{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 4: Exploratory data analysis <a name=\"step_4\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Import files & libraries <a name=\"step_4_1\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import libraries\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy import stats as st"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# try-except blocks handle errors that occur from changing file directories\n",
    "\n",
    "try:\n",
    "    company = pd.read_csv('project_sql_result_01.csv')\n",
    "except:\n",
    "    company = pd.read_csv('/datasets/project_sql_result_01.csv')\n",
    "\n",
    "try:\n",
    "    dropoff = pd.read_csv('project_sql_result_04.csv')\n",
    "except:\n",
    "    dropoff = pd.read_csv('/datasets/project_sql_result_04.csv')\n",
    "\n",
    "try:\n",
    "    loop_to_ohare = pd.read_csv('project_sql_result_07.csv')\n",
    "except:\n",
    "    loop_to_ohare = pd.read_csv('/datasets/project_sql_result_07.csv')\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Study general information <a name=\"step_4_2\"></a>"
   ]
  },
  {
   "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>company_name</th>\n",
       "      <th>trips_amount</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Flash Cab</td>\n",
       "      <td>19558</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Taxi Affiliation Services</td>\n",
       "      <td>11422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Medallion Leasin</td>\n",
       "      <td>10367</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Yellow Cab</td>\n",
       "      <td>9888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Taxi Affiliation Service Yellow</td>\n",
       "      <td>9299</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      company_name  trips_amount\n",
       "0                        Flash Cab         19558\n",
       "1        Taxi Affiliation Services         11422\n",
       "2                 Medallion Leasin         10367\n",
       "3                       Yellow Cab          9888\n",
       "4  Taxi Affiliation Service Yellow          9299"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print head for the new 'company' DataFrame\n",
    "\n",
    "company.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>dropoff_location_name</th>\n",
       "      <th>average_trips</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Loop</td>\n",
       "      <td>10727.466667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>River North</td>\n",
       "      <td>9523.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Streeterville</td>\n",
       "      <td>6664.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>West Loop</td>\n",
       "      <td>5163.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>O'Hare</td>\n",
       "      <td>2546.900000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  dropoff_location_name  average_trips\n",
       "0                  Loop   10727.466667\n",
       "1           River North    9523.666667\n",
       "2         Streeterville    6664.666667\n",
       "3             West Loop    5163.666667\n",
       "4                O'Hare    2546.900000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print head for the new 'dropoff' DataFrame\n",
    "\n",
    "dropoff.head()"
   ]
  },
  {
   "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>trips_amount</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>64.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2145.484375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3812.310186</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>20.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>178.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2106.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>19558.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       trips_amount\n",
       "count     64.000000\n",
       "mean    2145.484375\n",
       "std     3812.310186\n",
       "min        2.000000\n",
       "25%       20.750000\n",
       "50%      178.500000\n",
       "75%     2106.500000\n",
       "max    19558.000000"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print some descriptive statistics for 'company'\n",
    "\n",
    "company.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>average_trips</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>94.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>599.953728</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1714.591098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>14.266667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>52.016667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>298.858333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>10727.466667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       average_trips\n",
       "count      94.000000\n",
       "mean      599.953728\n",
       "std      1714.591098\n",
       "min         1.800000\n",
       "25%        14.266667\n",
       "50%        52.016667\n",
       "75%       298.858333\n",
       "max     10727.466667"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print some descriptive statistics for 'dropoff'\n",
    "\n",
    "dropoff.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 64 entries, 0 to 63\n",
      "Data columns (total 2 columns):\n",
      " #   Column        Non-Null Count  Dtype \n",
      "---  ------        --------------  ----- \n",
      " 0   company_name  64 non-null     object\n",
      " 1   trips_amount  64 non-null     int64 \n",
      "dtypes: int64(1), object(1)\n",
      "memory usage: 1.1+ KB\n"
     ]
    }
   ],
   "source": [
    "# print general information for 'company'\n",
    "\n",
    "company.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 94 entries, 0 to 93\n",
      "Data columns (total 2 columns):\n",
      " #   Column                 Non-Null Count  Dtype  \n",
      "---  ------                 --------------  -----  \n",
      " 0   dropoff_location_name  94 non-null     object \n",
      " 1   average_trips          94 non-null     float64\n",
      "dtypes: float64(1), object(1)\n",
      "memory usage: 1.6+ KB\n"
     ]
    }
   ],
   "source": [
    "# print general information for 'dropoff'\n",
    "\n",
    "dropoff.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Check for duplicates <a name=\"step_4_3\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of duplicates in the 'company' DataFrame: 0\n",
      "Number of duplicates in the 'dropoff' DataFrame: 0\n"
     ]
    }
   ],
   "source": [
    "# check both new DataFrames for duplicates\n",
    "\n",
    "print(\"Number of duplicates in the 'company' DataFrame: {}\".format(company.duplicated().sum()))\n",
    "print(\"Number of duplicates in the 'dropoff' DataFrame: {}\".format(dropoff.duplicated().sum()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Changing data types <a name=\"step_4_4\"></a>\n",
    "For large data sets with limited memory resources, it's a good idea to change data types when appropriate. Here, we will change the 'trips_amount' column in the 'company' DataFrame from *float* to *int16* to save memory."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# change 'trips_amount' from float to int16\n",
    "\n",
    "company['trips_amount'] = company['trips_amount'].astype('int16')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Conclusion <a name=\"step_4_4_1\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After our initial assessment of the data, we can say the following:\n",
    "- There are no missing values that need to be filled\n",
    "- There are no duplicates\n",
    "- We can save memory by changing floats to int16 where appropriate"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Identify top 10 neighborhoods by drop-offs <a name=\"step_4_3\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>dropoff_location_name</th>\n",
       "      <th>average_trips</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Loop</td>\n",
       "      <td>10727.466667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>River North</td>\n",
       "      <td>9523.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Streeterville</td>\n",
       "      <td>6664.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>West Loop</td>\n",
       "      <td>5163.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>O'Hare</td>\n",
       "      <td>2546.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Lake View</td>\n",
       "      <td>2420.966667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Grant Park</td>\n",
       "      <td>2068.533333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Museum Campus</td>\n",
       "      <td>1510.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Gold Coast</td>\n",
       "      <td>1364.233333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Sheffield &amp; DePaul</td>\n",
       "      <td>1259.766667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  dropoff_location_name  average_trips\n",
       "0                  Loop   10727.466667\n",
       "1           River North    9523.666667\n",
       "2         Streeterville    6664.666667\n",
       "3             West Loop    5163.666667\n",
       "4                O'Hare    2546.900000\n",
       "5             Lake View    2420.966667\n",
       "6            Grant Park    2068.533333\n",
       "7         Museum Campus    1510.000000\n",
       "8            Gold Coast    1364.233333\n",
       "9    Sheffield & DePaul    1259.766667"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print first 10 rows of 'dropoff' DataFrame sorted by average trips\n",
    "\n",
    "top_10_dropoff = dropoff.sort_values('average_trips', ascending=False).head(10)\n",
    "top_10_dropoff"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plot company vs Number of trips  <a name=\"step_4_4\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x648 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# filter for companies with over 1000 trips & plot\n",
    "\n",
    "company_high_trips = company.query('trips_amount > 1000')\n",
    "\n",
    "plt.rcParams.update({'font.size': 14})\n",
    "\n",
    "ax = company_high_trips.plot(kind='bar',\n",
    "                             x='company_name',\n",
    "                             y='trips_amount',\n",
    "                             figsize=(15, 9),\n",
    "                             title='Company vs Trips',\n",
    "                             fontsize=12,\n",
    "                             grid=True,\n",
    "                             yticks=range(0, 21000, 1000),\n",
    "                             legend=False)\n",
    "\n",
    "ax.set_xlabel('Company name')\n",
    "ax.set_ylabel('Number of trips')\n",
    "                       \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Conclusion  <a name=\"step_4_4_1\"></a>\n",
    "Flash Cab seems to be the dominant taxi company out of all of the companies in our data set. They get the most business, with nearly twice as many trips as the runner-up, Taxi Affiliation Services.\n",
    "\n",
    "There is a long tail of companies that get less than 3000 trips. Maybe we could classify these as 'lower-tier' companies while those with greater than 3000 trips could be classified as 'upper-tier' companies. If we were doing some type of business analysis on these companies, perhaps it would make sense to focus on the upper-tier companies since they get the majority of the business in this industry."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plot top 10 neighborhoods by drop-off count <a name=\"step_4_5\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x648 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot DataFrame from previous step\n",
    "\n",
    "ax = top_10_dropoff.plot(kind='bar',\n",
    "                         x='dropoff_location_name',\n",
    "                         y='average_trips',\n",
    "                         figsize=(15, 9),\n",
    "                         title='Top 10 Neighborhoods by Number of Drop-offs',\n",
    "                         fontsize=12,\n",
    "                         grid=True,\n",
    "                         yticks=range(0, 12000, 500),\n",
    "                         legend=False)\n",
    "\n",
    "ax.set_xlabel('Neighborhood')\n",
    "ax.set_ylabel('Average number of drop-offs')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Conclusion <a name=\"step_4_5_1\"></a>\n",
    "Most customers booking a taxi go to Loop, River North, Streeterville, and West Loop. We can't be certain why this is. Perhaps it's because these places are home to the cities entertainment and nightlife districts, or it could be that they're simply the most populous. We'll need more information in order to formulate and test a hypothesis."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 5: Testing hypotheses <a name=\"step_5\"></a>\n",
    "Next, we'll test the hypothesis:\n",
    "\n",
    "    \"The average duration of rides from the Loop to O'Hare International Airport changes on rainy Saturdays.\"\n",
    "\n",
    "But first, we need to check the new 'loop_to_ohare' DataFrame for missing values, dupicates, and optimal data types."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Study general info for 'loop_to_ohare' DataFrame <a name=\"step_5_1\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>start_ts</th>\n",
       "      <th>weather_conditions</th>\n",
       "      <th>duration_seconds</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2017-11-25 16:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>2410.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2017-11-25 14:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1920.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017-11-25 12:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1543.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2017-11-04 10:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>2512.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2017-11-11 07:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1440.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              start_ts weather_conditions  duration_seconds\n",
       "0  2017-11-25 16:00:00               Good            2410.0\n",
       "1  2017-11-25 14:00:00               Good            1920.0\n",
       "2  2017-11-25 12:00:00               Good            1543.0\n",
       "3  2017-11-04 10:00:00               Good            2512.0\n",
       "4  2017-11-11 07:00:00               Good            1440.0"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print head for'loop_to_ohare'\n",
    "\n",
    "loop_to_ohare.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>duration_seconds</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1068.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2071.731273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>769.461125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1438.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1980.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2580.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>7440.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       duration_seconds\n",
       "count       1068.000000\n",
       "mean        2071.731273\n",
       "std          769.461125\n",
       "min            0.000000\n",
       "25%         1438.250000\n",
       "50%         1980.000000\n",
       "75%         2580.000000\n",
       "max         7440.000000"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print some descriptive statistics for 'loop_to_ohare'\n",
    "\n",
    "loop_to_ohare.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1068 entries, 0 to 1067\n",
      "Data columns (total 3 columns):\n",
      " #   Column              Non-Null Count  Dtype  \n",
      "---  ------              --------------  -----  \n",
      " 0   start_ts            1068 non-null   object \n",
      " 1   weather_conditions  1068 non-null   object \n",
      " 2   duration_seconds    1068 non-null   float64\n",
      "dtypes: float64(1), object(2)\n",
      "memory usage: 25.2+ KB\n"
     ]
    }
   ],
   "source": [
    "# print general information for 'loop_to_ohare'\n",
    "\n",
    "loop_to_ohare.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Check for duplicates <a name=\"step_5_2\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of duplicates in the 'loop_to_ohare' DataFrame: 197\n"
     ]
    }
   ],
   "source": [
    "# check both new 'loop_to_ohare' DataFrame for duplicates\n",
    "\n",
    "print(\"Number of duplicates in the 'loop_to_ohare' DataFrame: {}\".format(loop_to_ohare.duplicated().sum()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>start_ts</th>\n",
       "      <th>weather_conditions</th>\n",
       "      <th>duration_seconds</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>2017-11-11 06:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1260.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>2017-11-11 08:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1380.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>2017-11-04 09:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1380.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>2017-11-11 07:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1380.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>2017-11-04 14:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>3300.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>2017-11-11 08:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1380.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>2017-11-11 09:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1380.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>2017-11-11 10:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1260.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>179</th>\n",
       "      <td>2017-11-11 06:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1260.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>2017-11-04 08:00:00</td>\n",
       "      <td>Good</td>\n",
       "      <td>1323.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                start_ts weather_conditions  duration_seconds\n",
       "62   2017-11-11 06:00:00               Good            1260.0\n",
       "74   2017-11-11 08:00:00               Good            1380.0\n",
       "76   2017-11-04 09:00:00               Good            1380.0\n",
       "117  2017-11-11 07:00:00               Good            1380.0\n",
       "119  2017-11-04 14:00:00               Good            3300.0\n",
       "125  2017-11-11 08:00:00               Good            1380.0\n",
       "126  2017-11-11 09:00:00               Good            1380.0\n",
       "130  2017-11-11 10:00:00               Good            1260.0\n",
       "179  2017-11-11 06:00:00               Good            1260.0\n",
       "190  2017-11-04 08:00:00               Good            1323.0"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print duplicate rows\n",
    "\n",
    "loop_to_ohare[loop_to_ohare.duplicated()].head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are 197 duplicates in the 'loop_to_ohare' DataFrame. It appears as if they're all in the 'duration_seconds' column. Since these are representing the amount of time it took to drive between two areas, it makes sense that it would take the same amount of time for some of these trips. This data should therefore be left alone."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Changing data types <a name=\"step_5_3\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see again that 'duration_seconds' is a *float* when it could be set as *int16* to save memory. Let's do that now."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# change 'duration_seconds' to int16\n",
    "\n",
    "loop_to_ohare['duration_seconds'] = loop_to_ohare['duration_seconds'].astype('int16')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Conclusion <a name=\"step_5_3_1\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After our initial assessment of the data, we can say the following:\n",
    "- There are no missing values that need to be filled\n",
    "- There were duplicates, but they were not due to an error and can be kept in the data set\n",
    "- We can save memory by changing floats to int16 where appropriate"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Finding averages & variances <a name=\"step_5_4\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rainy Saturday trip durations, average: 2427.21\n",
      "Rainy Saturday trip durations, variance: 520294.09\n",
      "\n",
      "All other trip durations, average: 1999.68\n",
      "All other trip durations, variance: 576382.01\n"
     ]
    }
   ],
   "source": [
    "# filter for rainy Saturday trips\n",
    "loop_to_ohare_rainy = loop_to_ohare.query('weather_conditions == \"Bad\"')\n",
    "loop_to_ohare_sats = loop_to_ohare_rainy['start_ts'].str.contains('2017-11-04|2017-11-11|2017-11-18|2017-11-25')\n",
    "loop_to_ohare_rainy_sats = loop_to_ohare_rainy[loop_to_ohare_sats]\n",
    "\n",
    "# average & variance for duration times on rainy Saturdays\n",
    "loop_to_ohare_rainy_sats_avg = loop_to_ohare_rainy_sats['duration_seconds'].mean()\n",
    "loop_to_ohare_rainy_sats_var = loop_to_ohare_rainy_sats['duration_seconds'].var()\n",
    "\n",
    "# filter for all other trips\n",
    "loop_to_ohare_all_others = loop_to_ohare[~loop_to_ohare.index.isin(loop_to_ohare_rainy_sats.index)]\n",
    "\n",
    "# average & variance for duration times on all other days\n",
    "loop_to_ohare_all_avg = loop_to_ohare_all_others['duration_seconds'].mean()\n",
    "loop_to_ohare_all_var = loop_to_ohare_all_others['duration_seconds'].var()\n",
    "\n",
    "print('Rainy Saturday trip durations, average: {:.2f}'.format(loop_to_ohare_rainy_sats_avg))\n",
    "print('Rainy Saturday trip durations, variance: {:.2f}\\n'.format(loop_to_ohare_rainy_sats_var))\n",
    "\n",
    "print('All other trip durations, average: {:.2f}'.format(loop_to_ohare_all_avg))\n",
    "print('All other trip durations, variance: {:.2f}'.format(loop_to_ohare_all_var))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Forming the null & alternative hypotheses <a name=\"step_5_5\"></a>\n",
    "After calculating means and variances for trips taken on rainy Saturdays and for all other trips, we can form the null hypothesis. It appears that **the average trip duration for rainy Saturdays is significantly higher than the average duration for all other days**. This is our null hypothesis.\n",
    "\n",
    "The alternative hypothesis is that this is due to randoness and **the averages are actually not different from each other**. To determine whether or not this difference is due to randomness or not, we can perform a p-test. Variances between the two data sets are pretty close, so for our p-test, we can assume equal variance.\n",
    "\n",
    "For our alpha value (critical statistical significance level) we **can choose 0.05**. This means **we can be 95% confident** that our analysis is correct."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Run the P-test <a name=\"step_5_6\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Null hypothesis:\n",
      "   The average duration of rides from the Loop to O'Hare International Airport changes on rainy Saturdays.\n",
      "\n",
      "Alternative hypothesis:\n",
      "   The average duration of rides from the Loop to O'Hare International Airport remains the same on rainy Saturdays.\n",
      "\n",
      "p-value:  6.517970327099473e-12\n",
      "We reject the null hypothesis\n"
     ]
    }
   ],
   "source": [
    "# run p-test\n",
    "\n",
    "results = st.ttest_ind(loop_to_ohare_rainy_sats['duration_seconds'], loop_to_ohare_all_others['duration_seconds'], equal_var=True)\n",
    "\n",
    "alpha = 0.05\n",
    "\n",
    "print('Null hypothesis:\\n   The average duration of rides from the Loop to O\\'Hare International Airport changes on rainy Saturdays.\\n')\n",
    "print('Alternative hypothesis:\\n   The average duration of rides from the Loop to O\\'Hare International Airport remains the same on rainy Saturdays.\\n')\n",
    "print('p-value: ', results.pvalue)\n",
    "\n",
    "if (results.pvalue < alpha):\n",
    "    print(\"We reject the null hypothesis\")\n",
    "else:\n",
    "    print(\"We can't reject the null hypothesis\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Conclusion <a name=\"step_5_6_1\"></a>\n",
    "The p-value for our p-test fell well below our critical statistical significance value of 0.05, meaning we can reject the null hypothesis in favor of the alternative hypothesis. This means that the difference in average trip durations as calculated previously is due to randomness, and in reality they are not statistically different."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 6: General Conclusion <a name=\"step_6\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From a business standpoint, we can do a few things based on the data that will result in higher revenues. Our main competition is Flash Cab. They're the leader in terms of number of trips and we should focus on providing more value to customers than they currently do. Of course, this will require more data and research to achieve detailed action items.\n",
    "\n",
    "The top neighborhoods are Loop, River North, Streeterville, and West Loop. These are all closely grouped together and represent the most populous areas. Perhaps it would be a good idea to focus drivers and resources into these areas.\n",
    "\n",
    "A large number of rides end in O'Hare, which is where Chicago's largest airport was built. This massive airport is the 6th-busiest in the world and served 83 million passengers in 2018. It makes sense that many of these rides also originate in the Loop, the main business district in Chicago.\n",
    "\n",
    "From our p-test, we determined that rides from Loop to O'Hare on rainy Saturdays are not statistically longer in duration than rides on all other days. It could be because Satudays have much less traffic than weekdays, which lessens the ride duration. Rain and bad weather is expected to slow rides down, so perhaps this combination evens things out. In this case, we don't need to alter our business strategy for these days."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}