更新 function.py

function.py

@@ -5,9 +5,7 @@ name = "魏明帅"
 
 def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     m, n = X.shape
-    # 添加偏置项
-    X = np.c_[np.ones((m, 1)), X]
-    weights = np.zeros(n + 1)
+    weights = np.zeros(n)
     
     for _ in range(iterations):
         for i in range(m):
@@ -31,20 +29,31 @@ def load_data(filepath):
     with open(filepath, 'r') as f:
         for line in f:
             values = line.strip().split()
+            # 跳过包含 '?' 的行
             if '?' in values:
                 continue
+            # 将标签和特征转换为浮点数
             y.append(float(values[-1]))
             X.append([float(x) for x in values[:-1]])
     
-    # 特征缩放
     X_array = np.array(X)
-    X_scaled = (X_array - np.mean(X_array, axis=0)) / np.std(X_array, axis=0)
-    return X_scaled, np.array(y).reshape(-1, 1)
+    y_array = np.array(y).reshape(-1, 1)
+    
+    # 特征缩放，处理标准差为零的特征
+    stds = np.std(X_array, axis=0)
+    means = np.mean(X_array, axis=0)
+    X_scaled = (X_array - means) / np.where(stds == 0, 1, stds)
+    
+    return X_scaled, y_array
 
 if __name__ == "__main__":
     X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
 
+    # 添加偏置项
+    X_train = np.c_[np.ones((X_train.shape[0], 1)), X_train]
+    X_test = np.c_[np.ones((X_test.shape[0], 1)), X_test]
+
     weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
     y_pred = predict_logreg(X_test[11], weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")