In [1]:

    

from datetime import datetime
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

#%load_ext autoreload
#%autoreload 2
%matplotlib inline
%config InlineBackend.figure_format = 'retina'


    

In [4]:

    

pwd


    

    
Out[4]:





'C:\\Users\\gary\\Documents\\data'

In [3]:

    

cd C:\Users\gary\Documents\data


    

    




C:\Users\gary\Documents\data

In [5]:

    

ls


    

    




 Volume in drive C is OS
 Volume Serial Number is F8CA-7CC7

 Directory of C:\Users\gary\Documents\data

07/02/2017  04:16 PM    <DIR>          .
07/02/2017  04:16 PM    <DIR>          ..
07/02/2017  08:15 AM    <DIR>          atusact_2016
07/01/2017  09:25 AM         3,684,229 atusact_2016.zip
07/02/2017  08:15 AM    <DIR>          atuscps_2016
07/01/2017  09:26 AM         6,860,353 atuscps_2016.zip
07/02/2017  09:28 AM           864,474 atuscpscodebk16.pdf
07/02/2017  09:29 AM           570,216 atusintcodebk16.pdf
07/01/2017  09:35 AM    <DIR>          atusresp_2016
07/01/2017  09:25 AM           841,679 atusresp_2016.zip
07/02/2017  08:15 AM    <DIR>          atusrost_2016
07/01/2017  09:25 AM           144,334 atusrost_2016.zip
07/02/2017  08:17 AM    <DIR>          atusrostec_2016
07/01/2017  09:26 AM            23,198 atusrostec_2016.zip
07/02/2017  08:17 AM    <DIR>          atussum_2016
07/01/2017  09:25 AM           713,076 atussum_2016.zip
07/02/2017  08:17 AM    <DIR>          atuswho_2016
07/01/2017  09:25 AM           841,409 atuswho_2016.zip
07/02/2017  04:16 PM    <DIR>          cps_00001.csv
07/02/2017  04:15 PM         1,215,296 cps_00001.csv.gz
07/02/2017  09:26 AM            70,656 hinc01_1.xls
              11 File(s)     15,828,920 bytes
              10 Dir(s)  669,635,338,240 bytes free

In [6]:

    

filename = 'cps_00001.csv/cps_00001.csv'
resp = pd.read_csv(filename)
resp.describe()


    

    
Out[6]:







  

    

      

      
YEAR
      
SERIAL
      
HWTSUPP
      
ASECFLAG
      
HHINCOME
      
WTSUPP
    
  
  

    

      
count
      
185487.0
      
185487.000000
      
185487.000000
      
185487.0
      
1.854870e+05
      
185487.000000
    
    

      
mean
      
2016.0
      
48751.964774
      
1679.426439
      
1.0
      
9.119382e+04
      
1719.088077
    
    

      
std
      
0.0
      
27496.014576
      
1022.340851
      
0.0
      
9.988669e+04
      
1065.911059
    
    

      
min
      
2016.0
      
2.000000
      
101.190000
      
1.0
      
-9.999000e+03
      
69.880000
    
    

      
25%
      
2016.0
      
24557.000000
      
834.760000
      
1.0
      
3.510700e+04
      
846.260000
    
    

      
50%
      
2016.0
      
49263.000000
      
1640.200000
      
1.0
      
6.900000e+04
      
1651.990000
    
    

      
75%
      
2016.0
      
73243.000000
      
2133.940000
      
1.0
      
1.165530e+05
      
2218.350000
    
    

      
max
      
2016.0
      
94097.000000
      
8148.970000
      
1.0
      
2.289913e+06
      
12515.280000
    
  

In [7]:

    

resp.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 185487 entries, 0 to 185486
Data columns (total 6 columns):
YEAR        185487 non-null int64
SERIAL      185487 non-null int64
HWTSUPP     185487 non-null float64
ASECFLAG    185487 non-null int64
HHINCOME    185487 non-null int64
WTSUPP      185487 non-null float64
dtypes: float64(2), int64(4)
memory usage: 8.5 MB

In [8]:

    

list(resp)


    

    
Out[8]:





['YEAR', 'SERIAL', 'HWTSUPP', 'ASECFLAG', 'HHINCOME', 'WTSUPP']

In [9]:

    

resp.head()


    

    
Out[9]:







  

    

      

      
YEAR
      
SERIAL
      
HWTSUPP
      
ASECFLAG
      
HHINCOME
      
WTSUPP
    
  
  

    

      
0
      
2016
      
2
      
1132.05
      
1
      
13309
      
1132.05
    
    

      
1
      
2016
      
7
      
1077.54
      
1
      
29296
      
1077.54
    
    

      
2
      
2016
      
7
      
1077.54
      
1
      
29296
      
1077.54
    
    

      
3
      
2016
      
8
      
1151.49
      
1
      
24099
      
1151.49
    
    

      
4
      
2016
      
9
      
705.00
      
1
      
6300
      
705.00
    
  

In [33]:

    

percent = 0.01
n  = percent * len(resp)
int(n)


    

    
Out[33]:





1854

In [35]:

    

top01 = resp.nlargest(int(n), 'HHINCOME')
top01.HHINCOME.min(), top01.HHINCOME.max()


    

    
Out[35]:





(441050, 2289913)

In [11]:

    

np.percentile(resp.HHINCOME, 12)


    

    
Out[11]:





20000.0

In [15]:

    

np.percentile(resp.HHINCOME, 24)


    

    
Out[15]:





34315.0

In [16]:

    

np.percentile(resp.HHINCOME, 54)


    

    
Out[16]:





75010.0

In [17]:

    

np.percentile(resp.HHINCOME, 84)


    

    
Out[17]:





146892.67999999993

In [18]:

    

np.percentile(resp.HHINCOME, 99)


    

    
Out[18]:





440857.35999999661

In [ ]: