更新 function.py

function.py

@@ -1,70 +1,82 @@
-# function.py
 import numpy as np  
 from sklearn.preprocessing import StandardScaler  
-from sklearn.metrics import accuracy_score  
-
-# 学号和姓名  
-id = "202210423223"  
+  
+# 填写学号和姓名  
+id = "20221042323"  
 name = "李顺潮"  
-
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.1):  
-    m, n = X.shape  
+  
+def train_logreg(X, y, other_params="你自己设置一些其它参数", learning_rate=0.01, num_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。  
+    - other_params (str): 其它参数，这里暂未使用。  
+    - learning_rate (float): 学习率。  
+    - num_iterations (int): 迭代次数。  
+  
+    Returns:  
+    - numpy array: 训练得到的权重。  
+    """  
+    # 添加偏置项  
+    X_b = np.c_[np.ones((X.shape[0], 1)), X]  # 添加一列1作为偏置项  
+    m, n = X_b.shape  
     weights = np.zeros(n)  
-    bias = 0  
-    
-    for _ in range(iterations):  
-        linear_output = np.dot(X, weights) + bias  
-        y_predicted = 1 / (1 + np.exp(-linear_output))  
-        
-        # 计算梯度（包括正则化项）  
-        dw = (1 / m) * np.dot(X.T, (y_predicted - y)) + (lambda_reg / m) * weights  
-        db = (1 / m) * np.sum(y_predicted - y)  
-        
-        # 更新权重和偏置  
+  
+    # 梯度下降  
+    for iteration in range(num_iterations):  
+        y_pred_prob = 1 / (1 + np.exp(-np.dot(X_b, weights)))  
+        dw = (1 / m) * np.dot(X_b.T, (y_pred_prob - y))  
         weights -= learning_rate * dw  
-        bias -= learning_rate * db  
-    
-    return weights, bias    
-
-def predict_logreg(inX, weights, bias):  
-    linear_output = np.dot(inX, weights) + bias  
-    y_predicted = 1 if linear_output >= 0 else 0  
-    return y_predicted   
-
+      
+    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。  
+    """  
+    # 添加偏置项  
+    inX_b = np.c_[1, inX]  
+    y_pred_prob = 1 / (1 + np.exp(-np.dot(inX_b, weights)))  
+    return 1 if y_pred_prob > 0.5 else 0  
+  
 def load_data(filepath):  
-    data = []  
-    with open(filepath, 'r') as file:  
-        for line in file:  
-            parts = line.strip().split()  
-            features = [float(part) if part != '?' else np.nan for part in parts[:-1]]  
-            features = np.nan_to_num(features, nan=0.0)  
-            label = int(parts[-1])  
-            data.append(features + [label])  
-
-    data_array = np.array(data)  
-    X = data_array[:, :-1]  
-    y = data_array[:, -1]  
-    
-    # 特征缩放  
-    scaler = StandardScaler()  
-    X_scaled = scaler.fit_transform(X)  
-    
-    return X_scaled, y  
-
+    """  
+    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 = np.loadtxt(filepath, delimiter=",")  
+    X = data[:, :-1]  # 特征  
+    y = data[:, -1]   # 标签，转换为0和1  
+    y = np.where(y == 2, 1, 0)  # 将标签2转换为1，其他（1和3，这里只有1）转换为0  
+    return X, y  
+  
 if __name__ == "__main__":  
-    # 加载训练集和测试集  
+    # 加载训练集  
     X_train, y_train = load_data("./data/horse-colic.data")  
-    X_test, y_test = load_data("./data/horse-colic.test")  
-    
+      
+    # 数据标准化  
+    scaler = StandardScaler()  
+    X_train_scaled = scaler.fit_transform(X_train)  
+      
     # 训练模型  
-    weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.1)  
-    
-    # 测试模型并评估性能  
-    y_pred = [predict_logreg(x, weights, bias) for x in X_test]  
-    accuracy = accuracy_score(y_test, y_pred)  
-    print(f"模型准确率: {accuracy}")  
-    
-    # 如果测试样本有效  
-    if len(y_test) > 11:  
-        sample_index = 11  
-        print(f"预测结果: {y_pred[sample_index]}, 实际结果: {y_test[sample_index]}")
+    weights = train_logreg(X_train_scaled, y_train)  
+      
+    # 测试预测（这里示例性地选择一个样本进行预测）  
+    sample_index = 0  # 选择第一个样本进行预测  
+    y_pred = predict_logreg(X_train_scaled[sample_index], weights)  
+    print(f"预测结果: {y_pred}, 实际结果: {y_train[sample_index]}")