更新 function.py

function.py

@@ -24,67 +24,78 @@ from sklearn.model_selection import KFold
 id = "202210423117"
 name = "程悦"
 
-
 def sigmoid(z):
+    """计算Sigmoid激活函数值"""
     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, cv=5):
+def train_logreg(X, y, learning_rate=0.05, iterations=1500, batch_size=64,
+                 regularization='L2', lambda_reg=0.05, cv=5):
+    """训练逻辑回归模型并使用交叉验证计算权重"""
     m, n = X.shape
     kf = KFold(n_splits=cv, shuffle=True)
     weights_list = []
     fold_scores = []
+
     for train_index, val_index in kf.split(X):
         X_train, X_val = X[train_index], X[val_index]
         y_train, y_val = y[train_index], y[val_index]
         weights = np.random.randn(n) * 0.01
-        for i in range(iterations):
+
+        for _ in range(iterations):
             indices = np.random.permutation(len(X_train))
-            X_shuffled = X_train[indices]
-            y_shuffled = y_train[indices]
+            X_shuffled, y_shuffled = X_train[indices], y_train[indices]
+
             for j in range(0, len(X_train), 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)) / X_batch.shape[0]
+                gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+
+                # 正则化处理
                 if regularization == 'L1':
                     gradient += lambda_reg * np.sign(weights) / len(y_batch)
                 elif regularization == 'L2':
-                    gradient += (lambda_reg / m) * weights
+                    gradient += (lambda_reg / len(y_train)) * weights
+
                 weights -= learning_rate * gradient
-            if i % 100 == 0:
-                learning_rate *= 0.95
-        # 在验证集上计算准确率
-        predictions = [predict_logreg(x, weights) for x in X_val]
+
+            if _ % 100 == 0:
+                learning_rate *= 0.95  # 动态调整学习率
+
+        # 验证集准确率
+        predictions = predict_logreg(X_val, weights)
         score = np.mean(predictions == y_val)
         fold_scores.append(score)
         weights_list.append(weights)
-    # 对权重进行加权平均融合，权重为各折的准确率
+
+    # 权重加权平均
     total_score = sum(fold_scores)
     if total_score == 0:
         return weights_list[-1]
+
     averaged_weights = np.zeros(n)
     for weight, score in zip(weights_list, fold_scores):
         averaged_weights += weight * score
-    averaged_weights /= total_score
-    return averaged_weights
+    return averaged_weights / total_score
 
 
-def predict_logreg(inX, weights):
-    z = np.dot(inX, weights)
+def predict_logreg(X, weights):
+    """对输入数据进行逻辑回归预测"""
+    z = np.dot(X, weights)
     h = sigmoid(z)
-    return 1 if h > 0.5 else 0
+    return (h > 0.5).astype(int)
 
 
 def load_data(filepath):
+    """加载数据并处理缺失值"""
     data, labels = [], []
+
     with open(filepath, 'r') as f:
-        for line in f.readlines():
+        for line in f:
             line = line.strip().split()
-            if len(line) >= 1 and line[-1].isdigit():
+            if line and line[-1].isdigit():
                 line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
                 data.append(line_data)
                 labels.append(int(line[-1]))
@@ -92,39 +103,47 @@ def load_data(filepath):
     data = np.array(data)
     labels = np.array(labels)
 
-    target_variable = labels
-    target_variable[(target_variable == 2) | (target_variable == 3)] = 0
-
+    # 处理目标变量
+    labels[(labels == 2) | (labels == 3)] = 0
     data = np.delete(data, [2] + list(range(23, 28)), axis=1)
 
+    # 数据标准化
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
 
-    return data, target_variable
+    return data, labels
 
 
 def accuracy(X, y, weights):
-    predictions = [predict_logreg(x, weights) for x in X]
+    """计算模型的准确率"""
+    predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
 
-def ensemble_predict(X, models):
-    predictions = [predict_logreg(x, model) for model in models for x in X]
-    ensemble_predictions = [1 if np.sum(pred == 1) > len(models) / 2 else 0 for pred in np.array(predictions).reshape(-1, len(models))]
-    return ensemble_predictions
+def ensemble_predict(X, models, weights):
+    """集成模型预测"""
+    predictions = np.array([predict_logreg(X, model) for model in models])  # (num_models, num_samples)
+    weighted_predictions = np.tensordot(predictions, weights, axes=(0, 0))  # 权重加权
+    return (weighted_predictions > 0.5).astype(int)  # 返回最终预测
+
 
 
 if __name__ == "__main__":
-    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")
 
     # 训练多个模型
     num_models = 5
-    models = [train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=32, regularization='None',
-                           lambda_reg=0.01) for _ in range(num_models)]
+    models = [train_logreg(X_train, y_train, learning_rate=0.02, iterations=6000,
+                           batch_size=48, regularization='None', lambda_reg=0.02)
+              for _ in range(num_models)]
+
+    # 模型准确率作为权重
+    model_accuracies = [accuracy(X_train, y_train, model) for model in models]
+    weights = np.array(model_accuracies) / sum(model_accuracies)
 
     # 集成预测
-    ensemble_predictions = ensemble_predict(X_test, models)
+    ensemble_predictions = ensemble_predict(X_test, models, weights)
 
     final_accuracy = np.mean(ensemble_predictions == y_test)
-    print(f"最终测试集的准确率: {final_accuracy:.4f}")
+    print(f"最终测试集的准确率: {final_accuracy:.4f}")