In [ ]:

    

"""
Inspired from the "Introduction to Statistical Learning" of James et al.
where we see a scatter plot of two variables and  the corresponding boxplots.

It can be particularily useful for a binary classification case where we have to pass
the target binary variable too.
"""


    

In [1]:

    

# necessary imports
import pandas as pd
import numpy as np
%load_ext autoreload
%autoreload 2
import sys
sys.path.append("../lib_plot")
#import db_to_pd as ddd
import scatter_boxplot as sbp

%matplotlib inline


    

    




/Users/charilaostsarouchas/anaconda/lib/python2.7/site-packages/pytz/__init__.py:29: UserWarning: Module argparse was already imported from /Users/charilaostsarouchas/anaconda/lib/python2.7/argparse.pyc, but /Users/charilaostsarouchas/anaconda/lib/python2.7/site-packages is being added to sys.path
  from pkg_resources import resource_stream

In [2]:

    

# download the data concerning the defaults of credit cards 
# — the dataset is provided by James et al., Introduction to Statistical Learning.

# sample found online in this link http://www.datarobot.com/blog/classification-with-scikit-learn/
# or maybe here:
#http://www-bcf.usc.edu/~gareth/ISL/Credit.csv


df = pd.read_csv('https://d1pqsl2386xqi9.cloudfront.net/notebooks/Default.csv', index_col=0)
# we need to transform the default var to boolean
df['target'] = df['default'].apply(lambda x: True if x=='Yes' else False)
df.head()


    

    
Out[2]:






  

    

      

      
default
      
student
      
balance
      
income
      
target
    
  
  

    

      
1
      
 No
      
  No
      
  729.526495
      
 44361.625074
      
 False
    
    

      
2
      
 No
      
 Yes
      
  817.180407
      
 12106.134700
      
 False
    
    

      
3
      
 No
      
  No
      
 1073.549164
      
 31767.138947
      
 False
    
    

      
4
      
 No
      
  No
      
  529.250605
      
 35704.493935
      
 False
    
    

      
5
      
 No
      
  No
      
  785.655883
      
 38463.495879
      
 False
    
  

In [3]:

    

# see the scatter plot and the relevant boxplots
sbp.plot_2d_data(df, 'balance', 'income', 'target' , filename=None, title='', xlabel='', ylabel='')


    

In [ ]: