更新 function.py

function.py

@@ -21,12 +21,26 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
+id = "202210423209"
-name = "test_name"
+name = "万子玉"
 
 
 # 这里写自己的代码实现
-def train_logreg(X, y, other_params="你自己设置一些其它参数"):
+def sigmoid(z):
+    return 1 / (1 + np.exp(-z))
+
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
+    weights = np.zeros(X.shape[1])
+    m = X.shape[0]
+    
+    for _ in range(iterations):
+        z = np.dot(X, weights)
+        h = sigmoid(z)
+        gradient = np.dot(X.T, (h - y)) / m
+        weights -= learning_rate * gradient
+        
+    return weights
     """
     对率回归训练函数。
 
@@ -41,6 +55,11 @@ def train_logreg(X, y, other_params="你自己设置一些其它参数"):
 
 
 def predict_logreg(inX, weights):
+    inX = np.insert(inX, 0, 1)  # 添加偏置项
+    z = np.dot(inX, weights)
+    h = sigmoid(z)
+    return 1 if h >= 0.5 else 0
+
     """
     对率回归预测函数。
 
@@ -55,6 +74,24 @@ def predict_logreg(inX, weights):
 
 # 这里也写自己的代码实现
 def load_data(filepath):
+    with open(filepath, 'r') as file:
+        lines = file.readlines()
+    
+    data = [line.strip().split() for line in lines]
+    data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
+    
+    # 处理缺失值，这里简单用平均值填充
+    for i in range(len(data[0])):
+        mean_val = np.nanmean([row[i] for row in data if not np.isnan(row[i])])
+        for row in data:
+            if np.isnan(row[i]):
+                row[i] = mean_val
+    
+    # 分离特征和标签
+    X = [row[:-1] for row in data]
+    y = [row[-1] for row in data]
+    
+    return np.array(X), np.array(y)
     """
     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**。