更新 function.py

function.py

@@ -63,27 +63,36 @@ def predict_logreg(inX, weights):
     return 1 if h > 0.5 else 0
 
 def load_data(filepath):
+    """加载数据并处理缺失值。"""
     data, labels = [], []
+
     with open(filepath, 'r') as f:
-        for line in f.readlines():
+        for line in f:
-            line = line.strip().split()
+            values = line.strip().replace('?', '0').split()
-            if len(line) >= 1 and line[-1].isdigit():
+            try:
-                line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
+                values = [float(v) for v in values]
-                data.append(line_data)
+
-                labels.append(int(line[-1]))
+                # 合并特征23的取值
+                if values[22] in [2, 3]:  # 特征23索引(22)
+                    labels.append(0)  # 死亡
+                elif values[22] == 1:
+                    labels.append(1)  # 生存
+                else:
+                    continue  # 无效标签，丢弃
+
+                # 用0填充缺失值并提取特征
+                data.append([0 if v == 0 else v for v in values[:2] + values[3:23]])  # 保留特征1, 2 和特征4-23
+            except ValueError:
+                continue
 
     data = np.array(data)
     labels = np.array(labels)
 
-    target_variable = labels
+    # 数据标准化
-    target_variable[(target_variable == 2) | (target_variable == 3)] = 0
-
-    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
-
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
 
-    return data, target_variable
+    return data, labels
 
 def accuracy(X, y, weights):
     predictions = [predict_logreg(x, weights) for x in X]