更新 function.py

function.py

@@ -26,85 +26,121 @@ name = "邓龙树"
 
 # user_cod
 import numpy as np
+import pandas as pd
 from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split, KFold
 
+id = "202210423130"
+name = "董秋"
 
 def sigmoid(z):
-    return 1.0 / (1 + np.exp(-z))
+    """Sigmoid 激活函数。"""
+    return 1 / (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=0.1, 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。"""
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01
-    best_weights = weights.copy()
-    best_accuracy = 0
-    wait = 0
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
 
     for i in range(iterations):
+        # 每次迭代打乱数据
         indices = np.random.permutation(m)
-        X_shuffled = X[indices]
-        y_shuffled = y[indices]
+        X = X[indices]
+        y = y[indices]
+
+        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]
 
-        for j in range(0, m, 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)) / len(y_batch)
+            predictions = sigmoid(z)
+            gradient = np.dot(X_batch.T, (predictions - y_batch)) / X_batch.shape[0]
 
+            # L2正则化
+            gradient += (lambda_reg / m) * weights
+
+            # 更新权重
             weights -= learning_rate * gradient
 
-        # 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
+        # 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 best_weights
+    return weights
 
-
-def predict_logreg(X, weights):
-    z = np.dot(X, weights)
-    h = sigmoid(z)
-    return np.where(h > 0.5, 1, 0)
+def predict_logreg(inX, weights):
+    """逻辑回归预测函数。"""
+    z = np.dot(inX, weights)
+    prediction_prob = sigmoid(z)
+    return 1 if prediction_prob >= 0.5 else 0
 
 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:
-            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]]
-                data.append(line_data)
-                labels.append(int(line[-1]))
+            values = line.strip().replace('?', '0').split()
+            try:
+                values = [float(v) for v in values]
+                
+                # 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
+                
+                # 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
 
     data = np.array(data)
     labels = np.array(labels)
 
-    target_variable = np.where((labels == 2) | (labels == 3), 0, labels)
-
-    return data, target_variable
-
-
-def accuracy(X, y, weights):
-    predictions = predict_logreg(X, weights)
-    return np.mean(predictions == y)
+    return data, labels
 
+def preprocess_data(X):
+    """特征标准化。"""
+    scaler = StandardScaler()
+    return scaler.fit_transform(X)
 
 if __name__ == "__main__":
-    X_train, y_train = load_data("./horse-colic.data")
-    X_test, y_test = load_data("./horse-colic.test")
+    # 加载数据集
+    X, y = load_data("./data/horse-colic.data")
 
-    # 标准化数据
-    scaler = StandardScaler()
-    X_train = scaler.fit_transform(X_train)
-    X_test = scaler.transform(X_test)
+    # 归一化数据
+    X = preprocess_data(X)
 
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=1500, batch_size=64)
+    # 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)
 
-    final_accuracy = accuracy(X_test, y_test, final_weights)
-    print(f"最终测试集的准确率: {final_accuracy:.4f}")
+    # 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]}")