In [1]:

    

import numpy as np
import pandas as pd
from sklearn.svm import SVR
from sklearn.linear_model import Lasso
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import StandardScaler
from sklearn.cross_validation import train_test_split


    

In [2]:

    

# input data reading
df = pd.read_csv("winequality-white.csv", sep=";")
df.head()


    

    
Out[2]:






  

    

      

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

    

      
0
      
7.0
      
0.27
      
0.36
      
20.7
      
0.045
      
45
      
170
      
1.0010
      
3.00
      
0.45
      
8.8
      
6
    
    

      
1
      
6.3
      
0.30
      
0.34
      
1.6
      
0.049
      
14
      
132
      
0.9940
      
3.30
      
0.49
      
9.5
      
6
    
    

      
2
      
8.1
      
0.28
      
0.40
      
6.9
      
0.050
      
30
      
97
      
0.9951
      
3.26
      
0.44
      
10.1
      
6
    
    

      
3
      
7.2
      
0.23
      
0.32
      
8.5
      
0.058
      
47
      
186
      
0.9956
      
3.19
      
0.40
      
9.9
      
6
    
    

      
4
      
7.2
      
0.23
      
0.32
      
8.5
      
0.058
      
47
      
186
      
0.9956
      
3.19
      
0.40
      
9.9
      
6
    
  

In [3]:

    

# independent variables and dependent variable
x = df.loc[:, : "alcohol"]
y = df["quality"]


    

In [4]:

    

# features have to be scaled before model learning
scaler = StandardScaler()
x = scaler.fit_transform(x)


    

In [5]:

    

# spliting data to train and test parts
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=1)


    

In [66]:

    

# create and fit LASSO and SVR models 
lasso = Lasso(alpha=0.001)
svr = SVR(C=8, epsilon=0.2, gamma=0.5)
lasso.fit(x_train, y_train)
svr.fit(x_train, y_train)


    

    
Out[66]:





SVR(C=8, cache_size=200, coef0=0.0, degree=3, epsilon=0.2, gamma=0.5,
  kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False)

In [67]:

    

# make prediction on test data and rounding results
y_pred_lasso = np.round(np.clip(lasso.predict(x_test), 1, 10)).astype(int)
y_pred_svr = np.round(np.clip(svr.predict(x_test), 1, 10)).astype(int)


    

In [68]:

    

np.round(1 - mean_squared_error(y_test, y_pred_lasso) / y_test.std(), 2)


    

    
Out[68]:





0.28000000000000003

In [69]:

    

np.round(1 - mean_squared_error(y_test, y_pred_svr) / y_test.std(), 2)


    

    
Out[69]:





0.5