更新 function.py

function.py

@@ -26,54 +26,107 @@ import numpy as np
 id = "202210423113"
 name = "杨文强"
 
-import os
-from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split
+def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
+    """
+    对率回归训练函数，加入L2正则化。
 
-def sigmoid(z):
-    """计算sigmoid函数"""
-    return 1.0 / (1 + np.exp(-z))
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - numIter (int): 迭代次数。默认为1000。
+    - learning_rate (float): 学习率。默认为0.06。
+    - batch_size (int): 批量大小。默认为128。
+    - lambda_reg (float): L2正则化参数。默认为0.01。
 
-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
+    Returns:
+    - numpy array: 训练得到的权重。
+    """
+    m, n = X.shape  # m: 样本数, n: 特征数
+    weights = np.zeros(n)  # 参数初始化
 
-def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
-    """逻辑回归训练函数。"""
-    m, n = X.shape
-    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
-    print("开始训练逻辑回归模型")
-    
-    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
+    for j in range(numIter):
+        # 随机打乱样本顺序
+        dataIndex = np.random.permutation(m)
+        for i in range(0, m, batch_size):
+            end = min(i + batch_size, m)
+            # 批量梯度下降
+            batch_X = X[dataIndex[i:end]]
+            batch_y = y[dataIndex[i:end]]
             
-        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}")
+            # 计算梯度
+            z = np.dot(batch_X, weights)
+            h = 1 / (1 + np.exp(-z))  # 计算h
+            error = batch_y - h  # 计算误差
+            gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
+            # 添加L2正则化
+            reg_term = 2 * lambda_reg * weights
+            gradient += reg_term / len(batch_y)
+            weights += learning_rate * gradient  # 更新权重
 
     return weights
 
-def predict_logreg(inX, weights):
-    """逻辑回归预测函数。"""
-    z = np.dot(inX, weights)
-    h = sigmoid(z)
-    return 1 if h >= 0.5 else 0
 
 
+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。
+    """
+    z = np.dot(inX, weights)  # 线性组合
+    prob = 1 / (1 + np.exp(-z))  # 计算概率
+    return 1 if prob >= 0.5 else 0  # 返回分类标签
+
+
+
+# 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**。
+
+    Args:
+    - directory (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+
+    file = open(filepath)
+    fr = file.readlines()
+    data_list = []
+    y = []
+    for data in fr:
+        data = data.strip()
+        data = data.split(' ')
+        data_25 = data[24]
+        y.append(data[22])
+        del data[-1]
+        del data[26]
+        del data[25]
+        del data[24]
+        del data[22]
+        del data[2]
+        for i in data_25:
+            data.append(i)
+        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
+        data_list.append(data)
+    data_number = len(y)
+    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
+    X = np.array(data_list)
+    X_train = np.insert(X, 0, 1, axis=1)
+    return X_train, y_train
+   
+
 
 
 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")
@@ -86,4 +139,17 @@ if __name__ == "__main__":
 
     # 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"预测结果: {y_pred}, 实际结果: {y_test[11]}")'''
+    X_train, y_train = load_data("./data/horse-colic.data")
+    X_test, y_test = load_data("./data/horse-colic.test")
+    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01,lambda_reg=0.2)
+    error=0
+    for i in range(len(y_test)):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred != y_test[i]:
+            error+=1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
+    print((len(y_test)-error)/len(y_test))
+
+
+