更新 function.py

function.py

@@ -1,170 +1,134 @@
-# function.py
 import numpy as np
 import os
+from sklearn.preprocessing import StandardScaler  # 导入标准化库
 
-"""
+# 学号和姓名
-实验说明:
-- 自行编写实现数据加载与 kNN 的手写数字分类算法。
-- 函数输入: 待分类的样本 input_vector, 训练数据集 dataSet, 训练集对应的标签 labels。
-- 函数返回: 预测的分类标签。
-
-注意事项:
-- 在 function.py 中实现 kNN 分类算法。
-- 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 classify 和 load_data 函数，请勿修改函数名。
-- 训练集和测试集需手动下载解压，并放入当前目录下。
-
-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
-"""
-
-
-"""
-请在这里填写学号和姓名，不填写即成绩无效。
-"""
 id = "202210423119"
 name = "肖锐"
 
+def sigmoid(z):
+    """计算sigmoid函数"""
+    return 1.0 / (1 + np.exp(-z))
 
-"""
+def compute_gradient(X_batch, y_batch, weights, lambda_reg):
-参数说明:
+    """计算梯度，包含L2正则化"""
-- input_vector (numpy array): 输入待分类的样本。
+    z = np.dot(X_batch, weights)
-- dataSet (numpy array): 训练数据集。
+    h = sigmoid(z)
-- labels (list or numpy array): 训练集对应的标签。
+    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
-- k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
+    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
-返回值:
+    return gradient
-- int: 预测的分类标签。
-"""
 
+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")
     
-# 这里写自己的代码实现
+    for i in range(iterations):
-def classify(input_vector, dataSet, labels, k=4):
+        indices = np.random.permutation(m)
-    """
+        X_shuffled = X[indices]
-    KNN 分类算法。
+        y_shuffled = y[indices]
 
-    Args:
+        for j in range(0, m, batch_size):
-    - input_vector (numpy array): 输入待分类的样本。
+            X_batch = X_shuffled[j:j + batch_size]
-    - dataSet (numpy array): 训练数据集。
+            y_batch = y_shuffled[j:j + batch_size]
-    - labels (list or numpy array): 训练集对应的标签。
+            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
-    - k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
+            weights -= learning_rate * gradient
             
-    Returns:
+        if i % 1000 == 0:  # 每1000次迭代打印一次信息
-    - int: 预测的分类标签。
+            print(f"迭代 {i}: 当前权重形状: {weights.shape}")
-    """
-    """
-    使用欧式距离的 kNN 分类算法。
-    """
-     # 计算欧式距离
-    distances = np.linalg.norm(dataSet - input_vector, axis=1)
 
-    # 获取距离最近的 k 个样本的索引
+    return weights
-    k_indices = np.argsort(distances)[:k]
 
-    # 获取最近邻样本的标签
+def predict_logreg(inX, weights):
-    k_nearest_labels = [labels[i] for i in k_indices]
+    """对率回归预测函数。"""
+    z = np.dot(inX, weights)
+    h = sigmoid(z)
+    return 1 if h >= 0.5 else 0
 
-    # 找出出现次数最多的标签
+def load_data(filepath):
-    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)
+    """从文件中加载数据。"""
+    if not os.path.exists(filepath):
+        raise FileNotFoundError(f"文件 {filepath} 不存在！")
     
-    return most_common
+    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)
     
-# 这里也写自己的代码实现
+    num_features = data.shape[1]
+        indices_to_remove = [2]  # 去掉特征3（索引2）
     
-def load_dataset(directory):
+    if num_features > 23:
-    """
+        indices_to_remove.extend(range(23, min(28, num_features)))
-    从文件夹中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
 
-    Args:
+    data = np.delete(data, indices_to_remove, axis=1)
-    - directory (str): 数据文件夹路径。
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
-    Returns:
+    print(f"数据加载成功，数据形状: {data.shape}, 标签形状: {target_variable.shape}")
-    - np.array: 特征数据。
+    return data, target_variable
-    - np.array: 标签数据。
-    """
-    features = []
-    labels = []
 
-    # 遍历文件夹中的所有文件
+def k_fold_cross_validation(X, y, k=5, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
-    for filename in os.listdir(directory):
+    """K折交叉验证。"""
-        if filename.endswith(".txt"):  # 假设文件是 .txt 格式
+    m = X.shape[0]
-            filepath = os.path.join(directory, filename)
+    fold_size = m // k
+    accuracies = []
 
-            # 假设文件名格式为 "数字_编号.txt"
+    for i in range(k):
-            label = int(filename.split('_')[0])
+        val_start = i * fold_size
+        val_end = (i + 1) * fold_size if i != k - 1 else m
         
-            # 加载文件中的二进制数据并转换为 1D 向量
+        X_val = X[val_start:val_end]
-            image_vector = img_to_vector(filepath)
+        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:]))
 
-            features.append(image_vector)
+        weights = train_logreg(X_train, y_train, learning_rate, iterations, batch_size, lambda_reg)
-            labels.append(label)
         
-    return np.array(features), np.array(labels)
+        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}")
 
-# 这里还写自己的代码实现
+    return np.mean(accuracies)
-def img_to_vector(filename):
-    """
-    将二值图像转换为向量。
-    该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
-
-    Args:
-    - filename (str): 图像文件路径。
-
-    Returns:
-    - np.array: 二值图像向量。
-    """
-    with open(filename) as file:
-        lines = file.readlines()
-        image_vector = np.array([int(char) for line in lines for char in line.strip()])
-    
-    return image_vector
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
+    # 加载训练集
-    train_data, train_labels = load_dataset("trainingDigits")
+    try:
+        X_train, y_train = load_data("./data/horse-colic.data")
+    except FileNotFoundError as e:
+        print(e)
+        exit()
 
-    test_data = (
+    # 数据归一化处理
-        "00000000000000110000000000000000"
+    scaler = StandardScaler()
-        "00000000000011111000000000000000"
+    X_train = scaler.fit_transform(X_train)  # 使用训练集进行标准化
-        "00000000000011111100000000000000"
-        "00000000001111111110000000000000"
-        "00000000001111111110000000000000"
-        "00000000001111111100000000000000"
-        "00000000011111111000000000000000"
-        "00000000111111111000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111111111000000000000"
-        "00000001111111111111111000000000"
-        "00000001111111111111111100000000"
-        "00000011111111111111111110000000"
-        "00000011111111111111111110000000"
-        "00000001111111111111111110000000"
-        "00000001111111111111111110000000"
-        "00000000111111111100111111100000"
-        "00000000111111111000111111100000"
-        "00000000011111111001111111100000"
-        "00000000011111111111111111000000"
-        "00000000001111111111111111000000"
-        "00000000000111111111111111000000"
-        "00000000000011111111111100000000"
-        "00000000000001111111110000000000"
-        "00000000000000000111100000000000"
-    )
-    predicted_label = classify(
-        np.array([int(char) for char in test_data]).reshape(1, 1024),
-        train_data,
-        train_labels,
-    )
 
-    print(f"预测的标签: {predicted_label}")
+    # 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]}")