from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor

X_train, X_test, y_train, y_test = train_test_split(X_C2, y_C2, random_state=0)

# k=1 يفرط في التلاؤم (حدود متعرجة جدا)؛ k الأكبر يعمم بشكل أفضل
clf = KNeighborsClassifier(n_neighbors=11).fit(X_train, y_train)

knnreg = KNeighborsRegressor(n_neighbors=5).fit(X_train, y_train)
print('R-squared test score: {:.3f}'.format(knnreg.score(X_test, y_test)))

from sklearn.linear_model import LinearRegression

linreg = LinearRegression().fit(X_train, y_train)
print('coeff (w): {}'.format(linreg.coef_))
print('intercept (b): {:.3f}'.format(linreg.intercept_))
print('R-squared (train): {:.3f}'.format(linreg.score(X_train, y_train)))
print('R-squared (test): {:.3f}'.format(linreg.score(X_test, y_test)))

from sklearn.linear_model import Ridge, Lasso
from sklearn.preprocessing import MinMaxScaler, PolynomialFeatures

scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)

linridge = Ridge(alpha=20.0).fit(X_train_scaled, y_train)   # عقوبة L2
linlasso = Lasso(alpha=2.0, max_iter=10000).fit(X_train_scaled, y_train)  # عقوبة L1، تدفع المعاملات نحو الصفر

poly = PolynomialFeatures(degree=2)
X_poly = poly.fit_transform(X_F1)   # يضيف تفاعلات سمات تربيعية

from sklearn.linear_model import LogisticRegression

clf = LogisticRegression(C=100).fit(X_train, y_train)
print('Accuracy on training set: {:.2f}'.format(clf.score(X_train, y_train)))
print('Accuracy on test set: {:.2f}'.format(clf.score(X_test, y_test)))

from sklearn.svm import SVC, LinearSVC

clf = SVC(kernel='linear', C=1.0).fit(X_train, y_train)
clf2 = LinearSVC(C=100).fit(X_train, y_train)

from sklearn.svm import SVC

clf = SVC(kernel='rbf', gamma=1.0, C=15).fit(X_train, y_train)   # النواة الافتراضية هي RBF
clf_poly = SVC(kernel='poly', degree=3).fit(X_train, y_train)

from sklearn.tree import DecisionTreeClassifier

clf = DecisionTreeClassifier().fit(X_train, y_train)          # تميل للإفراط في التلاؤم (دقة التدريب = 1.00)
clf2 = DecisionTreeClassifier(max_depth=3).fit(X_train, y_train)  # تحديد العمق لتقليل الإفراط في التلاؤم

print('Feature importances: {}'.format(clf.feature_importances_))