更新 function.py

function.py

@@ -30,20 +30,19 @@ name = "万子玉"
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=2000, lambda_reg=0.01, batch_size=32):
-    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
+def train_logreg(X, y, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=32):
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
 
     for i in range(iterations):
-        indices = np.arange(m)
-        np.random.shuffle(indices)
-        X_shuffled = X[indices]
-        y_shuffled = y[indices]
+        # 每次迭代打乱数据
+        indices = np.random.permutation(m)
+        X = X[indices]
+        y = y[indices]
 
-        for j in range(0, m, batch_size):
-            X_batch = X_shuffled[j:j + batch_size]
-            y_batch = y_shuffled[j:j + batch_size]
+        for j in range(0, m, batch_size):  # 按照 batch size 迭代
+            X_batch = X[j:j + batch_size]
+            y_batch = y[j:j + batch_size]
 
             z = np.dot(X_batch, weights)
             predictions = sigmoid(z)
@@ -55,6 +54,10 @@ def train_logreg(X, y, learning_rate=0.01, iterations=2000, lambda_reg=0.01, bat
             # 更新权重
             weights -= learning_rate * gradient
 
+        # 动态调整学习率，逐渐减小
+        if i % 100 == 0:  # 每100次迭代输出一次学习率
+            print(f"Iteration {i}, Learning Rate: {learning_rate}")
+
     return weights
 
     """
@@ -70,12 +73,10 @@ def train_logreg(X, y, learning_rate=0.01, iterations=2000, lambda_reg=0.01, bat
     """
 
 
-def predict_logreg(inX, weights):
-    inX = np.insert(inX, 0, 1)  # 添加偏置项
-    z = np.dot(inX, weights)
-    prediction_prob = sigmoid(z)
-    return 1 if prediction_prob >= 0.5 else 0
-
+def preprocess_data(X):
+    """特征标准化。"""
+    scaler = StandardScaler()
+    return scaler.fit_transform(X)
 
     """
     对率回归预测函数。
@@ -87,61 +88,37 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
-def evaluate_model(X_val, y_val, weights):
-    predictions = np.array([predict_logreg(x, weights) for x in X_val])
-    accuracy = np.mean(predictions == y_val)
-    return accuracy
-
-def split_train_val(X, y, val_size=0.2):
-    shuffled_indices = list(range(X.shape[0]))
-    random.shuffle(shuffled_indices)
-    X_shuffled = X[shuffled_indices]
-    y_shuffled = y[shuffled_indices]
-    
-    val_count = int(X.shape[0] * val_size)
-    
-    X_val = X_shuffled[:val_count]
-    y_val = y_shuffled[:val_count]
-    X_train = X_shuffled[val_count:]
-    y_train = y_shuffled[val_count:]
-    
-    return X_train, X_val, y_train, y_val
-
-
 
 # 这里也写自己的代码实现
 def load_data(filepath):
-    with open(filepath, 'r') as file:
-        lines = file.readlines()
+    """加载数据并处理缺失值。"""
+    data = []
+    labels = []
 
-    data = [line.strip().split() for line in lines if line.strip().split()[-1].isdigit()]
-    data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
+    with open(filepath, 'r') as f:
+        for line in f:
+            values = line.strip().replace('?', '0').split()
+            try:
+                values = [float(v) for v in values]
                 
-    # 移除类别标签缺失的样本
-    data = [row for row in data if not np.isnan(row[-1])]
+                # 合并特征23的取值
+	                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
+                    labels.append(0)  # 死亡
+                elif values[22] == 1:
+                    labels.append(1)  # 生存
+                else:
+                    continue  # 无效标签，丢弃
                 
-    # 使用“0”填充缺失值
-    for row in data:
-        for i in range(len(row)):
-            if np.isnan(row[i]):
-                row[i] = 0.0
+                # 用0填充缺失值
+                values = [0 if v == 0 else v for v in values]  # 直接用0填充
+                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
+            except ValueError:
+                continue
 
-    # 合并特征23的值2和3为0
-    for row in data:
-        if row[22] == 2 or row[22] == 3:  # 假设特征23是第23个元素
-            row[22] = 0
+    data = np.array(data)
+    labels = np.array(labels)
 
-    # 移除不需要的特征
-    data = [row[:2] + row[3:23] + row[28:] for row in data]
-
-    # 分离特征和标签
-    X = [row[:-1] for row in data]
-    y = [row[-1] for row in data]
-
-    scaler = StandardScaler()
-    X = scaler.fit_transform(X)
-
-    return np.array(X), np.array(y)
+    return data, labels
     """
     从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
 
@@ -154,10 +131,37 @@ def load_data(filepath):
     """
 
 if __name__ == "__main__":
-    X_train, y_train = load_data("./data/horse-colic.data")
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 加载数据集
+    X, y = load_data("./data/horse-colic.data")
 
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=2000)
+    # 归一化数据
+    X = preprocess_data(X)
 
+    # 使用 train_test_split 打乱并随机抽取数据
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # K折交叉验证
+    k = 5
+    kf = KFold(n_splits=k, shuffle=True, random_state=42)
+    accuracies = []
+
+    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
+        batch_size = 32
+        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=batch_size)
+
+        # 验证模型
+        val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
+        accuracy = np.mean(val_predictions == y_val_kf)
+        accuracies.append(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)}")
+
+    # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")