更新 function.py

function.py

@@ -31,19 +31,12 @@ def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
 
-def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regularization='L2', lambda_reg=0.05):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+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)
@@ -57,99 +50,62 @@ def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64, regul
             h = sigmoid(z)
             gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
 
-            # 添加正则化项
-            if regularization == 'L1':
-                gradient += lambda_reg * np.sign(weights) / len(y_batch)
-            elif regularization == 'L2':
-                gradient += lambda_reg * weights / len(y_batch)
-
             weights -= learning_rate * gradient
 
-        # 学习率衰减
+        # 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
+
         if i % 100 == 0:
             learning_rate *= 0.95
 
-    return weights
+    return best_weights
 
 
-def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    z = np.dot(inX, weights)
+def predict_logreg(X, weights):
+    z = np.dot(X, weights)
     h = sigmoid(z)
-    return 1 if h > 0.5 else 0
-
+    return np.where(h > 0.5, 1, 0)
 
 def load_data(filepath):
-    """
-    从文件中加载数据，填充缺失值，并进行特征处理。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    data, labels = [], []
-
+    data = []
+    labels = []
     with open(filepath, 'r') as f:
         for line in f:
             line = line.strip().split()
-            if line and line[-1].isdigit():
-                line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
+            if len(line) >= 1 and line[-1].isdigit():
+                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
                 data.append(line_data)
                 labels.append(int(line[-1]))
 
     data = np.array(data)
     labels = np.array(labels)
 
-    # 映射标签
-    labels[np.isin(labels, [2, 3])] = 0
+    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
 
-    # 删除不需要的列
-    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
+    return data, target_variable
 
-    # 数据标准化
-    scaler = StandardScaler()
-    data = scaler.fit_transform(data)
-
-    return data, labels
 
 def accuracy(X, y, weights):
-    """计算模型准确率"""
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
+
 if __name__ == "__main__":
-    # 加载数据
-    X_train, y_train = load_data("./horse-colic.data")
-    X_test, y_test = load_data("./horse-colic.test")
+    X_train, y_train = load_data("./data/horse-colic.data")
+    X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 使用随机森林进行初步预测
-    rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
-    rf_model.fit(X_train, y_train)
+    # 标准化数据
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
 
-    rf_predictions_train = rf_model.predict(X_train)
-    rf_predictions_test = rf_model.predict(X_test)
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
 
-    # 将随机森林预测的结果作为新的特征
-    X_train_combined = np.column_stack((X_train, rf_predictions_train))
-    X_test_combined = np.column_stack((X_test, rf_predictions_test))
-
-    # 使用逻辑回归进行训练
-    final_weights = train_logreg(X_train_combined, y_train, learning_rate=0.01,
-                                 iterations=5000, batch_size=32,
-                                 regularization='L1', lambda_reg=0.01)
-
-    # 计算准确率
-    final_accuracy = accuracy(X_test_combined, y_test, final_weights)
+    final_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"最终测试集的准确率: {final_accuracy:.4f}")