更新 function.py

function.py

@@ -1,5 +1,5 @@
+# function.py
 import numpy as np
-from sklearn.preprocessing import StandardScaler
 
 """
 实验说明:
@@ -18,82 +18,105 @@ from sklearn.preprocessing import StandardScaler
 """
 
 
+"""
+请在这里填写学号和姓名，不填写即成绩无效。
+"""
 id = "202210423130"
 name = "董秋"
+# 这里写自己的代码实现
+import numpy as np
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
 
 
-# 逻辑回归训练函数
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
+def sigmoid(z):
+    return 1.0 / (1 + np.exp(-z))
+
+def compute_gradient(X_batch, y_batch, weights, lambda_reg):
+    z = np.dot(X_batch, weights)
+    h = sigmoid(z)
+    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
+    return gradient
+
+def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重
+    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
+    best_weights = weights.copy()
+    best_accuracy = 0
 
-    for i in range(iterations):
-        z = np.dot(X, weights)
-        predictions = 1 / (1 + np.exp(-z))  # Sigmoid 激活函数
-        gradient = np.dot(X.T, (predictions - y)) / m + (lambda_reg / m) * weights  # L2 正则化
-        weights -= learning_rate * gradient  # 更新权重
+    for _ in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
 
-    return weights
+        for j in range(0, m, batch_size):
+            X_batch = X_shuffled[j:j + batch_size]
+            y_batch = y_shuffled[j:j + batch_size]
+            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
+            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()
 
-# 逻辑回归预测函数
-def predict_logreg(inX, weights):
-    z = np.dot(inX, weights)
-    prediction_prob = 1 / (1 + np.exp(-z))  # Sigmoid 激活函数
-    return 1 if prediction_prob >= 0.5 else 0
+        # 动态调整学习率
+        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
+            learning_rate *= 0.9
 
+    return best_weights
+
+def predict_logreg(X, weights):
+    z = np.dot(X, weights)
+    h = sigmoid(z)
+    return np.where(h >= 0.5, 1, 0)
 
-# 从文件中加载数据
 def load_data(filepath):
-    data = []
-    labels = []
-
+    data, labels = [], []
     with open(filepath, 'r') as f:
         for line in f:
-            values = line.strip().replace('?', '0').split()
-            try:
-                values = [float(v) for v in values]
-
-                # 跳过第3行（索引为2）和24-28行（索引为23-27）
-                if len(data) in [2, 23, 24, 25, 26, 27]:
-                    continue
-
-                # 用0填充缺失值
-                values = [0 if v == 0 else v for v in values]  # 用0填充
-                
-                # 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
-
-                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
-            except ValueError:
-                continue
+            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]))
 
     data = np.array(data)
     labels = np.array(labels)
+    # 将标签二分类化，2和3为0，其余为1
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
-    # 数据归一化
-    scaler = StandardScaler()
-    data = scaler.fit_transform(data)
-
-    return data, labels
+    return data, target_variable
 
+def accuracy(X, y, weights):
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    # 加载数据
+    X, y = load_data("./data/horse-colic.data")
+    
+    # 拆分训练集和验证集
+    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # 数据归一化
+    scaler = MinMaxScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_val = scaler.transform(X_val)
+
+    # 训练模型
+    final_weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1)
+
+    # 验证模型
+    val_accuracy = accuracy(X_val, y_val, final_weights)
+    print(f"验证集的准确率: {val_accuracy:.4f}")
 
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
+    X_test = scaler.transform(X_test)
 
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-
-    # 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]}")
+    # 测试模型
+    final_test_accuracy = accuracy(X_test, y_test, final_weights)
+    print(f"最终测试集的准确率: {final_test_accuracy:.4f}")