In [32]:

    

import pandas as pd


    

In [33]:

    

df = pd.DataFrame({'name': ['Alice', 'Bob', 'Charlie', 'Danielle'],
                   'balance': [100.0, 200.0, 300.0, 400.0],
                   'gender': ['Female', 'Male', 'Male', 'Female']},
                   columns=['name', 'balance', 'gender'])


    

In [34]:

    

df.dtypes


    

    
Out[34]:





name        object
balance    float64
gender      object
dtype: object

In [35]:

    

df['gender'] = df['gender'].astype('category')


    

In [36]:

    

df


    

    
Out[36]:






  

    

      

      
name
      
balance
      
gender
    
  
  

    

      
0
      
Alice
      
100
      
Female
    
    

      
1
      
Bob
      
200
      
Male
    
    

      
2
      
Charlie
      
300
      
Male
    
    

      
3
      
Danielle
      
400
      
Female
    
  

In [37]:

    

df.dtypes


    

    
Out[37]:





name         object
balance     float64
gender     category
dtype: object

In [38]:

    

df.gender


    

    
Out[38]:





0    Female
1      Male
2      Male
3    Female
Name: gender, dtype: category
Categories (2, object): [Female, Male]

In [39]:

    

df.gender.cat.categories


    

    
Out[39]:





Index([u'Female', u'Male'], dtype='object')

In [40]:

    

df.gender.cat.codes


    

    
Out[40]:





0    0
1    1
2    1
3    0
dtype: int8

In [41]:

    

df = pd.read_csv('trip_data_1.csv')


    

In [42]:

    

df.head()


    

    
Out[42]:






  

    

      

      
medallion
      
hack_license
      
vendor_id
      
rate_code
      
store_and_fwd_flag
      
pickup_datetime
      
dropoff_datetime
      
passenger_count
      
trip_time_in_secs
      
trip_distance
      
pickup_longitude
      
pickup_latitude
      
dropoff_longitude
      
dropoff_latitude
    
  
  

    

      
0
      
89D227B655E5C82AECF13C3F540D4CF4
      
BA96DE419E711691B9445D6A6307C170
      
CMT
      
1
      
N
      
2013-01-01 15:11:48
      
2013-01-01 15:18:10
      
4
      
382
      
1.0
      
-73.978165
      
40.757977
      
-73.989838
      
40.751171
    
    

      
1
      
0BD7C8F5BA12B88E0B67BED28BEA73D8
      
9FD8F69F0804BDB5549F40E9DA1BE472
      
CMT
      
1
      
N
      
2013-01-06 00:18:35
      
2013-01-06 00:22:54
      
1
      
259
      
1.5
      
-74.006683
      
40.731781
      
-73.994499
      
40.750660
    
    

      
2
      
0BD7C8F5BA12B88E0B67BED28BEA73D8
      
9FD8F69F0804BDB5549F40E9DA1BE472
      
CMT
      
1
      
N
      
2013-01-05 18:49:41
      
2013-01-05 18:54:23
      
1
      
282
      
1.1
      
-74.004707
      
40.737770
      
-74.009834
      
40.726002
    
    

      
3
      
DFD2202EE08F7A8DC9A57B02ACB81FE2
      
51EE87E3205C985EF8431D850C786310
      
CMT
      
1
      
N
      
2013-01-07 23:54:15
      
2013-01-07 23:58:20
      
2
      
244
      
0.7
      
-73.974602
      
40.759945
      
-73.984734
      
40.759388
    
    

      
4
      
DFD2202EE08F7A8DC9A57B02ACB81FE2
      
51EE87E3205C985EF8431D850C786310
      
CMT
      
1
      
N
      
2013-01-07 23:25:03
      
2013-01-07 23:34:24
      
1
      
560
      
2.1
      
-73.976250
      
40.748528
      
-74.002586
      
40.747868
    
  

In [43]:

    

%time
df.groupby(df.medallion).trip_distance.sum().sort(ascending=False, inplace=False).head()


    

    




CPU times: user 8 µs, sys: 2 µs, total: 10 µs
Wall time: 59.1 µs






    
Out[43]:





medallion
6945300E90C69061B463CCDA370DE5D6    5391.43
6BD1B641A1CD55803A21560299B985A7    5359.30
8211BE04462ADE4621B68E1DFEA54754    5342.80
0076C8327A95E988E721AC33B0FA9D67    5276.70
6B19837BFEAA374B7B4694799D7CC746    5149.70
Name: trip_distance, dtype: float64

In [44]:

    

%time df['medallion'] = df['medallion'].astype('category')


    

    




CPU times: user 2.64 s, sys: 1.7 s, total: 4.34 s
Wall time: 5.05 s

In [45]:

    

%time
df.groupby(df.medallion).trip_distance.sum().sort(ascending=False, inplace=False).head()


    

    




CPU times: user 4 µs, sys: 1 µs, total: 5 µs
Wall time: 10 µs






    
Out[45]:





medallion
6945300E90C69061B463CCDA370DE5D6    5391.43
6BD1B641A1CD55803A21560299B985A7    5359.30
8211BE04462ADE4621B68E1DFEA54754    5342.80
0076C8327A95E988E721AC33B0FA9D67    5276.70
6B19837BFEAA374B7B4694799D7CC746    5149.70
Name: trip_distance, dtype: float64

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: