small update

2023-09-14 04:46:59 +02:00
parent 8aab9c6367
commit 4c79407670
2 changed files with 110 additions and 86 deletions
@@ -310,21 +310,23 @@ for p in range(d):
 #Split data in train and test
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

-print(X_train)
 # Scale data by subtracting mean value using scikit-learn
-from sklearn.preprocessing import StandardScaler
 scaler = StandardScaler()
 scaler.fit(X_train)
 X_train_scaled = scaler.transform(X_train)
-print(X_train_scaled)
+X_test_scaled = scaler.transform(X_test)
+
+y_train_scaled = y_train - np.mean(y_train)
+y_test_scaled = y_test - np.mean(y_test)
+

 #Calculate beta
 OLS = LinearRegression()
-OLS.fit(X_train,y_train_scaled)
-ypredictOLS = OLS.predict(X_test)
+OLS.fit(X_train_scaled,y_train_scaled)
+ypredictOLS = OLS.predict(X_test_scaled)
 RegRidge = linear_model.Ridge(Lambda)
-RegRidge.fit(X_train_scaled,y_train)
-ypredictRidge = RegRidge.predict(X_test)
+RegRidge.fit(X_train_scaled,y_train_scaled)
+ypredictRidge = RegRidge.predict(X_test_scaled)
 print(OLS.coef_)
 print(RegRidge.coef_)
 print(OLS.intercept_)