-
Notifications
You must be signed in to change notification settings - Fork 0
/
bikeshare.py
247 lines (179 loc) · 8.31 KB
/
bikeshare.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
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!')
#Initializing an empty city variable to store city choice from user
#You will see this repeat throughout the program
city = ''
#Running this loop to ensure the correct user input gets selected else repeat
while city not in CITY_DATA.keys():
print("\nWelcome to this program. Please choose your city:")
print("\n1. Chicago 2. New York City 3. Washington")
#Taking user input and converting into lower to standardize them
city = input().lower()
if city not in CITY_DATA.keys():
print("\nPlease check your input, it doesn\'t appear to be conforming to any of the accepted input formats.")
print("\nRestarting...")
print(f"\nYou have chosen {city.title()} as your city.")
#Creating a dictionary to store all the months including the 'all' option
MONTH_DATA = {'january': 1, 'february': 2, 'march': 3, 'april': 4, 'may': 5, 'june': 6, 'all': 7}
month = ''
while month not in MONTH_DATA.keys():
print("\nWhich Month (all, january, ... june)?")
month = input().lower()
if month not in MONTH_DATA.keys():
print("\nInvalid input. Please try again in the accepted input format.")
print("\nRestarting...")
print(f"\nYou have chosen {month.title()} as your month.")
#Creating a list to store all the days including the 'all' option
DAY_LIST = ['all', 'monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
day = ''
while day not in DAY_LIST:
print("\nWhich day? (all, monday, tuesday, ... sunday")
day = input().lower()
if day not in DAY_LIST:
print("\nInvalid input. Please try again in one of the accepted input formats.")
print("\nRestarting...")
print(f"\nYou have chosen {day.title()} as your day.")
print(f"\nYou have chosen to view data for city: {city.upper()}, month/s: {month.upper()} and day/s: {day.upper()}.")
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()]
#Returns the selected file as a dataframe (df) with relevant columns
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: uses mode to display the most common month
popular_month = df['month'].mode()[0]
print('The most Popular Month is:', popular_month)
# display the most common day of week : uses mode to display most common day of week
popular_day = df['day_of_week'].mode()[0]
print('The most common day of week is:', popular_day)
# display the most common start hour
popular_hour = df['Start Time'].mode()[0]
print('The most common start hour is:', popular_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
popular_start_station = df['Start Station'].mode()[0]
print('Most Start Station:', popular_start_station)
# display most commonly used end station
popular_end_station = df['End Station'].mode()[0]
print('Most End Station:', popular_end_station)
# display most frequent combination of start station and end station trip
group_field=df.groupby(['Start Station','End Station'])
popular_combination_station = group_field.size().sort_values(ascending=False).head(1)
print('Most frequent combination of Start Station and End Station trip:\n', popular_combination_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 travel time is:', total_travel_time)
# display mean travel time
mean_travel_time = df['Trip Duration'].mean()
print('The mean travel time is:', mean_travel_time)
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def user_stats(df, city):
"""Displays statistics on bikeshare users."""
print('\nCalculating User Stats...\n')
start_time = time.time()
# Display counts of user types
print('User Type Stats:')
print(df['User Type'].value_counts())
if city != 'washington':
# Display counts of gender
print('Gender Stats:')
print(df['Gender'].value_counts())
# Display earliest, most recent, and most common year of birth
print('Birth Year Stats:')
most_common_year = df['Birth Year'].mode()[0]
print('Most Common Year:',most_common_year)
most_recent_year = df['Birth Year'].max()
print('Most Recent Year:',most_recent_year)
earliest_year = df['Birth Year'].min()
print('Earliest Year:',earliest_year)
print("\nThis took %s seconds." % (time.time() - start_time))
print('-'*40)
def display_raw_data(df):
"""Displays 5 rows of raw data upon user request from the csv file of selected city.
Args:
(DataFrame) df - pandas DataFrame containing city data filtered by month and day_of_week
"""
#pring the first 5 rows of raw data
print(df.head())
next = 0
while True:
view_raw_data = input('\nWould you like to view the next five rows of raw data? Enter yes or no.\n')
if view_raw_data.lower() != 'yes':
return
next = next + 5
#prints the next five lines from were the previous print statement paused
print(df.iloc[next:next+5])
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, city)
while True:
view_raw_data = input('\nWould you like to view first five rows of raw data? Enter yes or no\n')
if view_raw_data.lower() != 'yes':
break
display_raw_data(df)
break
restart = input('\nWould you like to restart? Enter yes or no.\n')
if restart.lower() != 'yes':
break
if __name__ == "__main__":
main()