简介：随着共享单车的星期，这次探索三大美国城市的自行车共享系统相关的数据：芝加哥、纽约和华盛顿特区，帮助共享单车公司得到一些关键性的数据信息，例如哪个起始车站最热门，哪一趟行程最热门等等，来对共享单车的投放给予一定帮助。
一、分析步骤
- 编写代码导入数据，并通过计算描述性统计数据回答有趣的问题。
- 编写一个脚本，该脚本会接受原始输入并在终端中创建交互式体验，以展现这些统计信息。
- 提出问题
- 终端应用脚本
二、提出问题
- 起始时间（Start Time 列）中哪个月份最常见？
- 起始时间中，一周的哪一天（比如 Monday, Tuesday）最常见？
- 起始时间中，一天当中哪个小时最常见？
- 总骑行时长（Trip Duration）是多久，平均骑行时长是多久？
- 哪个起始车站（Start Station）最热门，哪个结束车站（End Station）最热门？
- 哪一趟行程最热门（即，哪一个起始站点与结束站点的组合最热门）？
- 每种用户类型有多少人？
- 每种性别有多少人？
- 出生年份最早的是哪一年、最晚的是哪一年，最常见的是哪一年？
三、代码实现
工具：Python
文本编辑器：Pycharm
import time
import pandas as pd
import numpy as np
CITY_DATA = { 'chicago': 'chicago.csv',
'new york city': 'new_york_city.csv',
'washington': 'washington.csv' }
def get_filters():
"""
Asks user to specify a city, month, and day to analyze.
Returns:
(str) city - name of the city to analyze
(str) month - name of the month to filter by, or "all" to apply no month filter
(str) day - name of the day of week to filter by, or "all" to apply no day filter
"""
print('Hello! Let\'s explore some US bikeshare data!')
# get user input for city (chicago, new york city, washington). HINT: Use a while loop to handle invalid inputs
city = input("Which city do you want to analyze? input ：chicago, new york city, washington\n").lower()
while True:
if city not in CITY_DATA.keys():
city = input('Invalid input======\nwould you like to see data for chicago, '
'new youk city, or washington?')
else:
break
# get user input for month (all, january, february, ... , june)
months = ['all', 'january', 'february', 'march', 'april', 'may', 'june']
month = input("Which month data do you want to analyze？input ：all，january, february, "
"march, april, may, june\n").lower()
while True:
if month not in months:
month = input('Invalid input======\nWhich month data do you want to analyze？input ：all，january, february,'
'march, april, may, june\n').lower()
else:
break
# get user input for day of week (all, monday, tuesday, ... sunday)
days = ['all', 'monday','tuesday','wednesday','thursday','friday','saturday','sunday']
day = input("Which day of week do you want to analyze? input："
"all，monday, tuesday, wednesday, thursday, friday, saturday, sunday").lower()
while True:
if day not in days:
day = input("Invalid input======\nWhich day of week do you want to analyze? input："
"all，monday, tuesday, wednesday, thursday, friday, saturday, sunday").lower()
else:
break
print('-'*40)
return city, month, day
def load_data(city, month, day):
"""
Loads data for the specified city and filters by month and day if applicable.
Args:
(str) city - name of the city to analyze
(str) month - name of the month to filter by, or "all" to apply no month filter
(str) day - name of the day of week to filter by, or "all" to apply no day filter
Returns:
df - Pandas DataFrame containing city data filtered by month and day
"""
# load data file into a dataframe
df = pd.read_csv(CITY_DATA[city])
# convert the Start Time column to datetime
df['Start Time'] = pd.to_datetime(df['Start Time'])
# extract month and day of week from Start Time to create new columns
df['month'] = df['Start Time'].dt.month
df['day_of_week'] = df['Start Time'].dt.weekday_name
# filter by month if applicable
if month != 'all':
# use the index of the months list to get the corresponding int
months = ['january', 'february', 'march', 'april', 'may', 'june']
month = months.index(month) + 1
# filter by month to create the new dataframe
df = df[df['month'] == month]
# filter by day of week if applicable
if day != 'all':
# filter by day of week to create the new dataframe
df = df[df['day_of_week'] == day.title()]
return df
def time_stats(df):
"""Displays statistics on the most frequent times of travel."""
print('\nCalculating The Most Frequent Times of Travel...\n')
start_time = time.time()
# display the most common month
common_month = df['month'].mode()[0]
print('The most common month: ', common_month)
# display the most common day of week
common_day_of_week = df['day_of_week'].mode()[0]
print('The most common day of week: ', common_day_of_week)
# display the most common start hour
df['start_hour'] = df['Start Time'].dt.hour
common_start_hour = df['start_hour'].mode()[0]
print('The most common start hour: ', common_start_hour)
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def station_stats(df):
"""Displays statistics on the most popular stations and trip."""
print('\nCalculating The Most Popular Stations and Trip...\n')
start_time = time.time()
# display most commonly used start station
common_start_station = df['Start Station'].mode()[0]
print('The most commonly used start station: ', common_start_station)
# display most commonly used end station
common_end_station = df['End Station'].mode()[0]
print('The most commonly used end station: ', common_end_station)
# display most frequent combination of start station and end station trip
df['Station'] = df['Start Station'] + df['End Station']
frequent_station = df['Station'].mode()[0]
print('The most frequent station: ', frequent_station)
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def trip_duration_stats(df):
"""Displays statistics on the total and average trip duration."""
print('\nCalculating Trip Duration...\n')
start_time = time.time()
# display total travel time
total_travel_time = df['Trip Duration'].sum()
print('The total trabel time: ', total_travel_time)
# display mean travel time
mean_trabel_time = df['Trip Duration'].mean()
print('The mean travel time: ', mean_trabel_time)
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def user_stats(df):
"""Displays statistics on bikeshare users."""
print('\nCalculating User Stats...\n')
start_time = time.time()
# Display counts of user types
count_user_types = df['User Type'].value_counts()
print('Counts of user types: ', count_user_types)
# Display counts of gender
try:
count_gender = df['Gender'].value_counts()
print('Counts of gender: ', count_gender)
except KeyError:
print('Counts of gender:oh sorry, this city have no this data.')
# Display earliest, most recent, and most common year of birth
try:
earliest_birth = df['Birth Year'].min()
most_recent_birth = df['Birth Year'].max()
most_common_birth = df['Birth Year'].mode()[0]
print('Earliest year of birth:',earliest_birth)
print('Most recent year of birth',most_recent_birth)
print('Most common year of birth',most_common_birth)
except KeyError:
print('oh sorry, this city have no Birth Year data.')
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def main():
while True:
city, month, day = get_filters()
df = load_data(city, month, day)
time_stats(df)
station_stats(df)
trip_duration_stats(df)
user_stats(df)
restart = input('\nWould you like to restart? Enter yes or no.\n')
if restart.lower() != 'yes':
break
if __name__ == "__main__":
main()
四、互动式体验
该文件是一个脚本，它接受原始输入在终端中创建交互式体验，来回答有关数据集的问题。
输入想要查看的问题：
输入.png
得出答案：
答案.png
Ps：脚本还可以持续地优化，这次只是做了一个简易的版本，另外还可以在脚本加入可视化的工具，输入需要的数据，自动生成需要的图表，这就不要太方便了啊啊啊啊啊！！！！！！
网友评论