更新 function.py

function.py

@@ -57,24 +57,27 @@ def preprocess_data(X, y):
 
     return X, y
 
+
+
 def load_data(filepath):
     # 使用csv模块读取数据
     data = []
     with open(filepath, 'r') as file:
         reader = csv.reader(file, delimiter=' ')
         for row in reader:
-            if row and row[0] != '?':  # 忽略以'?'开头的行
-                row = [float(x) if x != '?' else np.nan for x in row]
+            if row:  # 确保行不为空
+                # 将非数值和空字符串转换为np.nan
+                row = [float(x) if x.replace('.', '', 1).isdigit() else np.nan for x in row]
                 data.append(row)
     
-    # 将'?'替换为np.nan
+    # 将列表转换为numpy数组
     data = np.array(data, dtype=float)
 
     # 使用SimpleImputer填充缺失值
     imputer = SimpleImputer(missing_values=np.nan, strategy='constant', fill_value=0)
     data = imputer.fit_transform(data)
 
-    # 将所有列转换为数值类型
+    # 分割特征和标签
     X = data[:, :-1]
     y = data[:, -1].astype(int)
 
@@ -83,6 +86,18 @@ def load_data(filepath):
 
     return X, y
 
+def preprocess_data(X, y):
+    # 合并目标变量的类别
+    y[y == 2] = 0
+    y[y == 3] = 0
+
+    # 删除特征3和特征24~28
+    X = np.delete(X, [3], axis=1)
+    X = X[:, :23]
+
+    return X, y
+
+# 确保其他函数（sigmoid, train_logreg, predict_logreg）保持不变
 def main():
     # 更新文件路径以匹配实际位置
     X_train, y_train = load_data("C:/Users/HP/Desktop/机器学习/Experiment-LogReg/data/horse-colic.data")