更新 function.py

function.py

@@ -6,7 +6,7 @@ name = "吴杨洋"
 def sigmoid(z):
     return 1 / (1 + np.exp(-np.clip(z, -500, 500)))
 
-def train_logreg(X, y, numIter=1 + 1000, learning_rate=0.01, lambda_reg=0.01):
+def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
     for j in range(numIter):
@@ -33,21 +33,14 @@ def load_data(filepath):
     for data in fr:
         data = data.strip()
         data = data.split()
-        if len(data) < 25:  # 确保每行数据有足够的元素
+        if len(data) < 26:  # 确保每行数据有足够的元素
             continue
-        y.append(int(data[22]) > 1)  # 假设标签是 0 或 1
+        y.append(1 if data[22] in ['2', '3'] else 0)  # 假设标签是 '2' 或 '3' 为正类
         data_25 = data[24]
-        # 删除不需要的元素
+        data = [float(x) if x != '?' else 0 for x in data[:24] + data_25.split(',')]  # 处理缺失值
-        del data[0], data[1], data[2], data[22], data[24], data[25]
-        for i in data_25.split(','):
-            data.append(i)
-        # 将 '?' 替换为 0
-        data = [0 if x == '?' else float(x) for x in data]
         data_list.append(data)
-    data_number = len(y)
-    y_train = np.array(y)
     X = np.array(data_list)
-    return X, y_train
+    return X, np.array(y)
 
 def standardize(X):
     mean = X.mean(axis=0)
@@ -67,5 +60,5 @@ def main():
     accuracy_test = np.mean(y_pred_test == y_test)
     print(f"Test Accuracy: {accuracy_test:.2f}")
 
-if __name__ == "__main__":
+if __name__.split("__main__"):
     main()