Data_Wrangling_Project_Starter (1).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GNIwe5N7s0e_"
   },
   "source": [
    "# Real-world Data Wrangling"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_BG63Tpg8ep_"
   },
   "source": [
    "In this project, you will apply the skills you acquired in the course to gather and wrangle real-world data with two datasets of your choice.\n",
    "\n",
    "You will retrieve and extract the data, assess the data programmatically and visually, accross elements of data quality and structure, and implement a cleaning strategy for the data. You will then store the updated data into your selected database/data store, combine the data, and answer a research question with the datasets.\n",
    "\n",
    "Throughout the process, you are expected to:\n",
    "\n",
    "1. Explain your decisions towards methods used for gathering, assessing, cleaning, storing, and answering the research question\n",
    "2. Write code comments so your code is more readable"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lDYDkH-Zs7Nn"
   },
   "source": [
    "## 1. Gather data\n",
    "\n",
    "In this section, you will extract data using two different data gathering methods and combine the data. Use at least two different types of data-gathering methods."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "LbN7z7rcuqpO"
   },
   "source": [
    "### **1.1.** Problem Statement\n",
    "In 2-4 sentences, explain the kind of problem you want to look at and the datasets you will be wrangling for this project."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gi6swhjSYqu2"
   },
   "source": [
    "The association between weather and bicycle rentals is the issue I wish to investigate. For this project, I will manage two datasets: the Capital Bikeshare dataset for bicycle rentals, which offers details about bike rentals such as start time, end time, and rental duration; and the OpenWeatherMap API weather data, which includes elements such as temperature, humidity, and precipitation. I want to learn how the weather affects the demand for bike rentals and find any relationships between weather variables and rental trends by studying these information."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8AQfBAdUypMm"
   },
   "source": [
    "### **1.2.** Gather at least two datasets using two different data gathering methods\n",
    "\n",
    "List of data gathering methods:\n",
    "\n",
    "- Download data manually\n",
    "- Programmatically downloading files\n",
    "- Gather data by accessing APIs\n",
    "- Gather and extract data from HTML files using BeautifulSoup\n",
    "- Extract data from a SQL database\n",
    "\n",
    "Each dataset must have at least two variables, and have greater than 500 data samples within each dataset.\n",
    "\n",
    "For each dataset, briefly describe why you picked the dataset and the gathering method (2-3 full sentences), including the names and significance of the variables in the dataset. Show your work (e.g., if using an API to download the data, please include a snippet of your code). \n",
    "\n",
    "Load the dataset programmtically into this notebook."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7e6gS0wL1KTu"
   },
   "source": [
    "#### **Dataset 1**\n",
    "\n",
    "Type: CSV File\n",
    "\n",
    "Method: Download  data manually from the Capital Bikeshare website (https://www.capitalbikeshare.com/system-data).\n",
    "\n",
    "Variables: The dataset contains information about bike rentals, including the ride ID, rideable type (e.g., classic bike,electric bike), start time, end time, start station name, start station ID, end station name, end station ID, start latitude, start longitude, end latitude, end longitude, and member type (casual or member). These variables provide details about bike rides and are important for analyzing rental patterns and their correlation with weather conditions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 331,
   "metadata": {
    "id": "Su8E0uLuYkHU"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Load the bicycle rental data from the CSV file\n",
    "bicycle_data = pd.read_csv('202306-capitalbikeshare-tripdata.csv')\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "hoUjq1tPzz7P"
   },
   "source": [
    "#### Dataset 2\n",
    "Weather Data\n",
    "Type: API \n",
    "\n",
    "Method: The data was gathered using the \"API\" method from  https://openweathermap.org/ source.\n",
    "\n",
    "Dataset variables:\n",
    "\n",
    "*  temperature, humidity, wind speed, precipitation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 332,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "api_key = \"6ffd1c1304e0b7b38066eede83041047\"\n",
    "city = \"VIRGINIA\"\n",
    "\n",
    "url = f\"http://api.openweathermap.org/data/2.5/weather?q={city}&appid={api_key}\"\n",
    "\n",
    "response = requests.get(url)\n",
    "weather_data = response.json()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Optional data storing step: You may save your raw dataset files to the local data store before moving to the next step."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 333,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "# bicycle rental data.\n",
    "bicycle_data.to_csv('RAW_bicycle_data.csv', index=False)\n",
    "# weather data.\n",
    "with open('RAW_weather_data.json', 'w') as f:\n",
    "    json.dump(weather_data, f)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QwSWIVmotLgV"
   },
   "source": [
    "## 2. Assess data\n",
    "\n",
    "Assess the data according to data quality and tidiness metrics using the report below.\n",
    "\n",
    "List **two** data quality issues and **two** tidiness issues. Assess each data issue visually **and** programmatically, then briefly describe the issue you find.  **Make sure you include justifications for the methods you use for the assessment.**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "adaK2iPNzVu4"
   },
   "source": [
    "### Quality Issue 1:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 334,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Display a sample of the bicycle rental data ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 335,
   "metadata": {
    "id": "SpW59kh-zl8d"
   },
   "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>ride_id</th>\n",
       "      <th>rideable_type</th>\n",
       "      <th>started_at</th>\n",
       "      <th>ended_at</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>end_station_name</th>\n",
       "      <th>end_station_id</th>\n",
       "      <th>start_lat</th>\n",
       "      <th>start_lng</th>\n",
       "      <th>end_lat</th>\n",
       "      <th>end_lng</th>\n",
       "      <th>member_casual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>FE7088887B6327BA</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-28 16:10:03</td>\n",
       "      <td>2023-06-28 16:26:07</td>\n",
       "      <td>20th &amp; O St NW / Dupont South</td>\n",
       "      <td>31234.0</td>\n",
       "      <td>14th &amp; G St NW</td>\n",
       "      <td>31238.0</td>\n",
       "      <td>38.908905</td>\n",
       "      <td>-77.044780</td>\n",
       "      <td>38.898164</td>\n",
       "      <td>-77.031898</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>F6006ED5FC8FD066</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-04 15:01:05</td>\n",
       "      <td>2023-06-04 15:01:22</td>\n",
       "      <td>11th &amp; V St NW</td>\n",
       "      <td>31332.0</td>\n",
       "      <td>11th &amp; V St NW</td>\n",
       "      <td>31332.0</td>\n",
       "      <td>38.918199</td>\n",
       "      <td>-77.027171</td>\n",
       "      <td>38.918199</td>\n",
       "      <td>-77.027171</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>01BC1C121A5AFB60</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-24 16:21:20</td>\n",
       "      <td>2023-06-24 16:24:59</td>\n",
       "      <td>1st &amp; D St SE</td>\n",
       "      <td>31643.0</td>\n",
       "      <td>1st &amp; I St SE</td>\n",
       "      <td>31628.0</td>\n",
       "      <td>38.884916</td>\n",
       "      <td>-77.005965</td>\n",
       "      <td>38.878854</td>\n",
       "      <td>-77.005727</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4A3C07740E161B08</td>\n",
       "      <td>docked_bike</td>\n",
       "      <td>2023-06-11 17:54:52</td>\n",
       "      <td>2023-06-11 18:11:09</td>\n",
       "      <td>Virginia Square Metro / Monroe St &amp; 9th St N</td>\n",
       "      <td>31024.0</td>\n",
       "      <td>Clarendon Blvd &amp; Pierce St</td>\n",
       "      <td>31016.0</td>\n",
       "      <td>38.882788</td>\n",
       "      <td>-77.103148</td>\n",
       "      <td>38.893438</td>\n",
       "      <td>-77.076389</td>\n",
       "      <td>casual</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>D73EEBADBFB8DF88</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-14 15:00:56</td>\n",
       "      <td>2023-06-14 15:05:18</td>\n",
       "      <td>17th St &amp; Massachusetts Ave NW</td>\n",
       "      <td>31267.0</td>\n",
       "      <td>11th &amp; O St NW</td>\n",
       "      <td>31286.0</td>\n",
       "      <td>38.908142</td>\n",
       "      <td>-77.038359</td>\n",
       "      <td>38.908431</td>\n",
       "      <td>-77.027088</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            ride_id rideable_type           started_at             ended_at  \\\n",
       "0  FE7088887B6327BA  classic_bike  2023-06-28 16:10:03  2023-06-28 16:26:07   \n",
       "1  F6006ED5FC8FD066  classic_bike  2023-06-04 15:01:05  2023-06-04 15:01:22   \n",
       "2  01BC1C121A5AFB60  classic_bike  2023-06-24 16:21:20  2023-06-24 16:24:59   \n",
       "3  4A3C07740E161B08   docked_bike  2023-06-11 17:54:52  2023-06-11 18:11:09   \n",
       "4  D73EEBADBFB8DF88  classic_bike  2023-06-14 15:00:56  2023-06-14 15:05:18   \n",
       "\n",
       "                             start_station_name  start_station_id  \\\n",
       "0                 20th & O St NW / Dupont South           31234.0   \n",
       "1                                11th & V St NW           31332.0   \n",
       "2                                 1st & D St SE           31643.0   \n",
       "3  Virginia Square Metro / Monroe St & 9th St N           31024.0   \n",
       "4                17th St & Massachusetts Ave NW           31267.0   \n",
       "\n",
       "             end_station_name  end_station_id  start_lat  start_lng  \\\n",
       "0              14th & G St NW         31238.0  38.908905 -77.044780   \n",
       "1              11th & V St NW         31332.0  38.918199 -77.027171   \n",
       "2               1st & I St SE         31628.0  38.884916 -77.005965   \n",
       "3  Clarendon Blvd & Pierce St         31016.0  38.882788 -77.103148   \n",
       "4              11th & O St NW         31286.0  38.908142 -77.038359   \n",
       "\n",
       "     end_lat    end_lng member_casual  \n",
       "0  38.898164 -77.031898        member  \n",
       "1  38.918199 -77.027171        member  \n",
       "2  38.878854 -77.005727        member  \n",
       "3  38.893438 -77.076389        casual  \n",
       "4  38.908431 -77.027088        member  "
      ]
     },
     "execution_count": 335,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bicycle_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 336,
   "metadata": {
    "id": "-qfcocStzsKg"
   },
   "outputs": [],
   "source": [
    "#Check the data types and non-null values in the bicycle rental data ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 337,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 430670 entries, 0 to 430669\n",
      "Data columns (total 13 columns):\n",
      " #   Column              Non-Null Count   Dtype  \n",
      "---  ------              --------------   -----  \n",
      " 0   ride_id             430670 non-null  object \n",
      " 1   rideable_type       430670 non-null  object \n",
      " 2   started_at          430670 non-null  object \n",
      " 3   ended_at            430670 non-null  object \n",
      " 4   start_station_name  394665 non-null  object \n",
      " 5   start_station_id    394665 non-null  float64\n",
      " 6   end_station_name    392411 non-null  object \n",
      " 7   end_station_id      392411 non-null  float64\n",
      " 8   start_lat           430670 non-null  float64\n",
      " 9   start_lng           430670 non-null  float64\n",
      " 10  end_lat             429980 non-null  float64\n",
      " 11  end_lng             429980 non-null  float64\n",
      " 12  member_casual       430670 non-null  object \n",
      "dtypes: float64(6), object(7)\n",
      "memory usage: 42.7+ MB\n"
     ]
    }
   ],
   "source": [
    "bicycle_data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Issue and justification: *FILL IN*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "8Be77N4I1AmE"
   },
   "source": [
    "### Quality Issue 2:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 340,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Display a sample of the weather data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 341,
   "metadata": {
    "id": "iMhHyiyLM2I3"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'coord': {'lon': -77.4467, 'lat': 37.5481},\n",
       " 'weather': [{'id': 803,\n",
       "   'main': 'Clouds',\n",
       "   'description': 'broken clouds',\n",
       "   'icon': '04d'}],\n",
       " 'base': 'stations',\n",
       " 'main': {'temp': 303,\n",
       "  'feels_like': 307.83,\n",
       "  'temp_min': 300.94,\n",
       "  'temp_max': 304.49,\n",
       "  'pressure': 1014,\n",
       "  'humidity': 70},\n",
       " 'visibility': 10000,\n",
       " 'wind': {'speed': 6.69, 'deg': 200},\n",
       " 'clouds': {'all': 75},\n",
       " 'dt': 1689356038,\n",
       " 'sys': {'type': 2,\n",
       "  'id': 2042621,\n",
       "  'country': 'US',\n",
       "  'sunrise': 1689328766,\n",
       "  'sunset': 1689381083},\n",
       " 'timezone': -14400,\n",
       " 'id': 6254928,\n",
       " 'name': 'Virginia',\n",
       " 'cod': 200}"
      ]
     },
     "execution_count": 341,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 342,
   "metadata": {
    "id": "bnviRCUI-bb7"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'coord': {'lon': -77.4467, 'lat': 37.5481}, 'weather': [{'id': 803, 'main': 'Clouds', 'description': 'broken clouds', 'icon': '04d'}], 'base': 'stations', 'main': {'temp': 303, 'feels_like': 307.83, 'temp_min': 300.94, 'temp_max': 304.49, 'pressure': 1014, 'humidity': 70}, 'visibility': 10000, 'wind': {'speed': 6.69, 'deg': 200}, 'clouds': {'all': 75}, 'dt': 1689356038, 'sys': {'type': 2, 'id': 2042621, 'country': 'US', 'sunrise': 1689328766, 'sunset': 1689381083}, 'timezone': -14400, 'id': 6254928, 'name': 'Virginia', 'cod': 200}\n"
     ]
    }
   ],
   "source": [
    "print(weather_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 343,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "303\n"
     ]
    }
   ],
   "source": [
    "temperature = weather_data['main']['temp']\n",
    "print(temperature)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 344,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Check the data types and non-null values in the weather data ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 345,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Key: coord\n",
      "Data Type: <class 'dict'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: weather\n",
      "Data Type: <class 'list'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: base\n",
      "Data Type: <class 'str'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: main\n",
      "Data Type: <class 'dict'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: visibility\n",
      "Data Type: <class 'int'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: wind\n",
      "Data Type: <class 'dict'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: clouds\n",
      "Data Type: <class 'dict'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: dt\n",
      "Data Type: <class 'int'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: sys\n",
      "Data Type: <class 'dict'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: timezone\n",
      "Data Type: <class 'int'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: id\n",
      "Data Type: <class 'int'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: name\n",
      "Data Type: <class 'str'>\n",
      "Non-null Values: True\n",
      "------------------------\n",
      "Key: cod\n",
      "Data Type: <class 'int'>\n",
      "Non-null Values: True\n",
      "------------------------\n"
     ]
    }
   ],
   "source": [
    "for key in weather_data.keys():\n",
    "    print(f\"Key: {key}\")\n",
    "    print(f\"Data Type: {type(weather_data[key])}\")\n",
    "    print(f\"Non-null Values: {weather_data[key] is not None}\")\n",
    "    print(\"------------------------\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Issue and justification: missing rationale and description of the data quality problem.\n",
    "\n",
    "Justification: We can spot any discrepancies, missing values, or data type inconsistencies that impair the quality of the data by looking at a sample of the weather data (print(weather_data)) and iterating over its keys to check the data types and non-null values."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lXhGiYyiwwKN"
   },
   "source": [
    "### Tidiness Issue 1:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 346,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Display sample of the bicycle rental data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 347,
   "metadata": {
    "id": "fleC5rORI0Xl"
   },
   "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>ride_id</th>\n",
       "      <th>rideable_type</th>\n",
       "      <th>started_at</th>\n",
       "      <th>ended_at</th>\n",
       "      <th>start_station_name</th>\n",
       "      <th>start_station_id</th>\n",
       "      <th>end_station_name</th>\n",
       "      <th>end_station_id</th>\n",
       "      <th>start_lat</th>\n",
       "      <th>start_lng</th>\n",
       "      <th>end_lat</th>\n",
       "      <th>end_lng</th>\n",
       "      <th>member_casual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>FE7088887B6327BA</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-28 16:10:03</td>\n",
       "      <td>2023-06-28 16:26:07</td>\n",
       "      <td>20th &amp; O St NW / Dupont South</td>\n",
       "      <td>31234.0</td>\n",
       "      <td>14th &amp; G St NW</td>\n",
       "      <td>31238.0</td>\n",
       "      <td>38.908905</td>\n",
       "      <td>-77.044780</td>\n",
       "      <td>38.898164</td>\n",
       "      <td>-77.031898</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>F6006ED5FC8FD066</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-04 15:01:05</td>\n",
       "      <td>2023-06-04 15:01:22</td>\n",
       "      <td>11th &amp; V St NW</td>\n",
       "      <td>31332.0</td>\n",
       "      <td>11th &amp; V St NW</td>\n",
       "      <td>31332.0</td>\n",
       "      <td>38.918199</td>\n",
       "      <td>-77.027171</td>\n",
       "      <td>38.918199</td>\n",
       "      <td>-77.027171</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>01BC1C121A5AFB60</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-24 16:21:20</td>\n",
       "      <td>2023-06-24 16:24:59</td>\n",
       "      <td>1st &amp; D St SE</td>\n",
       "      <td>31643.0</td>\n",
       "      <td>1st &amp; I St SE</td>\n",
       "      <td>31628.0</td>\n",
       "      <td>38.884916</td>\n",
       "      <td>-77.005965</td>\n",
       "      <td>38.878854</td>\n",
       "      <td>-77.005727</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4A3C07740E161B08</td>\n",
       "      <td>docked_bike</td>\n",
       "      <td>2023-06-11 17:54:52</td>\n",
       "      <td>2023-06-11 18:11:09</td>\n",
       "      <td>Virginia Square Metro / Monroe St &amp; 9th St N</td>\n",
       "      <td>31024.0</td>\n",
       "      <td>Clarendon Blvd &amp; Pierce St</td>\n",
       "      <td>31016.0</td>\n",
       "      <td>38.882788</td>\n",
       "      <td>-77.103148</td>\n",
       "      <td>38.893438</td>\n",
       "      <td>-77.076389</td>\n",
       "      <td>casual</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>D73EEBADBFB8DF88</td>\n",
       "      <td>classic_bike</td>\n",
       "      <td>2023-06-14 15:00:56</td>\n",
       "      <td>2023-06-14 15:05:18</td>\n",
       "      <td>17th St &amp; Massachusetts Ave NW</td>\n",
       "      <td>31267.0</td>\n",
       "      <td>11th &amp; O St NW</td>\n",
       "      <td>31286.0</td>\n",
       "      <td>38.908142</td>\n",
       "      <td>-77.038359</td>\n",
       "      <td>38.908431</td>\n",
       "      <td>-77.027088</td>\n",
       "      <td>member</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            ride_id rideable_type           started_at             ended_at  \\\n",
       "0  FE7088887B6327BA  classic_bike  2023-06-28 16:10:03  2023-06-28 16:26:07   \n",
       "1  F6006ED5FC8FD066  classic_bike  2023-06-04 15:01:05  2023-06-04 15:01:22   \n",
       "2  01BC1C121A5AFB60  classic_bike  2023-06-24 16:21:20  2023-06-24 16:24:59   \n",
       "3  4A3C07740E161B08   docked_bike  2023-06-11 17:54:52  2023-06-11 18:11:09   \n",
       "4  D73EEBADBFB8DF88  classic_bike  2023-06-14 15:00:56  2023-06-14 15:05:18   \n",
       "\n",
       "                             start_station_name  start_station_id  \\\n",
       "0                 20th & O St NW / Dupont South           31234.0   \n",
       "1                                11th & V St NW           31332.0   \n",
       "2                                 1st & D St SE           31643.0   \n",
       "3  Virginia Square Metro / Monroe St & 9th St N           31024.0   \n",
       "4                17th St & Massachusetts Ave NW           31267.0   \n",
       "\n",
       "             end_station_name  end_station_id  start_lat  start_lng  \\\n",
       "0              14th & G St NW         31238.0  38.908905 -77.044780   \n",
       "1              11th & V St NW         31332.0  38.918199 -77.027171   \n",
       "2               1st & I St SE         31628.0  38.884916 -77.005965   \n",
       "3  Clarendon Blvd & Pierce St         31016.0  38.882788 -77.103148   \n",
       "4              11th & O St NW         31286.0  38.908142 -77.038359   \n",
       "\n",
       "     end_lat    end_lng member_casual  \n",
       "0  38.898164 -77.031898        member  \n",
       "1  38.918199 -77.027171        member  \n",
       "2  38.878854 -77.005727        member  \n",
       "3  38.893438 -77.076389        casual  \n",
       "4  38.908431 -77.027088        member  "
      ]
     },
     "execution_count": 347,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bicycle_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 348,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Check data shape of the bicycle rental data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 349,
   "metadata": {
    "id": "BTuQw7Rbsio4"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(430670, 13)"
      ]
     },
     "execution_count": 349,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bicycle_data.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Issue and justification: We can make sure that the data is correctly formatted and arranged in a tidy fashion by looking at a sample of the bicycle rental data (bicycle_data.head()) and determining its shape (bicycle_data.shape)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "4ffMoRGSwzYj"
   },
   "source": [
    "### Tidiness Issue 2: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 350,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Display sample of the weather data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 351,
   "metadata": {
    "id": "XUpeoqokw5Qt"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'coord': {'lon': -77.4467, 'lat': 37.5481},\n",
       " 'weather': [{'id': 803,\n",
       "   'main': 'Clouds',\n",
       "   'description': 'broken clouds',\n",
       "   'icon': '04d'}],\n",
       " 'base': 'stations',\n",
       " 'main': {'temp': 303,\n",
       "  'feels_like': 307.83,\n",
       "  'temp_min': 300.94,\n",
       "  'temp_max': 304.49,\n",
       "  'pressure': 1014,\n",
       "  'humidity': 70},\n",
       " 'visibility': 10000,\n",
       " 'wind': {'speed': 6.69, 'deg': 200},\n",
       " 'clouds': {'all': 75},\n",
       " 'dt': 1689356038,\n",
       " 'sys': {'type': 2,\n",
       "  'id': 2042621,\n",
       "  'country': 'US',\n",
       "  'sunrise': 1689328766,\n",
       "  'sunset': 1689381083},\n",
       " 'timezone': -14400,\n",
       " 'id': 6254928,\n",
       " 'name': 'Virginia',\n",
       " 'cod': 200}"
      ]
     },
     "execution_count": 351,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weather_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 352,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Check data shape of the weather data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 353,
   "metadata": {
    "id": "c8JK4DoXxtFA"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "13\n"
     ]
    }
   ],
   "source": [
    "print(len(weather_data))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Issue and justification: Incomplete exposition and justification of the tidyness issue.\n",
    "\n",
    "Justification: We can check that the weather data is appropriately formatted and arranged in a neat fashion by looking at a sample of the weather data (print(weather_data)) and using the len() method to check the number of entries in the weather_data dictionary."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D6gmLnBttpCh"
   },
   "source": [
    "## 3. Clean data\n",
    "Clean the data to solve the 4 issues corresponding to data quality and tidiness found in the assessing step. **Make sure you include justifications for your cleaning decisions.**\n",
    "\n",
    "After the cleaning for each issue, please use **either** the visually or programatical method to validate the cleaning was succesful.\n",
    "\n",
    "At this stage, you are also expected to remove variables that are unnecessary for your analysis and combine your datasets. Depending on your datasets, you may choose to perform variable combination and elimination before or after the cleaning stage. Your dataset must have **at least** 4 variables after combining the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 354,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Make copies of the datasets to ensure the raw dataframes "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 355,
   "metadata": {},
   "outputs": [],
   "source": [
    "bicycle_data_cleaned = bicycle_data.copy()\n",
    "weather_data_cleaned = weather_data.copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FmFhN52Yyn3l"
   },
   "source": [
    "### **Quality Issue 1: FILL IN**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 356,
   "metadata": {
    "id": "9UejDWrNMW4a"
   },
   "outputs": [],
   "source": [
    "bicycle_data_cleaned.dropna(subset=['ride_id', 'started_at', 'ended_at', 'start_station_name', 'end_station_name'], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 357,
   "metadata": {
    "id": "oUBee-LPytkv"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 377553 entries, 0 to 430669\n",
      "Data columns (total 13 columns):\n",
      " #   Column              Non-Null Count   Dtype  \n",
      "---  ------              --------------   -----  \n",
      " 0   ride_id             377553 non-null  object \n",
      " 1   rideable_type       377553 non-null  object \n",
      " 2   started_at          377553 non-null  object \n",
      " 3   ended_at            377553 non-null  object \n",
      " 4   start_station_name  377553 non-null  object \n",
      " 5   start_station_id    377553 non-null  float64\n",
      " 6   end_station_name    377553 non-null  object \n",
      " 7   end_station_id      377553 non-null  float64\n",
      " 8   start_lat           377553 non-null  float64\n",
      " 9   start_lng           377553 non-null  float64\n",
      " 10  end_lat             377553 non-null  float64\n",
      " 11  end_lng             377553 non-null  float64\n",
      " 12  member_casual       377553 non-null  object \n",
      "dtypes: float64(6), object(7)\n",
      "memory usage: 40.3+ MB\n"
     ]
    }
   ],
   "source": [
    "bicycle_data_cleaned.info()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Justification: Analysis errors might result from missing data in crucial columns. We assure the accuracy of the data and maintain the consistency of the variables that are essential for studying rental patterns and their relationship to weather conditions by removing rows with missing values in the critical columns."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "n_DAUbJrymBL"
   },
   "source": [
    "### **Quality Issue 2: FILL IN**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 358,
   "metadata": {
    "id": "5Yfb-Yu5MTuE"
   },
   "outputs": [],
   "source": [
    "bicycle_data_cleaned['started_at'] = pd.to_datetime(bicycle_data_cleaned['started_at'])\n",
    "bicycle_data_cleaned['ended_at'] = pd.to_datetime(bicycle_data_cleaned['ended_at'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 359,
   "metadata": {
    "id": "ionB2sRaMUmY"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "datetime64[ns]\n",
      "datetime64[ns]\n"
     ]
    }
   ],
   "source": [
    "print(bicycle_data_cleaned['started_at'].dtypes)\n",
    "print(bicycle_data_cleaned['ended_at'].dtypes)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Justification: It's crucial to have a consistent format when performing calculations and analyses that use date and time. We make sure that the dates and times can be properly evaluated by converting the \"started_at\" and \"ended_at\" columns to datetime format."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bIUrrfSNyOPR"
   },
   "source": [
    "### **Tidiness Issue 1: FILL IN**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 360,
   "metadata": {
    "id": "fib0zAm333bn"
   },
   "outputs": [],
   "source": [
    "bicycle_data_cleaned['duration'] = (bicycle_data_cleaned['ended_at'] - bicycle_data_cleaned['started_at']).dt.total_seconds() / 60\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 361,
   "metadata": {
    "id": "yhrnUGY_Nk8B"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    16.066667\n",
      "1     0.283333\n",
      "2     3.650000\n",
      "3    16.283333\n",
      "4     4.366667\n",
      "Name: duration, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(bicycle_data_cleaned['duration'].head())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Justification: For the purpose of assessing rental patterns and their relationship to weather conditions, adding a \"duration\" column offers useful information on the rental period. The dataset becomes more helpful and complete as a result."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "o51Bt8kwyTzk"
   },
   "source": [
    "### **Tidiness Issue 2: FILL IN**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 362,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['ride_id', 'rideable_type', 'started_at', 'ended_at',\n",
      "       'start_station_name', 'start_station_id', 'end_station_name',\n",
      "       'end_station_id', 'start_lat', 'start_lng', 'end_lat', 'end_lng',\n",
      "       'member_casual', 'duration'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(bicycle_data_cleaned.columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 363,
   "metadata": {},
   "outputs": [],
   "source": [
    "bicycle_data_cleaned = bicycle_data_cleaned.drop(['rideable_type', 'start_station_id'], axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 364,
   "metadata": {
    "id": "q6I_Sr7lxXi5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['ride_id', 'started_at', 'ended_at', 'start_station_name',\n",
      "       'end_station_name', 'end_station_id', 'start_lat', 'start_lng',\n",
      "       'end_lat', 'end_lng', 'member_casual', 'duration'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(bicycle_data_cleaned.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Justification:removing the unnecessary columns from the bicycle_data_cleaned dataset,we  ensure that we are focusing only on the relevant variables for our analysis. This helps to simplify the dataset and reduce redundancy."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Remove unnecessary variables and combine datasets**\n",
    "\n",
    "Depending on the datasets, you can also peform the combination before the cleaning steps."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 365,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['ride_id', 'started_at', 'ended_at', 'start_station_name',\n",
       "       'end_station_name', 'end_station_id', 'start_lat', 'start_lng',\n",
       "       'end_lat', 'end_lng', 'member_casual', 'duration'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 365,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bicycle_data_cleaned.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 366,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['ride_id', 'started_at', 'ended_at', 'start_station_name',\n",
      "       'end_station_name', 'end_station_id', 'start_lat', 'start_lng',\n",
      "       'end_lat', 'end_lng', 'member_casual', 'duration'],\n",
      "      dtype='object')\n",
      "Index(['coord', 'weather', 'base', 'main', 'visibility', 'wind', 'clouds',\n",
      "       'dt', 'sys', 'timezone', 'id', 'name', 'cod'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(bicycle_data_cleaned.columns)\n",
    "print(weather_data_df.columns)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "F42urHuzttjF"
   },
   "source": [
    "## 4. Update your data store\n",
    "Update your local database/data store with the cleaned data, following best practices for storing your cleaned data:\n",
    "\n",
    "- Must maintain different instances / versions of data (raw and cleaned data)\n",
    "- Must name the dataset files informatively\n",
    "- Ensure both the raw and cleaned data is saved to your database/data store"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 367,
   "metadata": {
    "id": "V3uay7EJUV_L"
   },
   "outputs": [],
   "source": [
    "# Save raw bicycle rental data.\n",
    "bicycle_data.to_csv('RAW_bicycle_data.csv', index=False)\n",
    "#Save the cleaned bicycle rental data.\n",
    "bicycle_data_cleaned.to_csv('Cleaned_bicycle_data.csv', index=False)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cGy_yddGtzhM"
   },
   "source": [
    "## 5. Answer the research question\n",
    "\n",
    "### **5.1:** Define and answer the research question \n",
    "Going back to the problem statement in step 1, use the cleaned data to answer the question you raised. Produce **at least** two visualizations using the cleaned data and explain how they help you answer the question."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gjedE4s4ZkEd"
   },
   "source": [
    "Research question:What is the relationship between the duration of bike rides and the type of user (member or casual)  bike rides and the kind of user—a member or a casual—of the Washington, DC, bike rental system?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 368,
   "metadata": {},
   "outputs": [],
   "source": [
    " #Box plot comparing the duration of bike rides for member and casual users\n",
    "    #We can make a box plot that compares the length of bike rides for member and casual users in order to respond to the research question. \n",
    "   # The distribution of ride durations for each user type is shown graphically in the box plot. \n",
    "   # It enables us to determine whether there are any appreciable differences in the length of rides between members and non-members."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 319,
   "metadata": {
    "id": "Lkw3rW9kZmOm"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "sns.boxplot(x='member_casual', y='duration', data=bicycle_data_cleaned)\n",
    "plt.xlabel('User Type')\n",
    "plt.ylabel('Ride Duration (minutes)')\n",
    "plt.title('Distribution of Ride Durations by User Type')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Answer to research question:The box plot demonstrates that compared to casual users, member users typically have shorter ride durations. The shorter median ride duration for members suggests that the majority of member rides are shorter in length. Conversely, casual users have access to a wider range of ride lengths, some of which are noticeably longer. This implies that while casual users may use the bike rental system for a variety of uses, such as leisurely rides or longer trips, members may use it for shorter trips like commuting or running errands."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 320,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Bar plot showing the average ride duration for each user type\n",
    "#Calculating and contrasting the average ride duration for members and casual users is another way to examine the connection between ride duration and user type. This comparison can be effectively displayed using a bar plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 321,
   "metadata": {
    "id": "6fdK_8ZGZm9R"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "avg_duration = bicycle_data_cleaned.groupby('member_casual')['duration'].mean()\n",
    "\n",
    "x_labels = ['Member', 'Casual']\n",
    "x = np.arange(len(x_labels))\n",
    "plt.bar(x, avg_duration, align='center')\n",
    "plt.xticks(x, x_labels)\n",
    "plt.xlabel('User Type')\n",
    "plt.ylabel('Average Ride Duration (minutes)')\n",
    "plt.title('Average Ride Duration by User Type')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 322,
   "metadata": {},
   "outputs": [],
   "source": [
    " #How does the demand for bike rentals vary throughout the day?\n",
    "  #  The hourly demand for bike rentals is depicted by a line plot.\n",
    "#Explanation: We can create a line plot that shows the daily variation in demand for bike rentals to provide an answer\n",
    "  #  to this research question. The number of \n",
    "  #  bike rentals is represented by the y-axis, while the x-axis represents the hours of the day. We can determine demand peaks and comprehend the overall pattern of bike rental usage over a 24-hour period by examining the line plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 323,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "bicycle_data_cleaned['hour'] = bicycle_data_cleaned['started_at'].dt.hour\n",
    "\n",
    "hourly_demand = bicycle_data_cleaned.groupby('hour').size()\n",
    "\n",
    "plt.plot(hourly_demand.index, hourly_demand.values)\n",
    "plt.xlabel('Hour of the Day')\n",
    "plt.ylabel('Number of Bike Rentals')\n",
    "plt.title('Hourly Demand for Bike Rentals')\n",
    "plt.xticks(np.arange(0, 24, 2))\n",
    "plt.grid(True)\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "K5RgvMGUZoHn"
   },
   "source": [
    "The demand for bike rentals varies throughout the day, as shown by the line plot. The morning commute hours (around 7-9 AM) and the evening commute hours (around 5-7 PM) are when demand begins to increase, according to our observations. This pattern suggests that commuters who use bikes as an alternate mode of transportation during rush hour favor the bike rental system. Additionally, we can see that demand is relatively lower late at night, which suggests that fewer people are renting bikes then."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 324,
   "metadata": {},
   "outputs": [],
   "source": [
    "# How does the ride duration vary across different days of the week?\n",
    "   # Comparison of the ride times for each day of the week using a violin plot.\n",
    "#Explanation: We can make a violin plot that compares the ride lengths on various days of the week to provide an answer to this research question. The violin plot, which displays the range, median, and density of ride durations, sheds light on the distribution of ride lengths for each day. It enables us to determine if ride lengths significantly vary depending on the day of the week."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 327,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "bicycle_data_cleaned['weekday'] = bicycle_data_cleaned['started_at'].dt.dayofweek\n",
    "\n",
    "\n",
    "weekday_names = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']\n",
    "bicycle_data_cleaned['weekday_name'] = bicycle_data_cleaned['weekday'].map(lambda x: weekday_names[x])\n",
    "\n",
    "\n",
    "sns.violinplot(x='weekday_name', y='duration', data=bicycle_data_cleaned, order=weekday_names)\n",
    "plt.xlabel('Day of the Week')\n",
    "plt.ylabel('Ride Duration (minutes)')\n",
    "plt.title('Ride Duration Variation across Days of the Week')\n",
    "plt.xticks(rotation=45)\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 328,
   "metadata": {},
   "outputs": [],
   "source": [
    "#The violin plot illustrates the variance in ride lengths throughout the course of the week.\n",
    "#We can see that, as compared to the weekends (Saturday and Sunday),\n",
    "#ride times are often a little bit longer throughout the week, \n",
    "#especially on Mondays and Fridays. This shows that riding a bike throughout the workweek might entail longer distances or more frequent use for everyday commuting. \n",
    "#The violin plot, on the other hand, shows shorter riding times on the weekends.\n",
    "#suggesting that weekend bike rides are often more relaxed and enjoyable in character."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "0ezWXXZVj-TP"
   },
   "source": [
    "### **5.2:** Reflection\n",
    "In 2-4 sentences, if you had more time to complete the project, what actions would you take? For example, which data quality and structural issues would you look into further, and what research questions would you further explore?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XB3RBDG5kFe1"
   },
   "source": [
    "If I had more time to finish the project, I would thoroughly validate and clean the data in order to better understand the data quality and structural concerns. This would entail examining the data for anomalies, outliers, and discrepancies. Further study questions that I would look into include the effect of weather conditions on demand for bike rentals, the connection between ride duration and user type, and the interaction between bike rental trends and certain urban locations."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}