更新 function.py

function.py

@@ -30,7 +30,7 @@ name = "董秋"
 # 这里写自己的代码实现
 import numpy as np
 from sklearn.svm import SVC
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.metrics import classification_report, accuracy_score
 from sklearn.preprocessing import StandardScaler
 
@@ -40,7 +40,7 @@ def load_data(filepath):
     从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
 
     Args:
-    - directory (str): 数据文件路径。
+    - filepath (str): 数据文件路径。
 
     Returns:
     - np.array: 特征数据。
@@ -119,33 +119,32 @@ def predict_svm(inX, model):
 
 if __name__ == "__main__":
     # 加载数据
-    X_train, y_train = load_data("./data/horse-colic.data")
-    X_test, y_test = load_data("./data/horse-colic.test")
-
-    # 划分数据集
-    X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=42, stratify=y_train)
+    X, y = load_data("./data/horse-colic.data")
 
     # 数据标准化
     scaler = StandardScaler()
-    X_train = scaler.fit_transform(X_train)
-    X_test = scaler.transform(X_test)
+    X = scaler.fit_transform(X)
+
+    # 进行交叉验证评估
+    print("正在进行交叉验证评估...")
+
+    # 使用交叉验证计算准确率，设置10折交叉验证
+    svm_model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)
+    cv_scores = cross_val_score(svm_model, X, y, cv=10, scoring='accuracy')
+
+    # 输出交叉验证的评估结果
+    print(f"交叉验证准确率: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")
 
     # 训练支持向量机模型
-    print("正在训练支持向量机模型...")
-    svm_model = train_svm(X_train, y_train)
-
-    # 预测测试集
-    y_pred = svm_model.predict(X_test)
+    svm_model.fit(X, y)
 
     # 输出评估结果
+    y_pred = svm_model.predict(X)
+
+    # 输出分类报告
     print("\n分类报告:")
-    print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"]))
+    print(classification_report(y, y_pred, target_names=["存活", "安乐死", "死亡"]))
 
     # 输出准确率
-    accuracy = accuracy_score(y_test, y_pred)
-    print(f"测试集准确率: {accuracy * 100:.2f}%")
-
-    # 测试单个数据
-    test_sample = X_test[11]  # 选择第12个样本（从0开始计数）
-    y_pred_single = predict_svm(test_sample, svm_model)
-    print(f"\n单个样本预测结果: {y_pred_single}, 实际结果: {y_test[11]}")
+    accuracy = accuracy_score(y, y_pred)
+    print(f"模型准确率: {accuracy * 100:.2f}%")