更新 function.py

function.py

@@ -25,49 +25,45 @@ from sklearn.model_selection import train_test_split, KFold
 id = "202210423117"
 name = "程悦"
 
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split, KFold
+
+# 学号和姓名
+id = "202210423117"
+name = "程悦"
+
 def sigmoid(z):
-    """Sigmoid 激活函数。"""
+    """计算Sigmoid激活函数值"""
     return 1 / (1 + np.exp(-z))
 
 def train_logreg(X, y, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=32):
-    """逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。"""
+    """训练逻辑回归模型"""
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
+    weights = np.random.randn(n) * 0.01
 
-    for i in range(iterations):
+    for _ in range(iterations):
-        # 每次迭代打乱数据
         indices = np.random.permutation(m)
-        X_shuffled = X[indices]
+        X_shuffled, y_shuffled = X[indices], y[indices]
-        y_shuffled = y[indices]
-
-        for j in range(0, m, batch_size):  # 按照 batch size 迭代
-            X_batch = X_shuffled[j:j + batch_size]
-            y_batch = y_shuffled[j:j + batch_size]
 
+        for j in range(0, m, batch_size):
+            X_batch, y_batch = X_shuffled[j:j + batch_size], y_shuffled[j:j + batch_size]
             z = np.dot(X_batch, weights)
             predictions = sigmoid(z)
-            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]
+            gradient = np.dot(X_batch.T, (predictions - y_batch)) / batch_size
-
+            gradient += (lambda_reg / m) * weights  # L2正则化
-            # L2正则化
-            gradient += (lambda_reg / m) * weights
-
-            # 更新权重
             weights -= learning_rate * gradient
 
-        # 动态调整学习率，逐渐减小
+        learning_rate *= 0.95 if _ % 100 == 0 else 1  # 动态调整学习率
-        if i % 100 == 0:
-            learning_rate *= 0.95
 
     return weights
 
 def predict_logreg(X, weights):
-    """逻辑回归预测函数。"""
+    """使用逻辑回归模型进行预测"""
-    z = np.dot(X, weights)
+    return (sigmoid(np.dot(X, weights)) >= 0.5).astype(int)
-    prediction_prob = sigmoid(z)
-    return np.where(prediction_prob >= 0.5, 1, 0)
 
 def load_data(filepath):
-    """加载数据并处理缺失值。"""
+    """加载数据并处理缺失值"""
     data, labels = [], []
 
     with open(filepath, 'r') as f:
@@ -75,69 +71,38 @@ def load_data(filepath):
             values = line.strip().replace('?', '0').split()
             try:
                 values = [float(v) for v in values]
-
+                if values[22] in [1, 2, 3]:
-                # 合并特征23的取值
+                    labels.append(0 if values[22] in [2, 3] else 1)
-                if values[22] in [2, 3]:  # 特征23（索引22）
+                    data.append([0 if v == 0 else v for v in values[:2] + values[3:23]])
-                    labels.append(0)  # 死亡
-                elif values[22] == 1:
-                    labels.append(1)  # 生存
-                else:
-                    continue  # 无效标签，丢弃
-
-                # 用0填充缺失值并提取特征
-                data.append([0 if v == 0 else v for v in values[:2] + values[3:23]])  # 保留特征1, 2 和特征4-23
             except ValueError:
                 continue
 
     data = np.array(data)
     labels = np.array(labels)
-
+    return StandardScaler().fit_transform(data), labels
-    # 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。"""
+    """计算模型准确率"""
-    predictions = predict_logreg(X, weights)
+    return np.mean(predict_logreg(X, weights) == y)
-    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 加载训练集
+    X_train, y_train = load_data("./data/horse-colic.data")
-    X_train, y_train = load_data("./horse-colic.data")
-
-    # 使用 train_test_split 打乱并随机抽取训练和验证数据
     X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
 
-    # K折交叉验证
+    kf = KFold(n_splits=5, shuffle=True, random_state=42)
-    k = 5
+    accuracies = [accuracy(X_val_kf, y_val_kf, train_logreg(X_train_kf, y_train_kf, batch_size=32))
-    kf = KFold(n_splits=k, shuffle=True, random_state=42)
+                  for train_index, val_index in kf.split(X_train)
-    accuracies = []
+                  for X_train_kf, X_val_kf in [(X_train[train_index], X_train[val_index])]
+                  for y_train_kf, y_val_kf in [(y_train[train_index], y_train[val_index])]]
 
-    for train_index, val_index in kf.split(X_train):
-        X_train_kf, X_val_kf = X_train[train_index], X_train[val_index]
-        y_train_kf, y_val_kf = y_train[train_index], y_train[val_index]
-
-        # 训练逻辑回归模型，设置 batch size
-        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=32)
-
-        # 验证模型
-        val_accuracy = accuracy(X_val_kf, y_val_kf, weights)
-        accuracies.append(val_accuracy)
-
-    # 输出交叉验证的准确率和平均准确率
     print(f"K折交叉验证得分: {accuracies}")
     print(f"平均准确率: {np.mean(accuracies):.4f}")
 
-    # 加载测试集
+    X_test, y_test = load_data("./data/horse-colic.test")
-    X_test, y_test = load_data("./horse-colic.test")
+    final_weights = train_logreg(X_train, y_train, batch_size=32)
-
-    # 在测试集上评估最终模型
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.01, batch_size=32)
     test_accuracy = accuracy(X_test, y_test, final_weights)
     print(f"测试集的准确率: {test_accuracy:.4f}")
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], final_weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")