更新 function.py

function.py

@@ -1,5 +1,6 @@
 # function.py
 import numpy as np
+import pandas as pd
 
 """
 实验说明:
@@ -23,8 +24,12 @@ import numpy as np
 姓名请直接**填写中文**
 例如: name = "张三"
 """
-id = "202210423xxx"
+id = "202210423223"
-name = "test_name"
+name = "李顺潮"
+
+def sigmoid(z):  
+    """Sigmoid函数，用于对率回归的预测。"""  
+    return 1 / (1 + np.exp(-z)) 
 
 
 # 这里写自己的代码实现
@@ -40,6 +45,19 @@ def train_logreg(X, y, other_params="你自己设置一些其它参数"):
     Returns:
     - numpy array: 训练得到的权重。
     """
+    # 初始化权重  
+    weights = np.zeros(X.shape[1])  
+    learning_rate = 0.01  
+    iterations = 1000  
+    
+    for _ in range(iterations):  
+        z = np.dot(X, weights)  
+        predictions = sigmoid(z)  
+        error = y - predictions  
+        gradient = np.dot(X.T, error)  
+        weights += learning_rate * gradient  
+    
+    return weights 
 
 
 def predict_logreg(inX, weights):
@@ -53,6 +71,10 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
+    # 计算预测值  
+    z = np.dot(inX, weights)  
+    probability = sigmoid(z)  
+    return 1 if probability >= 0.5 else 0  
 
 
 # 这里也写自己的代码实现
@@ -67,6 +89,18 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
+        # 使用pandas加载数据  
+    df = pd.read_csv(filepath, header=None)  
+    
+    # 替换缺失值和非数值数据，这里假设我们用0来填补缺失数据  
+    df.replace('?', np.nan, inplace=True)  
+    df.fillna(0, inplace=True)  
+    
+    # 将数据拆分为特征和标签  
+    X = df.iloc[:, :-1].values  # 特征  
+    y = df.iloc[:, -1].values    # 标签  
+
+    return X, y 
 
 
 if __name__ == "__main__":  
@@ -74,12 +108,10 @@ if __name__ == "__main__":
     # 加载训练集  
     X_train, y_train = load_data("./data/horse-colic.data")  
 
-    # 加载测试集
+    # 训练模型  
-    X_test, y_test = load_data("./data/horse-colic.test")
+    weights = train_logreg(X_train, y_train)  
     
-    # 训练对率回归模型
+    # 测试单个样本的预测  
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    sample = X_train[0].reshape(1, -1)  # 取出第一行作为样本  
-
+    prediction = predict_logreg(sample, weights)  
-    # 测试单个数据
+    print(f"样本预测: {prediction}")  
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")