Homework 2 - Classification Dataset

In [10]:

    

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split


    

In [11]:

    

redSetPath = "classification/winequality-red.csv"
# whiteSetPath = "classification/winequality-white.csv"


    

In [12]:

    

#Reading in the raw data. Note that the features are seperated by ';' character 
redSet = pd.read_csv(redSetPath, sep=';')
# whiteSet = pd.read_csv(whiteSetPath, sep=';')


    

In [14]:

    

# redSet.drop(['index'], axis=1, inplace=True)
redSet.head()


    

    
Out[14]:







  

    

      

      
fixed acidity
      
volatile acidity
      
citric acid
      
residual sugar
      
chlorides
      
free sulfur dioxide
      
total sulfur dioxide
      
density
      
pH
      
sulphates
      
alcohol
      
quality
    
  
  

    

      
0
      
7.4
      
0.70
      
0.00
      
1.9
      
0.076
      
11.0
      
34.0
      
0.9978
      
3.51
      
0.56
      
9.4
      
5
    
    

      
1
      
7.8
      
0.88
      
0.00
      
2.6
      
0.098
      
25.0
      
67.0
      
0.9968
      
3.20
      
0.68
      
9.8
      
5
    
    

      
2
      
7.8
      
0.76
      
0.04
      
2.3
      
0.092
      
15.0
      
54.0
      
0.9970
      
3.26
      
0.65
      
9.8
      
5
    
    

      
3
      
11.2
      
0.28
      
0.56
      
1.9
      
0.075
      
17.0
      
60.0
      
0.9980
      
3.16
      
0.58
      
9.8
      
6
    
    

      
4
      
7.4
      
0.70
      
0.00
      
1.9
      
0.076
      
11.0
      
34.0
      
0.9978
      
3.51
      
0.56
      
9.4
      
5
    
  

In [15]:

    

# whiteSet.head()


    

In [16]:

    

#Breaking the datasets into 70% training and 30% testing
red_train, red_test  = train_test_split(redSet,test_size=0.30)
red_train, red_valid = train_test_split(red_train,test_size=0.20)

# white_train, white_test  = train_test_split(whiteSet,test_size=0.30)
# white_train, white_valid = train_test_split(white_train,test_size=0.20)


    

In [17]:

    

# Red Wine
red_train_path = "classification/red_train.csv"
red_valid_path = "classification/red_valid.csv"
red_test_path  = "classification/red_test.csv"

# # White Wine
# white_train_path  = "classification/white_train.csv"
# white_valid_path  = "classification/white_valid.csv"
# white_test_path   = "classification/white_test.csv"


    

In [18]:

    

red_train.to_csv(path_or_buf=red_train_path, index=False)
red_valid.to_csv(path_or_buf=red_valid_path, index=False)
red_test.to_csv(path_or_buf=red_test_path, index=False)

# white_train.to_csv(path_or_buf=white_train_path, sep=';')
# white_valid.to_csv(path_or_buf=white_valid_path, sep=';')
# white_test.to_csv(path_or_buf=white_test_path, sep=';')


    

In [19]:

    

print 'Red Wine - Number of Instances Per Set'
print 'Training Set:   %d'%(len(red_train))
print 'Validation Set: %d'%(len(red_valid))
print 'Testing Set:    %d'%(len(red_test))

# print ''
# print ''

# print 'White Wine - Number of Instances Per Set'
# print 'Training Set:   %d'%(len(white_train))
# print 'Validation Set: %d'%(len(white_valid))
# print 'Testing Set:    %d'%(len(white_test))


    

    




Red Wine - Number of Instances Per Set
Training Set:   895
Validation Set: 224
Testing Set:    480

In [ ]: