1. X=df.iloc[:, :-1].values
2. y=df.iloc[:, -1].values
3.  
4.  
5. # adding extra column because of Multiple linear regression
6. X_select = np.concatenate((X[:,9:10],X[:,10:11]), axis=1)
7. X_select_square = np.square(X_select)
8. X_select = X
9. #X_square = np.square(X_select)
10. #X_select = np.hstack((X_select, X_select_square))
11. X_t=np.append(arr=np.ones((X_select.shape[0],1)), values=X_select, axis=1)
12.  
13. # splitting the dataset
14. X_train, X_test, y_train, y_test = train_test_split(X_select, y, test_size=0.5, random_state=0)
15.  
16.  
17.  
18. # scaling the dataset
19. from sklearn.preprocessing import StandardScaler
20. sc_X=StandardScaler()
21. X_train=sc_X.fit_transform(X_train)
22. X_test=sc_X.transform(X_test)
23.  
24.  
25.  
26. #linear regression
27. #from sklearn.linear_model import LinearRegression
28. #regressor=LinearRegression()
29. from sklearn.linear_model import LogisticRegression
30. regressor=LogisticRegression()
31. regressor.fit(X_train,y_train)
32.  
33.  
34.  
35. #Prediction
36. predictions=regressor.predict(X_test)
37. for i, prediction in enumerate(predictions):
38.     print('Predicted: %s, Target: %s' % (prediction, y_test[i]))
39. score = regressor.score(X_test, y_test)
40. print('R-squared: %.2f' % regressor.score(X_test, y_test))