更新 function.py

function.py

@@ -1,57 +1,134 @@
-id = "202210423xxx"
-name = "test_name"
+import numpy as np
+import os
+from sklearn.preprocessing import StandardScaler  # 导入标准化库
 
-# -*- coding:UTF-8 -*-
-from sklearn.linear_model import LogisticRegression
+# 学号和姓名
+id = "202210423230"
+name = "尹家立"
 
-def colicSklearn():
-    # 加载训练集和测试集
-    frTrain = open('horseColicTraining.txt')
-    frTest = open('horseColicTest.txt')
-    trainingSet = []; trainingLabels = []
-    testSet = []; testLabels = []
+def sigmoid(z):
+    """计算sigmoid函数"""
+    return 1.0 / (1 + np.exp(-z))
 
-    # 读取训练集数据
-    for line in frTrain.readlines():
-        currLine = line.strip().split('\t')
-        lineArr = []
-        for i in range(len(currLine)-1):
-            lineArr.append(float(currLine[i]))
-        trainingSet.append(lineArr)
-        trainingLabels.append(float(currLine[-1]))
+def compute_gradient(X_batch, y_batch, weights, lambda_reg):
+    """计算梯度，包含L2正则化"""
+    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
 
-    # 读取测试集数据
-    for line in frTest.readlines():
-        currLine = line.strip().split('\t')
-        lineArr = []
-        for i in range(len(currLine)-1):
-            lineArr.append(float(currLine[i]))
-        testSet.append(lineArr)
-        testLabels.append(float(currLine[-1]))
+def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
+    """对率回归训练函数。"""
+    m, n = X.shape
+    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
+    print("开始训练对率回归模型")
     
-    # 训练Logistic回归分类器
-    classifier = LogisticRegression(solver='liblinear', max_iter=1000).fit(trainingSet, trainingLabels)
-    return classifier
+    for i in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
 
-def predict_logreg(sample, classifier):
-    """
-    函数说明:使用训练好的Logistic回归分类器预测单个样本
+        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
             
-    Parameters:
-        sample: 一个列表，包含单个样本的特征值
-        classifier: 训练好的Logistic回归分类器
+        if i % 1000 == 0:  # 每1000次迭代打印一次信息
+            print(f"迭代 {i}: 当前权重形状: {weights.shape}")
 
-    Returns:
-        预测结果
-    """
-    prediction = classifier.predict([sample])
-    return prediction[0]
+    return weights
 
-if __name__ == '__main__':
-    # 训练模型
-    classifier = colicSklearn()
+def predict_logreg(inX, weights):
+    """对率回归预测函数。"""
+    z = np.dot(inX, weights)
+    h = sigmoid(z)
+    return 1 if h >= 0.5 else 0
 
+def load_data(filepath):
+    """从文件中加载数据。"""
+    if not os.path.exists(filepath):
+        raise FileNotFoundError(f"文件 {filepath} 不存在！")
     
-    single_sample = testSet[11]  
-    y_pred = predict_logreg(single_sample, classifier)
-    print(f"预测结果: {y_pred}, 实际结果: {testLabels[11]}")
+    data, labels = [], []
+    print(f"加载数据中: {filepath}")
+    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]))
+
+    data = np.array(data)
+    labels = np.array(labels)
+    
+    num_features = data.shape[1]
+    indices_to_remove = [2]  # 去掉特征3（索引2）
+    
+    if num_features > 23:
+        indices_to_remove.extend(range(23, min(28, num_features)))
+
+    data = np.delete(data, indices_to_remove, axis=1)
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
+
+    print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}")
+    return data, target_variable
+
+def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
+    """K折交叉验证。"""
+    m = X.shape[0]
+    fold_size = m // k
+    accuracies = []
+
+    for i in range(k):
+        val_start = i * fold_size
+        val_end = (i + 1) * fold_size if i != k - 1 else m
+        
+        X_val = X[val_start:val_end]
+        y_val = y[val_start:val_end]
+        X_train = np.concatenate((X[:val_start], X[val_end:]))
+        y_train = np.concatenate((y[:val_start], y[val_end:]))
+
+        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)
+        
+        val_accuracy = np.mean([predict_logreg(X_val[j], weights) == y_val[j] for j in range(len(y_val))])
+        accuracies.append(val_accuracy)
+
+        print(f"Fold {i + 1}/{k} - 验证准确率: {val_accuracy:.4f}")
+
+    return np.mean(accuracies)
+
+if __name__ == "__main__":
+    # 加载训练集
+    try:
+        X_train, y_train = load_data("./data/horse-colic.data")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
+
+    # 数据归一化处理
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)  # 使用训练集进行标准化
+
+    # k折交叉验证
+    avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=1000)
+    print(f"K折交叉验证的平均准确率: {avg_accuracy:.4f}")
+
+    # 加载测试集
+    try:
+        X_test, y_test = load_data("./data/horse-colic.test")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
+
+    # 测试集也需要进行相同的归一化
+    X_test = scaler.transform(X_test)  # 使用相同的Scaler进行测试集的标准化
+
+    # 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]}")