更新 function.py

function.py

@@ -1,85 +1,149 @@
-# function.py
 import numpy as np
+import os
 
-"""
-实验说明:
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。
+# 学号和姓名
+id = "202210423220"
+name = "方子涵"
 
-注意事项:
-- 在 function.py 中实现对率回归算法。
-- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
-- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
+def sigmoid(z):
+    """计算sigmoid函数"""
+    return 1.0 / (1 + np.exp(-z))
 
-测评环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
-"""
+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
 
+def train_logreg(X, y, learning_rate=0.01, iterations=20000, batch_size=64, lambda_reg=0.01, patience=5):
+    """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
+    best_weights = weights.copy()
+    best_accuracy = 0
+    wait = 0
 
-"""
-请在这里填写学号和姓名，不填写即成绩无效。
-姓名请直接**填写中文**
-例如: name = "张三"
-"""
-id = "202210423xxx"
-name = "test_name"
+    for i in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = 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]
+            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
+            weights -= learning_rate * gradient
 
-# 这里写自己的代码实现
-def train_logreg(X, y, other_params="你自己设置一些其它参数"):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+        # 早停法：在验证集上评估模型性能
+        accuracy = np.mean([1 if sigmoid(np.dot(X[i], weights)) >= 0.5 and y[i] == 1 or sigmoid(np.dot(X[i], weights)) < 0.5 and y[i] == 0 else 0 for i in range(m)])
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_weights = weights.copy()
+            wait = 0
+        else:
+            wait += 1
+            if wait >= patience:
+                print(f"Early stopping at iteration {i+1}")
+                break
 
+    return best_weights
 
 def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
+    """对率回归预测函数。"""
+    z = np.dot(inX, weights)
+    h = sigmoid(z)
+    return 1 if h >= 0.5 else 0
 
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
+def standardize_data(X):
+    """标准化数据"""
+    mean = np.mean(X, axis=0)
+    std = np.std(X, axis=0)
+    return (X - mean) / std, mean, std
 
-    Returns:
-    - int: 预测的分类标签。
-    """
-
-
-# 这里也写自己的代码实现
 def load_data(filepath):
-    """
-    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**。
+    """从文件中加载数据。"""
+    if not os.path.exists(filepath):
+        raise FileNotFoundError(f"文件 {filepath} 不存在！")
+    
+    data, labels = [], []
+    print(f"Loading data: {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]))
 
-    Args:
-    - directory (str): 数据文件路径。
+    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)))
 
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
+    data = np.delete(data, indices_to_remove, axis=1)
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
+    print(f"Data loaded successfully, data shape: {data.shape}, label shape: {target_variable.shape}")
+    return data, target_variable
+
+def k_fold_cross_validation(X, y, k=5, learning_rate=0.01, iterations=20000, batch_size=64, lambda_reg=0.01):
+    """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} - Validation accuracy: {val_accuracy:.4f}")
+
+    return np.mean(accuracies)
 
 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")
+    try:
+        X_train, y_train = load_data("./data/horse-colic.data")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
+
+    # 数据标准化处理
+    X_train, mean, std = standardize_data(X_train)
+
+    # K折交叉验证
+    avg_accuracy = k_fold_cross_validation(X_train, y_train, k=5, learning_rate=0.01, iterations=20000)
+    print(f"Average accuracy of K-fold cross-validation: {avg_accuracy:.4f}")
 
     # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    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标准化
+    X_test = (X_test - mean) / std
 
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=20000)
 
     # 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]}")
+    print(f"Predicted result: {y_pred}, Actual result: {y_test[11]}")