更新 function.py

function.py

@@ -1,54 +1,90 @@
 import numpy as np
-import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split, KFold
 
+"""
+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。
+
+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。
+
+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 = "202210423130"
 name = "董秋"
 
+
 def sigmoid(z):
     """Sigmoid 激活函数。"""
     return 1 / (1 + np.exp(-z))
 
-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。"""
+
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
+    """
+    对率回归训练函数。
+
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - learning_rate (float): 学习率。
+    - iterations (int): 迭代次数。
+    - lambda_reg (float): L2正则化参数。
+
+    Returns:
+    - numpy array: 训练得到的权重。
+    """
     m, n = X.shape
-    weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
+    weights = np.random.randn(n) * 0.01  # 随机初始化权重
 
-    for i in range(iterations):
-        # 每次迭代打乱数据
-        indices = np.random.permutation(m)
-        X = X[indices]
-        y = y[indices]
+    for _ in range(iterations):
+        z = np.dot(X, weights)
+        predictions = sigmoid(z)
+        gradient = np.dot(X.T, (predictions - y)) / m
 
-        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]
+        # L2正则化
+        gradient += (lambda_reg / m) * weights
 
-            z = np.dot(X_batch, weights)
-            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
-
-        # 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}")
+        # 更新权重
+        weights -= learning_rate * gradient
 
     return weights
 
+
 def predict_logreg(inX, weights):
-    """逻辑回归预测函数。"""
+    """
+    对率回归预测函数。
+
+    Args:
+    - inX (numpy array): 输入待分类的样本。
+    - weights (numpy array): 训练得到的权重。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
     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。"""
+    """
+    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**。
+
+    Args:
+    - directory (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
     data = []
     labels = []
 
@@ -57,7 +93,7 @@ def load_data(filepath):
             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
@@ -65,62 +101,25 @@ def load_data(filepath):
                     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)
+    return np.array(data), np.array(labels)
 
-    return data, labels
-
-def preprocess_data(X):
-    """特征标准化。"""
-    scaler = StandardScaler()
-    return scaler.fit_transform(X)
 
 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")
 
-    # 归一化训练集
-    X_train = preprocess_data(X_train)
-
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 归一化测试集
-    X_test = preprocess_data(X_test)
-
-    # 使用 train_test_split 打乱并随机抽取数据
-    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
-
-    # 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)}")
-
-    # 训练逻辑回归模型
+    # 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