更新 function.py

function.py

@@ -29,12 +29,17 @@ name = "章程鸿"
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
+
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32, regularization_strength=0.1):
+
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
     m, n = X.shape
     weights = np.random.randn(n) * 0.01
+    best_weights = weights.copy()
+    best_accuracy = 0
+    wait = 0
 
     for i in range(iterations):
         indices = np.random.permutation(m)
@@ -44,18 +49,28 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32, regul
         for j in range(0, m, batch_size):
             X_batch = X_shuffled[j:j + batch_size]
             y_batch = y_shuffled[j:j + batch_size]
-
             z = np.dot(X_batch, weights)
             h = sigmoid(z)
-            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch) + regularization_strength * weights
+            gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+
             weights -= learning_rate * gradient
 
-    return weights
+        # 计算训练集准确率
+        train_accuracy = accuracy(X, y, weights)
+        if train_accuracy > best_accuracy:
+            best_accuracy = train_accuracy
+            best_weights = weights.copy()
+            wait = 0
+        else:
+            wait += 1
+
+    return best_weights
+
 
 def predict_logreg(X, weights):
     z = np.dot(X, weights)
     h = sigmoid(z)
-    return np.where(h >= 0.5, 1, 0)
+    return np.where(h > 0.5, 1, 0)
 
 def load_data(filepath):
     data = []
@@ -70,16 +85,18 @@ def load_data(filepath):
 
     data = np.array(data)
     labels = np.array(labels)
+
     target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
 
     return data, target_variable
 
+
 def accuracy(X, y, weights):
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
+
 if __name__ == "__main__":
-    # 读取数据
     X_train, y_train = load_data("./horse-colic.data")
     X_test, y_test = load_data("./horse-colic.test")
 
@@ -88,9 +105,7 @@ if __name__ == "__main__":
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
-    # 训练模型
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000, batch_size=64)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
 
-    # 评估模型
     final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")