更新 function.py

function.py

@@ -26,6 +26,8 @@ name = "赵昊龙"
 
 
 # 这里写自己的代码实现
+import numpy as np
+
 def load_data(filepath):
     """
     从文件中加载数据。
@@ -37,15 +39,17 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    file = open(filepath)
+    with open(filepath, 'r') as file:
-    fr = file.readlines()
         data_list = []
-    y_list = []
+        y_list = []  # 确保y_list在这里被初始化
-    for data in fr:
+        for line in file:
-        data = data.strip()
+            data = line.strip()
             data = data.split(' ')
+            if '?' in data:
+                continue  # 跳过包含 '?' 的行
             data_25 = data[24]
-        y_list.append(data[22])
+            y = data[22]  # 确保y在这里被定义
+            y_list.append(y)
             del data[-1]
             del data[26]
             del data[25]
@@ -54,19 +58,13 @@ def load_data(filepath):
             del data[2]
             for i in data_25:
                 data.append(i)
-        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
+            data = [0.0 if data_elem == '?' else float(data_elem) for data_elem in data]
             data_list.append(data)
-    
+        # 将标签转换为1如果它们是'2'或'3'，否则为0
-    data_number = len(y_list)
+        y_array = np.array([1 if label == '2' or label == '3' else 0 for label in y_list])
-    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
+        X_array = np.array(data_list)
-    X = np.array(data_list)
+        X_array = np.insert(X_array, 0, 1, axis=1)  # 添加偏置项
-    
+        return X_array, y_array
-    # 特征缩放
-    scaler = StandardScaler()
-    X = scaler.fit_transform(X)
-    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
-    
-    return X, y_train
 
 def train_logreg(X, y, numIter=1000, learning_rate=0.01, batch_size=128, lambda_reg=0.01):
     """