In [55]:

    

import pandas as pd
import numpy as np


    

In [68]:

    

np.set_printoptions(precision=2)


    

In [57]:

    

data = pd.read_csv("../data/beauty.csv", sep=";")


    

In [58]:

    

data.head()


    

    
Out[58]:







  

    

      

      
wage
      
exper
      
union
      
goodhlth
      
black
      
female
      
married
      
service
      
educ
      
looks
    
  
  

    

      
0
      
5.73
      
30
      
0
      
1
      
0
      
1
      
1
      
1
      
14
      
4
    
    

      
1
      
4.28
      
28
      
0
      
1
      
0
      
1
      
1
      
0
      
12
      
3
    
    

      
2
      
7.96
      
35
      
0
      
1
      
0
      
1
      
0
      
0
      
10
      
4
    
    

      
3
      
11.57
      
38
      
0
      
1
      
0
      
0
      
1
      
1
      
16
      
3
    
    

      
4
      
11.42
      
27
      
0
      
1
      
0
      
0
      
1
      
0
      
16
      
3
    
  

In [59]:

    

data.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1260 entries, 0 to 1259
Data columns (total 10 columns):
wage        1260 non-null float64
exper       1260 non-null int64
union       1260 non-null int64
goodhlth    1260 non-null int64
black       1260 non-null int64
female      1260 non-null int64
married     1260 non-null int64
service     1260 non-null int64
educ        1260 non-null int64
looks       1260 non-null int64
dtypes: float64(1), int64(9)
memory usage: 98.5 KB

In [60]:

    

data.describe()


    

    
Out[60]:







  

    

      

      
wage
      
exper
      
union
      
goodhlth
      
black
      
female
      
married
      
service
      
educ
      
looks
    
  
  

    

      
count
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
      
1260.000000
    
    

      
mean
      
6.306690
      
18.206349
      
0.272222
      
0.933333
      
0.073810
      
0.346032
      
0.691270
      
0.273810
      
12.563492
      
3.185714
    
    

      
std
      
4.660639
      
11.963485
      
0.445280
      
0.249543
      
0.261564
      
0.475892
      
0.462153
      
0.446089
      
2.624489
      
0.684877
    
    

      
min
      
1.020000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
5.000000
      
1.000000
    
    

      
25%
      
3.707500
      
8.000000
      
0.000000
      
1.000000
      
0.000000
      
0.000000
      
0.000000
      
0.000000
      
12.000000
      
3.000000
    
    

      
50%
      
5.300000
      
15.000000
      
0.000000
      
1.000000
      
0.000000
      
0.000000
      
1.000000
      
0.000000
      
12.000000
      
3.000000
    
    

      
75%
      
7.695000
      
27.000000
      
1.000000
      
1.000000
      
0.000000
      
1.000000
      
1.000000
      
1.000000
      
13.000000
      
4.000000
    
    

      
max
      
77.720000
      
48.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
1.000000
      
17.000000
      
5.000000
    
  

In [61]:

    

data['exper'].head()


    

    
Out[61]:





0    30
1    28
2    35
3    38
4    27
Name: exper, dtype: int64

In [62]:

    

type(data['exper'])


    

    
Out[62]:





pandas.core.series.Series

In [63]:

    

data.loc[0:5, ['wage', 'female']]


    

    
Out[63]:







  

    

      

      
wage
      
female
    
  
  

    

      
0
      
5.73
      
1
    
    

      
1
      
4.28
      
1
    
    

      
2
      
7.96
      
1
    
    

      
3
      
11.57
      
0
    
    

      
4
      
11.42
      
0
    
    

      
5
      
3.91
      
1
    
  

In [64]:

    

data.iloc[:,2:4].head()


    

    
Out[64]:







  

    

      

      
union
      
goodhlth
    
  
  

    

      
0
      
0
      
1
    
    

      
1
      
0
      
1
    
    

      
2
      
0
      
1
    
    

      
3
      
0
      
1
    
    

      
4
      
0
      
1
    
  

In [65]:

    

data[data['female'] == 1]['wage'].median(), \
data[data['female'] == 0]['wage'].median()


    

    
Out[65]:





(3.75, 6.41)

In [72]:

    

data[(data['female'] == 0) & (data['married'] == 1)]['wage'].median(), \
data[(data['female'] == 0) & (data['married'] != 1)]['wage'].median()


    

    
Out[72]:





(6.710000000000001, 5.0649999999999995)

In [82]:

    

for look, sub_df in data.groupby(['looks']):
    print(look, sub_df['female'].mean())


    

    




(1, 0.38461538461538464)
(2, 0.38028169014084506)
(3, 0.32271468144044324)
(4, 0.37362637362637363)
(5, 0.42105263157894735)

In [83]:

    

data.groupby('looks')['wage'].mean()


    

    
Out[83]:





looks
1    4.621538
2    5.328803
3    6.504598
4    6.299341
5    7.388421
Name: wage, dtype: float64

In [84]:

    

for look, sub_df in data.groupby(['looks', 'female']):
    print(look, sub_df['wage'].mean())


    

    




((1, 0), 6.16375)
((1, 1), 2.154)
((2, 0), 6.249090909090909)
((2, 1), 3.8290740740740743)
((3, 0), 7.598957055214724)
((3, 1), 4.207854077253218)
((4, 0), 7.226447368421053)
((4, 1), 4.745073529411764)
((5, 0), 9.923636363636364)
((5, 1), 3.9025)

In [90]:

    

data.groupby('looks')[['wage', 'exper']].agg(np.median)


    

    
Out[90]:







  

    

      

      
wage
      
exper
    
    

      
looks
      

      

    
  
  

    

      
1
      
3.460
      
32.0
    
    

      
2
      
4.595
      
18.0
    
    

      
3
      
5.635
      
18.0
    
    

      
4
      
5.240
      
12.5
    
    

      
5
      
4.810
      
8.0
    
  

In [94]:

    

pd.crosstab(data['female'], data['married'])


    

    
Out[94]:







  

    

      
married
      
0
      
1
    
    

      
female
      

      

    
  
  

    

      
0
      
166
      
658
    
    

      
1
      
223
      
213
    
  

In [97]:

    

pd.crosstab(data['female'], data['looks'])


    

    
Out[97]:







  

    

      
looks
      
1
      
2
      
3
      
4
      
5
    
    

      
female
      

      

      

      

      

    
  
  

    

      
0
      
8
      
88
      
489
      
228
      
11
    
    

      
1
      
5
      
54
      
233
      
136
      
8
    
  

In [111]:

    

data['is_rich'] = (data['wage'] > data['wage'].quantile(.75)).astype('int64')

print(data.head())


    

    




    wage  exper  union  goodhlth  black  female  married  service  educ  \
0   5.73     30      0         1      0       1        1        1    14   
1   4.28     28      0         1      0       1        1        0    12   
2   7.96     35      0         1      0       1        0        0    10   
3  11.57     38      0         1      0       0        1        1    16   
4  11.42     27      0         1      0       0        1        0    16   

   looks  is_rich  
0      4        0  
1      3        0  
2      4        1  
3      3        1  
4      3        1  

In [112]:

    

data.apply(np.mean)


    

    
Out[112]:





wage         6.306690
exper       18.206349
union        0.272222
goodhlth     0.933333
black        0.073810
female       0.346032
married      0.691270
service      0.273810
educ        12.563492
looks        3.185714
is_rich      0.250000
dtype: float64

In [114]:

    

def string_gender(female):
    return 'female' if female else 'male'


    

In [118]:

    

data['female'].apply(lambda female: 'female' if female else 'male')[:10]


    

    
Out[118]:





0    female
1    female
2    female
3      male
4      male
5    female
6      male
7      male
8    female
9    female
Name: female, dtype: object

In [120]:

    

d = {1: 'union', 0: 'nonunion'}


    

In [121]:

    

data['union'].map(d)[:5]


    

    
Out[121]:





0    nonunion
1    nonunion
2    nonunion
3    nonunion
4    nonunion
Name: union, dtype: object