更新 function.py

function.py

@@ -1,7 +1,7 @@
 import numpy as np
+from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
-from sklearn.model_selection import train_test_split, cross_val_score
 
 id = "202210423104"
 name = "张钦诚"
@@ -31,17 +31,16 @@ def preprocess_data(X):
     return X_poly
 
 def train_logreg(X, y):
-    X_processed = preprocess_data(X)  # 预处理训练数据
     model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
+    X_processed = preprocess_data(X)  # 预处理训练数据
     model.fit(X_processed, y)
     return model  # 返回训练好的模型
 
 def predict_logreg(model, X):
     X_processed = preprocess_data(X.reshape(1, -1))  # 预处理单个测试样本
-    return model.predict(X_processed)[0]  # 预测并返回结果
+    return model.predict(X_processed)[0]  # 返回预测结果
 
 if __name__ == "__main__":
-    # 加载数据
     X, y = load_data("./data/horse-colic.data")
 
     # 划分数据集
@@ -53,12 +52,13 @@ if __name__ == "__main__":
     # 预测
     y_pred = []
     for sample in X_test:
-        y_pred.append(predict_logreg(model, sample))
+        y_pred.append(predict_logreg(model, sample))  # 逐个样本预测
 
     # 计算准确率
     accuracy = np.mean(y_pred == y_test)
     print(f"测试出的正确率: {accuracy * 100:.2f}%")
 
     # 交叉验证
-    cv_scores = cross_val_score(model, preprocess_data(X_train), y_train, cv=5)
+    X_train_processed = preprocess_data(X_train)  # 预处理训练数据
+    cv_scores = cross_val_score(model, X_train_processed, y_train, cv=5)
     print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")