更新 function.py

function.py

@@ -54,16 +54,12 @@ def classify0(inX, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-    # 计算待分类样本与训练集中每个样本之间的距离
     dists = np.sqrt(((dataSet - inX) ** 2).sum(axis=1))
-    # 根据距离对训练样本进行排序
     sorted_index = np.argsort(dists)
-    # 选择距离最近的k个样本
     class_count = {}
     for i in range(k):
         vote_label = labels[sorted_index[i]]
         class_count[vote_label] = class_count.get(vote_label, 0) + 1
-    # 投票得到最多的标签作为预测结果
     sorted_class_count = sorted(class_count.items(), key=lambda item: item[1], reverse=True)
     if sorted_class_count:
         return sorted_class_count[0][0]
@@ -103,19 +99,23 @@ if __name__ == "__main__":
     train_features = standardize(train_features)
     test_features = standardize(test_features)
     
-    correct_count = 0
-    for i in range(len(test_features)):
-        test_feature = test_features[i].reshape(1, -1)
-        predict_label = classify0(test_feature, train_features, train_labels, k=3)
-        if predict_label == -1:
-            continue
-        correct_count += (predict_label == test_labels[i])
+    # 尝试不同的 K 值
+    best_k = 3
+    best_accuracy = 0.0
     
-    accuracy = correct_count / len(test_features)
-    print(f"Accuracy: {accuracy:.2f}")
-
-
-
+    for k in [1, 3, 5, 7, 9]:
+        correct_count = 0
+        for i in range(len(test_features)):
+            test_feature = test_features[i].reshape(1, -1)
+            predict_label = classify0(test_feature, train_features, train_labels, k=k)
+            if predict_label == -1:
+                continue
+            correct_count += (predict_label == test_labels[i])
+        
+        accuracy = correct_count / len(test_features)
+        print(f"Accuracy with k={k}: {accuracy:.2f}")
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_k = k
     
-    accuracy = correct_count / len(test_features)
-    print(f"Accuracy: {accuracy:.2f}")
+    print(f"Best K: {best_k}, Best Accuracy: {best_accuracy:.2f}")