from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.5, random_state = 0)

X=df.iloc[:, :-1].values
y=df.iloc[:, -1].values


# adding extra column because of Multiple linear regression
X_select = np.concatenate((X[:,9:10],X[:,10:11]), axis=1)
X_select_square = np.square(X_select)
X_select = X
#X_square = np.square(X_select)
#X_select = np.hstack((X_select, X_select_square))
X_t=np.append(arr=np.ones((X_select.shape[0],1)), values=X_select, axis=1)

# splitting the dataset
X_train, X_test, y_train, y_test = train_test_split(X_select, y, test_size=0.5, random_state=0)



# scaling the dataset
from sklearn.preprocessing import StandardScaler
sc_X=StandardScaler()
X_train=sc_X.fit_transform(X_train)
X_test=sc_X.transform(X_test)



#linear regression
#from sklearn.linear_model import LinearRegression
#regressor=LinearRegression()
from sklearn.linear_model import LogisticRegression
regressor=LogisticRegression()
regressor.fit(X_train,y_train)



#Prediction
predictions=regressor.predict(X_test)
for i, prediction in enumerate(predictions):
    print('Predicted: %s, Target: %s' % (prediction, y_test[i]))
score = regressor.score(X_test, y_test)
print('R-squared: %.2f' % regressor.score(X_test, y_test))