & 18th   \n",
       "3      2014-01-01           1006.0                      Zilker Park West   \n",
       "4      2014-01-01           1007.0                          Lavaca & 6th   \n",
       "...           ...              ...                                   ...   \n",
       "44161  2016-12-27              NaN                                   NaN   \n",
       "44162  2016-12-28              NaN                                   NaN   \n",
       "44163  2016-12-29              NaN                                   NaN   \n",
       "44164  2016-12-30              NaN                                   NaN   \n",
       "44165  2016-12-31              NaN                                   NaN   \n",
       "\n",
       "      month  day    year  duration_minutes  trip_revenue  trip_count  \\\n",
       "0       1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "1       1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "2       1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "3       1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "4       1.0  1.0  2014.0               0.0           0.0         0.0   \n",
       "...     ...  ...     ...               ...           ...         ...   \n",
       "44161   NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44162   NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44163   NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44164   NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "44165   NaN  NaN     NaN               NaN           NaN         NaN   \n",
       "\n",
       "      day_of_week  ...  visibilityavg_miles  visibilitylow_miles  \\\n",
       "0       Wednesday  ...                 10.0                  8.0   \n",
       "1       Wednesday  ...                 10.0                  8.0   \n",
       "2       Wednesday  ...                 10.0                  8.0   \n",
       "3       Wednesday  ...                 10.0                  8.0   \n",
       "4       Wednesday  ...                 10.0                  8.0   \n",
       "...           ...  ...                  ...                  ...   \n",
       "44161         NaN  ...                 10.0                 10.0   \n",
       "44162         NaN  ...                  9.0                  4.0   \n",
       "44163         NaN  ...                 10.0                 10.0   \n",
       "44164         NaN  ...                 10.0                 10.0   \n",
       "44165         NaN  ...                 10.0                  4.0   \n",
       "\n",
       "       windhigh_mph  windavg_mph  windgust_mph  precipitation_inches  fog  \\\n",
       "0              13.0          4.0          22.0                   0.0    0   \n",
       "1              13.0          4.0          22.0                   0.0    0   \n",
       "2              13.0          4.0          22.0                   0.0    0   \n",
       "3              13.0          4.0          22.0                   0.0    0   \n",
       "4              13.0          4.0          22.0                   0.0    0   \n",
       "...             ...          ...           ...                   ...  ...   \n",
       "44161           7.0          1.0          11.0                   0.0    0   \n",
       "44162          12.0          3.0          20.0                   0.0    0   \n",
       "44163          18.0          9.0          30.0                   0.0    0   \n",
       "44164          12.0          4.0          16.0                   0.0    0   \n",
       "44165          10.0          3.0          18.0                   0.0    0   \n",
       "\n",
       "       rain  snow  thunderstorm  \n",
       "0         0     0             0  \n",
       "1         0     0             0  \n",
       "2         0     0             0  \n",
       "3         0     0             0  \n",
       "4         0     0             0  \n",
       "...     ...   ...           ...  \n",
       "44161     0     0             0  \n",
       "44162     0     0             0  \n",
       "44163     0     0             0  \n",
       "44164     0     0             0  \n",
       "44165     1     0             0  \n",
       "\n",
       "[44166 rows x 27 columns]"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Day of the Week vs. Avg. Revenue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "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>day_of_week</th>\n",
       "      <th>trip_revenue</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Friday</td>\n",
       "      <td>30.036538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Monday</td>\n",
       "      <td>19.709119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Saturday</td>\n",
       "      <td>49.521987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Sunday</td>\n",
       "      <td>37.938942</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Thursday</td>\n",
       "      <td>19.359968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Tuesday</td>\n",
       "      <td>16.888526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Wednesday</td>\n",
       "      <td>16.882778</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  day_of_week  trip_revenue\n",
       "0      Friday     30.036538\n",
       "1      Monday     19.709119\n",
       "2    Saturday     49.521987\n",
       "3      Sunday     37.938942\n",
       "4    Thursday     19.359968\n",
       "5     Tuesday     16.888526\n",
       "6   Wednesday     16.882778"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "day_of_week_revenue = merged_data.groupby('day_of_week')['trip_revenue'].mean().reset_index()\n",
    "day_of_week_revenue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# graphing\n",
    "plt.figure(figsize = (10, 6))\n",
    "sns.barplot(x = 'day_of_week', y = 'trip_revenue', data = day_of_week_revenue, order = ['Monday', 'Tuesday', 'Wednesday', 'Thursday',\n",
    "                                                                                       'Friday', 'Saturday', 'Sunday'])\n",
    "plt.title('Average Daily Revenue by Day of Week (2014-2015)')\n",
    "plt.xlabel('Day')\n",
    "plt.ylabel('Revenue ($)');\n",
    "\n",
    "plt.savefig('./graphs/day_vs_revenue.jpeg', dpi = 1080)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Visually, we can see that there may be a trend present. This might suggest that the data is cyclical by week as it seems to peak in the weekends, and drop during mid-week. This gives an interesting clue about seasonality prior to modeling. <br><br>\n",
    "\n",
    "***FOR FUTURE:***\n",
    "I have not yet gotten to this, but I would like to conduct an ANOVA test here to check to see if the differences in average revenue for the days are statistically significant."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Month vs. Avg Revenue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "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>month</th>\n",
       "      <th>trip_revenue</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>10.736425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>16.458631</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.0</td>\n",
       "      <td>50.881129</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>33.317361</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>32.601129</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.0</td>\n",
       "      <td>28.031889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7.0</td>\n",
       "      <td>28.366344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>22.498118</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9.0</td>\n",
       "      <td>24.080750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10.0</td>\n",
       "      <td>41.177742</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11.0</td>\n",
       "      <td>21.545250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12.0</td>\n",
       "      <td>15.209785</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    month  trip_revenue\n",
       "0     1.0     10.736425\n",
       "1     2.0     16.458631\n",
       "2     3.0     50.881129\n",
       "3     4.0     33.317361\n",
       "4     5.0     32.601129\n",
       "5     6.0     28.031889\n",
       "6     7.0     28.366344\n",
       "7     8.0     22.498118\n",
       "8     9.0     24.080750\n",
       "9    10.0     41.177742\n",
       "10   11.0     21.545250\n",
       "11   12.0     15.209785"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "month_revenue = merged_data.groupby('month')['trip_revenue'].mean().reset_index()\n",
    "month_revenue"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# graphing\n",
    "plt.figure(figsize = (10, 6))\n",
    "sns.barplot(x = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct',\n",
    "                'Nov', 'Dec'], y = 'trip_revenue', data = month_revenue)\n",
    "plt.title('Average Daily Revenue by Month (2014-2015)')\n",
    "plt.xlabel('Month')\n",
    "plt.ylabel('Revenue ($)');\n",
    "\n",
    "plt.savefig('./graphs/month_vs_revenue.jpeg', dpi = 1080)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [],
   "source": [
    "# saving the merged data\n",
    "merged_data.to_csv('./cleaned_data/trips_weather_merged.csv', index = False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:sktimeenv]",
   "language": "python",
   "name": "conda-env-sktimeenv-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}