4444444

function.py

@@ -25,7 +25,7 @@ from sklearn.model_selection import train_test_split, GridSearchCV
 id = "202210423221"
 name = "廖子豪"
 
-def load_data(filepath):
+def load_data(filepath, fit_scaler=False):
     data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
     labels = data[:, -1].astype(int)
     features = data[:, :-1]
@@ -35,12 +35,28 @@ def load_data(filepath):
     
     # 数据标准化
     scaler = StandardScaler()
+    if fit_scaler:
         features = scaler.fit_transform(features)
+    else:
+        features = scaler.transform(features)
     
     return features, labels, scaler
 
-def train_logreg(X, y, random_state=42):
-    # 使用 GridSearchCV 进行参数调优
+# 示例使用
+if __name__ == "__main__":
+    # 加载训练数据和测试数据
+    X_train, y_train, scaler = load_data("./data/horse-colic.data", fit_scaler=True)
+    X_test, y_test, _ = load_data("./data/horse-colic.test", fit_scaler=False)  # 使用相同的scaler
+
+    # 训练模型
+    model = train_logreg(X_train, y_train, random_state=42)
+
+    # 进行预测
+    y_pred = [predict_logreg(x, model) for x in X_test]
+
+    # 计算准确率
+    accuracy = np.mean(y_pred == y_test)
+    print(f"Test Accuracy: {accuracy:.2f}")
     param_grid = {'C': [0.01, 0.1, 1, 10, 100], 'penalty': ['l1', 'l2']}
     model = LogisticRegression(solver='liblinear', random_state=random_state)
     grid_search = GridSearchCV(model, param_grid, cv=5)