I am trying to run the following code:
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
while True:
city = input('Which city you would like to explore : "chicago" , "new york city" , or "washington" :' )
if city not in ('chicago', 'new york city', 'washington'):
print(" You entered wrong choice , please try again")
continue
else:
break
# get user input for month (all, january, february, ... , june)
while True:
month = input('Enter "all" for all data or chose a month : "january" , "february" , "march", "april" , "may" or "june " :')
if month not in ("all", "january", "february", "march", "april", "may", "june"):
print(" You entered wrong choice , please try again")
continue
else:
break
# get user input for day of week (all, monday, tuesday, ... sunday)
while True:
day = input('Enter "all" for all days or chose a day : "saturday", "sunday", "monday", "tuesday", "wednesday", "thursday", "friday": ')
if day not in ("all","saturday", "sunday", "monday", "tuesday", "wednesday", "thursday", "friday"):
print(" You entered wrong choice , please try again")
continue
else:
break
print('-'*60)
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
"""
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 , day of week , and hour from Start Time to new columns
df['month'] = df['Start Time'].dt.month
df['day_of_week'] = df['Start Time'].dt.day_name
df['hour'] = df['Start Time'].dt.hour
# filter by month if applicable
if month != 'all':
# use the index of the month_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
popular_month = df['month'].mode()[0]
print('\n The most popular month is : \n', popular_month)
# display the most common day of week
popular_day = df['day_of_week'].mode()[0]
print('\n The most popular day of the week is : \n', str(popular_day))
# display the most common start hour
popular_hour = df['hour'].mode()[0]
print('\n The most popular hour of the day is :\n ', popular_hour)
print("\nThis took %s seconds.\n" % (time.time() - start_time))
print('-'*60)
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
start_station = df['Start Station'].value_counts().idxmax()
print('\n The most commonly used start station is : \n', start_station)
# display most commonly used end station
end_station = df['End Station'].value_counts().idxmax()
print('\nThe most commonly used end station is: \n', end_station)
# display most frequent combination of start station and end station trip
combination = df.groupby(['Start Station','End Station']).value_counts().idxmax()
print('\nThe most frequent combination of start station and end station are: \n', combination)
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."""
start_time = time.time()
travel_time = sum(df['Trip Duration'])
print('Total travel time:', travel_time / 86400, " Days")
# display total travel time
total_time = sum(df['Trip Duration'])
print('\nThe total travel time is {} seconds: \n', total_time)
# display mean travel time
mean_time = df['Trip Duration'].mean()
print('\n The average travel time is \n', mean_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()
# TO DO: Display counts of user types
user_types = df['User Type'].value_counts()
#print(user_types)
print('User Types:\n', user_types)
# TO DO: Display counts of gender
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()
and I am receiving the following errors , can someone assist please the errors:
> Traceback (most recent call last):
File "C:\Users\DELL\PycharmProjects\Professional\venv\Lib\site-packages\pandas\core\indexes\range.py", line 391, in get_loc
return self._range.index(new_key)
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: 0 is not in range
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\DELL\PycharmProjects\Professional\Bikeshare.py", line 203, in <module>
main()
File "C:\Users\DELL\PycharmProjects\Professional\Bikeshare.py", line 192, in main
time_stats(df)
File "C:\Users\DELL\PycharmProjects\Professional\Bikeshare.py", line 100, in time_stats
popular_month = df['month'].mode()[0]
~~~~~~~~~~~~~~~~~~^^^
File "C:\Users\DELL\PycharmProjects\Professional\venv\Lib\site-packages\pandas\core\series.py", line 981, in __getitem__
Calculating The Most Frequent Times of Travel...
return self._get_value(key)
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\DELL\PycharmProjects\Professional\venv\Lib\site-packages\pandas\core\series.py", line 1089, in _get_value
loc = self.index.get_loc(label)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\DELL\PycharmProjects\Professional\venv\Lib\site-packages\pandas\core\indexes\range.py", line 393, in get_loc
raise KeyError(key) from err
KeyError: 0
I am expecting to filter pandas DataFrame to return month, day of week, and hour to perform some statistics.
CodePudding user response：
KeyError means that the key isn't valid, because it doesn't exist. In this case, one reason to get KeyError when trying to get first mode is when column 'month' in dataframe is empty, and therefore mode() returns an empty collection, so you get KeyError: 0 when trying to get its first element.
To avoid this, you could replace:
popular_month = df['month'].mode()[0]
With:
try:
# try to get first mode of column 'month'
popular_month = df['month'].mode()[0]
except KeyError:
# if there's no data on column 'month'
popular_month = "unknown"
Because if there's no data on 'month' column, there's no point in trying to get its mode.
More about handling exceptions: https://docs.python.org/3/tutorial/errors.html#handling-exceptions
CodePudding user response：
Also when I tried to ( not use the filters) by choosing " all " in the second and 3rd input, I get the following result:
Calculating The Most Frequent Times of Travel...
The most popular month is : 6
The most popular day of the week is :
<bound method PandasDelegate._add_delegate_accessors.._create_delegator_method..f of <pandas.core.indexes.accessors.DatetimeProperties object at 0x0000022B7CD5E890>>
The most popular hour of the day is : 17
This took 0.0260775089263916 seconds.
Calculating The Most Popular Stations and Trip...
The most commonly used start station is :
Streeter Dr & Grand Ave
The most commonly used end station is:
Streeter Dr & Grand Ave
The most frequent combination of start station and end station are:
('2112 W Peterson Ave', '2112 W Peterson Ave', 1064651, Timestamp('2017-06-02 07:59:13'), '2017-06-02 08:25:42', 1589, 'Subscriber', 'Female', 1963.0, 6, <bound method PandasDelegate._add_delegate_accessors.._create_delegator_method..f of <pandas.core.indexes.accessors.DatetimeProperties object at 0x0000022B7CD5E890>>, 7)
This took 2.1254045963287354 seconds.
Total travel time: 3250.8308680555556 Days
The total travel time is {} seconds: 280871787
The average travel time is 936.23929
This took 0.06502270698547363 seconds.
Calculating User Stats...
User Types: Subscriber 238889 Customer 61110 Dependent 1 Name: User Type, dtype: int64
This took 0.022009611129760742 seconds.
Would you like to restart? Enter yes or no.