更新 function.py

function.py

@@ -3,15 +3,12 @@ import numpy as np
 id = "202210423210"
 name = "陈宇杰"
 
-# Sigmoid Function
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-# 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
-    prev_weights = np.copy(weights)
+    weights = np.zeros(n)
 
     for j in range(iterations):
         dataIndex = np.random.permutation(m)
@@ -20,63 +17,55 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=128, lamb
             batch_X = X[dataIndex[i:end]]
             batch_y = y[dataIndex[i:end]]
 
-            # Vectorized gradient calculation
             z = np.dot(batch_X, weights)
             h = sigmoid(z)
 
             error = batch_y - h
             gradient = np.dot(batch_X.T, error) / len(batch_y)
             gradient -= lambda_reg * weights / len(batch_y)
-            
             weights += learning_rate * gradient
 
-        # Early stopping condition
-        if np.linalg.norm(weights - prev_weights) < 1e-5:
-            print(f"Converged after {j} iterations.")
-            break
-        prev_weights = np.copy(weights)
-
     return weights
 
-def predict_logreg(X, weights):
-    probabilities = sigmoid(np.dot(X, weights))
-    return (probabilities >= 0.5).astype(int)
+def predict_logreg(inX, weights):
+    probability = sigmoid(np.dot(inX, weights))
+    return 1 if probability >= 0.5 else 0
 
-# Data Loading Function
 def load_data(filepath):
-    data, labels = [], []
+    data = []
+    labels = []
     with open(filepath, 'r') as file:
         for line in file:
             parts = line.strip().split()
-            features = [float(x) if x != '?' else 0.0 for x in parts[:-1]]
+            features = parts[:-1]
             label = parts[-1]
+            features = [float(x) if x != '?' else 0.0 for x in features]
             data.append(features)
             labels.append(1 if label in ['2', '3'] else 0)
 
-    # Convert to numpy arrays
+    # 转换为numpy数组
     data = np.array(data)
     labels = np.array(labels)
     
+    # 简单均值归一化
+    data_mean = np.mean(data, axis=0)
+    data_std = np.std(data, axis=0)
+    data = (data - data_mean) / (data_std + 1e-10)  # 防止除零
+
     return data, labels
 
-# Main script
-if __name__ == "__main__":
-    # Load training data
+if name == "main":
     X_train, y_train = load_data("./data/horse-colic.data")
-    # Calculate mean and std from training data
-    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
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=2000, batch_size=64, lambda_reg=0.01)
 
-    # Make predictions and calculate accuracy
-    y_pred = predict_logreg(X_test, weights)
-    accuracy = np.mean(y_pred == y_test)
+    error_count = 0
+    for i in range(len(y_test)):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred != y_test[i]:
+            error_count += 1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
 
-    print(f"Accuracy: {accuracy:.2f}")
+    accuracy = (len(y_test) - error_count) / len(y_test)
+    print(f"准确率: {accuracy:.2f}")