更新 function.py

function.py

@@ -26,6 +26,16 @@ name = "刘义天"
 
 
 def load_data(filepath):
+    """
+    Load data from a specified file path and handle missing values.
+
+    Args:
+    - filepath (str): The path to the data file.
+
+    Returns:
+    - np.array: Feature data.
+    - np.array: Label data.
+    """
     data = []
     with open(filepath, 'r') as file:
         for line in file:
@@ -44,6 +54,20 @@ def load_data(filepath):
 
 
 def train_logreg(X, y, learning_rate=0.1, n_estimators=200, max_depth=5):
+    """
+    Train a Gradient Boosting model.
+
+    Args:
+    - X (numpy array): Feature data.
+    - y (numpy array): Label data.
+    - learning_rate (float): Learning rate for gradient boosting.
+    - n_estimators (int): Number of trees.
+    - max_depth (int): Maximum depth of each tree.
+
+    Returns:
+    - GradientBoostingClassifier: Trained Gradient Boosting model as weights.
+    - StandardScaler: Scaler fitted on training data for consistent scaling.
+    """
     scaler = StandardScaler()
     X = scaler.fit_transform(X)
     
@@ -54,10 +78,23 @@ def train_logreg(X, y, learning_rate=0.1, n_estimators=200, max_depth=5):
         random_state=42
     )
     gb_model.fit(X, y)
+    
+    # Return model and scaler separately
     return gb_model, scaler
 
 
 def predict_logreg(inX, model, scaler):
+    """
+    Predict the class label for a given sample using Gradient Boosting.
+
+    Args:
+    - inX (numpy array): Input sample for classification.
+    - model (GradientBoostingClassifier): Trained model.
+    - scaler (StandardScaler): Scaler for feature normalization.
+
+    Returns:
+    - int: Predicted class label (0 or 1).
+    """
     inX = scaler.transform([inX])
     prediction = model.predict(inX)
     return int(prediction[0])
@@ -73,4 +110,4 @@ if __name__ == "__main__":
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], model, scaler)
-    print(f"预测结果: {y_pred}, 实际结果: {int(y_test[11])}")
+    print(f"预测结果: {y_pred}, 实际结果: {int(y_test[11])}")