更新 function.py

2024-10-17 20:12:56 +08:00
parent 6fdfe0b65c
commit 2dff16e543
1 changed files with 6 additions and 3 deletions
@@ -41,19 +41,22 @@ def classify(input_vector, dataSet, labels, k=2):
    Returns:
    - int: 预测的分类标签。
    """
+    sigma = 1.0
    dataSet_size = dataSet.shape[0]
    # 计算欧氏距离
    diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
    sq_diff_mat = diff_mat ** 2
-    sq_distances = sq_diff_mat.sum(axis=1)
+    sq_distances = sq_diff_mat.sum(axis = 1)
    distances = np.sqrt(sq_distances)
    # 对距离进行排序
    sorted_indices = distances.argsort()
    class_count = {}
    for i in range(k):
        vote_label = labels[sorted_indices[i]]
-        class_count[vote_label] = class_count.get(vote_label, 0) + 1
-    sorted_class_count = sorted(class_count.items(), key=lambda x: x[1], reverse=True)
+        # 计算权重，这里使用高斯核函数
+        weight = np.exp(- sq_distances[sorted_indices[i]] / (2 * sigma ** 2))
+        class_count[vote_label] = class_count.get(vote_label, 0)+ weight
+    sorted_class_count = sorted(class_count.items(), key = lambda x: x[1], reverse = True)
    return sorted_class_count[0][0]