更新 function.py

function.py

@@ -1,98 +1,73 @@
 import numpy as np
 
-"""
-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。
-"""
-
 id = "202210423218"
 name = "唐一鸣"
 
-def load_data(filepath):
-    """
-    从文件中加载数据。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-    data = []
-    labels = []
-
-    with open(filepath, 'r') as file:
-        for line in file:
-            # 用空格分割每一行
-            parts = line.strip().split()
-            # 将特征和标签分开，假设最后一列为标签
-            features = parts[:-1]
-            label = parts[-1]
-            
-            # 用-1替换缺失值（或你可以选择其他处理方式）
-            features = [float(x) if x != '?' else -1 for x in features]
-            data.append(features)
-            labels.append(int(label))
-
-    return np.array(data), np.array(labels)
-
 def sigmoid(z):
-    """Sigmoid 激活函数"""
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    """
-    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。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=128, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
 
-    for _ in range(iterations):
-        linear_model = np.dot(X, weights)
-        predictions = sigmoid(linear_model)
+    for j in range(iterations):
+        dataIndex = np.random.permutation(m)
+        for i in range(0, m, batch_size):
+            end = min(i + batch_size, m)
+            batch_X = X[dataIndex[i:end]]
+            batch_y = y[dataIndex[i:end]]
 
-        # 计算梯度
-        gradient = np.dot(X.T, (predictions - y)) / m
-        weights -= learning_rate * gradient
+            z = np.dot(batch_X, weights)
+            h = sigmoid(z)
+
+            error = batch_y - h
+            gradient = np.dot(batch_X.T, error) / len(batch_y)
+            gradient -= lambda_reg * weights / len(batch_y)
+            weights += learning_rate * gradient
 
     return weights
 
 def predict_logreg(inX, weights):
-    """
-    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。
-    """
     probability = sigmoid(np.dot(inX, weights))
     return 1 if probability >= 0.5 else 0
 
-if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+def load_data(filepath):
+    data = []
+    labels = []
+    with open(filepath, 'r') as file:
+        for line in file:
+            parts = line.strip().split()
+            features = parts[:-1]
+            label = parts[-1]
+            features = [float(x) if x != '?' else 0.0 for x in features]
+            data.append(features)
+            labels.append(1 if label in ['2', '3'] else 0)
 
-    # 加载测试集
+    # 转换为numpy数组
+    data = np.array(data)
+    labels = np.array(labels)
+    
+    # 简单均值归一化
+    data_mean = np.mean(data, axis=0)
+    data_std = np.std(data, axis=0)
+    data = (data - data_mean) / (data_std + 1e-10)  # 防止除零
+
+    return data, labels
+
+if __name__ == "__main__":
+    X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 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=2000, batch_size=64, lambda_reg=0.01)
 
-    # 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]}")
+    error_count = 0
+    for i in range(len(y_test)):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred != y_test[i]:
+            error_count += 1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
+
+    accuracy = (len(y_test) - error_count) / len(y_test)
+    print(f"准确率: {accuracy:.2f}")