更新 function.py

function.py

@@ -3,14 +3,14 @@ import numpy as np
 id="202210423210"
 name="陈宇杰"
 
-# Utility Functions
+# Sigmoid Function
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-# Optimized Logistic Regression Training
+# Optimized Logistic Regression Training Function
 def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=128, lambda_reg=0.01):
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # Initialize weights with small random values for faster convergence
+    weights = np.random.randn(n) * 0.01  # Initialize weights with small random values
     prev_weights = np.copy(weights)
 
     for j in range(iterations):
@@ -30,7 +30,7 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=128, lamb
             
             weights += learning_rate * gradient
 
-        # Early stopping: Check for convergence
+        # Early stopping condition
         if np.linalg.norm(weights - prev_weights) < 1e-5:
             print(f"Converged after {j} iterations.")
             break
@@ -42,7 +42,7 @@ def predict_logreg(X, weights):
     probabilities = sigmoid(np.dot(X, weights))
     return (probabilities >= 0.5).astype(int)
 
-# Load Data Function
+# Data Loading Function
 def load_data(filepath):
     data, labels = [], []
     with open(filepath, 'r') as file:
@@ -53,22 +53,23 @@ def load_data(filepath):
             data.append(features)
             labels.append(1 if label in ['2', '3'] else 0)
 
+    # Convert to numpy arrays
     data = np.array(data)
     labels = np.array(labels)
     
-    # Normalize data
+    return data, labels
-    data_mean = np.mean(data, axis=0)
-    data_std = np.std(data, axis=0)
-    data = (data - data_mean) / (data_std + 1e-10)
 
-    return data, labels, data_mean, data_std
+# Main script
-
-# Load and Preprocess Data
 if __name__ == "__main__":
-    # Training data
+    # Load training data
-    X_train, y_train, data_mean, data_std = load_data("./data/horse-colic.data")
+    X_train, y_train = load_data("./data/horse-colic.data")
-    # Normalize test data using training mean and std
+    # Calculate mean and std from training data
-    X_test, y_test, _, _ = load_data("./data/horse-colic.test")
+    data_mean = np.mean(X_train, axis=0)
+    data_std = np.std(X_train, axis=0)
+    X_train = (X_train - data_mean) / (data_std + 1e-10)
+
+    # Load and normalize test data using training mean and std
+    X_test, y_test = load_data("./data/horse-colic.test")
     X_test = (X_test - data_mean) / (data_std + 1e-10)
 
     # Train model