更新 function.py

function.py

@@ -26,17 +26,17 @@ from sklearn.ensemble import RandomForestClassifier
 id = "202210423117"
 name = "程悦"
 
-
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
 
-def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, patience=100, decay_rate=0.95):
     m, n = X.shape
     weights = np.random.randn(n) * 0.01
     best_weights = weights.copy()
     best_accuracy = 0
     wait = 0
+    decay_step = iterations // 10  # 每10%的迭代衰减一次学习率
 
     for i in range(iterations):
         indices = np.random.permutation(m)
@@ -49,11 +49,12 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
             z = np.dot(X_batch, weights)
             h = sigmoid(z)
             gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
-
             weights -= learning_rate * gradient
 
-        # 计算训练集准确率
+            # 计算训练集准确率
         train_accuracy = accuracy(X, y, weights)
+        print(f"Iteration {i + 1}, Train Accuracy: {train_accuracy:.4f}")
+
         if train_accuracy > best_accuracy:
             best_accuracy = train_accuracy
             best_weights = weights.copy()
@@ -61,8 +62,13 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64):
         else:
             wait += 1
 
-        if i % 100 == 0:
-            learning_rate *= 0.95
+        if i % decay_step == 0 and i > 0:
+            learning_rate *= decay_rate
+            print(f"Learning rate decayed to: {learning_rate:.6f}")
+
+        if wait >= patience:
+            print("Early stopping!")
+            break
 
     return best_weights
 
@@ -72,23 +78,24 @@ def predict_logreg(X, weights):
     h = sigmoid(z)
     return np.where(h > 0.5, 1, 0)
 
+
 def load_data(filepath):
     data = []
     labels = []
     with open(filepath, 'r') as f:
         for line in f:
-            line = line.strip().split()
-            if len(line) >= 1 and line[-1].isdigit():
-                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
+            parts = line.strip().split()
+            if len(parts) >= 2 and parts[-1].isdigit():
+                line_data = [0 if x == '?' else float(x) for x in parts[:-1]]
+                label = int(parts[-1])
+                # 将标签映射到0和1（假设原始标签是1, 2, 3，我们将其映射为0和1）
+                target_label = 0 if label in [2, 3] else 1
                 data.append(line_data)
-                labels.append(int(line[-1]))
+                labels.append(target_label)
 
     data = np.array(data)
     labels = np.array(labels)
-
-    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-
-    return data, target_variable
+    return data, labels
 
 
 def accuracy(X, y, weights):
@@ -97,15 +104,15 @@ def accuracy(X, y, weights):
 
 
 if __name__ == "__main__":
-    X_train, y_train = load_data("./data/horse-colic.data")
-    X_test, y_test = load_data("./data/horse-colic.test")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
 
     # 标准化数据
     scaler = StandardScaler()
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64, patience=200)
 
     final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")