In [1]:

    

import pandas as pd
import numpy as np
import matplotlib as plt

df = pd.read_csv("http://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data",sep=',\s', na_values=["?"])
df.columns = ("age", "type_employer", "fnlwgt", "education", 
                "education_num","marital", "occupation", "relationship", "race","sex",
                "capital_gain", "capital_loss", "hr_per_week","country", "income")
del df['fnlwgt']

df.dropna(how='any',inplace=True)
df1= df.drop_duplicates(keep="first")
df1.isnull().sum()
df1.type_employer.value_counts()


    

    




C:\anaconda\lib\site-packages\ipykernel\__main__.py:5: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.






    
Out[1]:





Private             19214
Self-emp-not-inc     2431
Local-gov            2014
State-gov            1252
Self-emp-inc         1049
Federal-gov           929
Without-pay            14
Name: type_employer, dtype: int64

In [2]:

    

df1.replace(['Local-gov','State-gov','Federal-gov'],['Gov','Gov','Gov'],inplace=True)


    

    




C:\anaconda\lib\site-packages\ipykernel\__main__.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  if __name__ == '__main__':

In [3]:

    

df1.replace(['Self-emp-not-inc','Self-emp-inc'],['self-emp','self-emp'],inplace=True)


    

    




C:\anaconda\lib\site-packages\ipykernel\__main__.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  if __name__ == '__main__':

In [4]:

    

df1.replace(['Prof-specialty','Adm-clerical','Other-service','Priv-house-serv','Craft-repair','Machine-op-inspct','Transport-moving','Handlers-cleaners','Farming-fishing'],
            ['Professional','Admin','Service','Service','Blue-Collar','Blue-Collar','Blue-Collar','Blue-Collar','Blue-Collar'],inplace=True)


    

    




C:\anaconda\lib\site-packages\ipykernel\__main__.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  from ipykernel import kernelapp as app

In [5]:

    

del df1['capital_gain']
del df1['capital_loss']


    

In [6]:

    

import random
from numba import jit
import matplotlib.pyplot as plt
%matplotlib inline
plt.style.use('bmh')
plt.rcParams['figure.figsize'] = (10, 7)


    

In [7]:

    

import random

def sample(df1, n):
    reservoirs = []
    for t, row in df1.iterrows():
        if t < n:
            reservoirs.append(row)
        else:
            m = random.randint(0,t)
            if m < n:
                reservoirs[m] = row
                t=t+1
    return reservoirs


    

In [8]:

    

df2=pd.DataFrame(sample(df1,10))
df2


    

    
Out[8]:






  

    

      

      
age
      
type_employer
      
education
      
education_num
      
marital
      
occupation
      
relationship
      
race
      
sex
      
hr_per_week
      
country
      
income
    
  
  

    

      
5699
      
49
      
Private
      
7th-8th
      
4
      
Married-civ-spouse
      
Blue-Collar
      
Husband
      
White
      
Male
      
48
      
United-States
      
<=50K
    
    

      
21093
      
23
      
Private
      
12th
      
8
      
Never-married
      
Blue-Collar
      
Own-child
      
White
      
Female
      
40
      
United-States
      
<=50K
    
    

      
18111
      
46
      
Gov
      
Some-college
      
10
      
Married-civ-spouse
      
Exec-managerial
      
Husband
      
White
      
Male
      
48
      
United-States
      
>50K
    
    

      
281
      
34
      
Private
      
Assoc-acdm
      
12
      
Divorced
      
Sales
      
Unmarried
      
Black
      
Female
      
45
      
United-States
      
<=50K
    
    

      
13470
      
22
      
Private
      
Some-college
      
10
      
Never-married
      
Service
      
Not-in-family
      
White
      
Female
      
50
      
United-States
      
<=50K
    
    

      
24050
      
23
      
Private
      
HS-grad
      
9
      
Never-married
      
Sales
      
Own-child
      
White
      
Male
      
30
      
United-States
      
<=50K
    
    

      
15434
      
47
      
Private
      
Bachelors
      
13
      
Married-civ-spouse
      
Sales
      
Husband
      
White
      
Male
      
60
      
United-States
      
>50K
    
    

      
19458
      
55
      
Private
      
HS-grad
      
9
      
Married-civ-spouse
      
Blue-Collar
      
Husband
      
White
      
Male
      
40
      
United-States
      
>50K
    
    

      
10432
      
27
      
Private
      
HS-grad
      
9
      
Never-married
      
Service
      
Not-in-family
      
White
      
Female
      
52
      
United-States
      
<=50K
    
    

      
13908
      
37
      
self-emp
      
HS-grad
      
9
      
Divorced
      
Blue-Collar
      
Not-in-family
      
White
      
Male
      
50
      
United-States
      
<=50K
    
  

In [ ]: