In [3]:
from __future__ import absolute_import, division, print_function, unicode_literals
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
In [4]:
divvy_data = pd.read_csv('data/divvy_zip_summer_15.csv')
divvy_data.head()
Out[4]:
In [7]:
divvy_data['start_time']=pd.to_datetime(divvy_data['start_time'],format='%Y-%m-%d %H:%M:%S')
In [8]:
divvy_data.start_time
Out[8]:
In [9]:
divvy_data['stop_time']=pd.to_datetime(divvy_data['stop_time'],format='%Y-%m-%d %H:%M:%S')
In [10]:
divvy_data.stop_time
Out[10]:
In [11]:
divvy_data['trip_time'] = divvy_data['stop_time']- divvy_data['start_time']
In [13]:
divvy_data.head()
Out[13]:
In [16]:
divvy_data.trip_time.describe()
Out[16]:
In [17]:
divvy_data.hist(column = 'trip_time')
In [18]:
(divvy_data['trip_time'] / np.timedelta64(1, 'M')).astype(int)
Out[18]:
In [19]:
divvy_data['trip_time'].astype('timedelta64[m]')
Out[19]:
In [20]:
divvy_data['trip_time_mins'] = divvy_data['trip_time'].astype('timedelta64[m]')
In [21]:
divvy_data.head()
Out[21]:
In [23]:
divvy_data[divvy_data['trip_time_mins'] < 60].trip_time_mins.hist()
Out[23]:
In [26]:
divvy_data[divvy_data['trip_time_mins'] < 2]['trip_time_mins'].count()
Out[26]:
In [27]:
divvy_data[divvy_data['trip_time_mins'] < 10]['trip_time_mins'].hist()
Out[27]:
In [30]:
divvy_data[(divvy_data['from_lat'] == divvy_data['to_lat']) & (divvy_data['trip_time_mins'] < 4)].trip_time_mins.count()
Out[30]:
In [31]:
divvy_data[(divvy_data['from_lat'] != divvy_data['to_lat']) & (divvy_data['trip_time_mins'] < 4)].trip_time_mins.count()
Out[31]:
In [32]:
divvy_data[divvy_data['trip_time_mins'] >30].trip_time_mins.count()
Out[32]:
In [33]:
divvy_data.head()
Out[33]:
In [35]:
divvy_data.user_type.unique()
Out[35]:
In [37]:
divvy_data.groupby("user_type").count()
Out[37]:
In [ ]: