更新 function.py

function.py

@@ -1,6 +1,6 @@
 import numpy as np
 import os
-from scipy.spatial import KDTree
+
 """
 实验说明:
 - 自行编写实现数据加载与 kNN 的手写数字分类算法。
@@ -28,7 +28,7 @@ id = "202210423117"
 name = "程悦"
 
 
-def classify(input_vector, dataSet, labels, k=20):
+def classify(input_vector, dataSet, labels, k=2):
     """
     KNN 分类算法。
 
@@ -41,11 +41,17 @@ def classify(input_vector, dataSet, labels, k=20):
     Returns:
     - int: 预测的分类标签。
     """
-    tree = KDTree(dataSet)
+    dataSet_size = dataSet.shape[0]
-    distances, indices = tree.query(input_vector, k=k)
+    # 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)
+    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[indices[i]]
+        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)
     return sorted_class_count[0][0]
@@ -94,47 +100,47 @@ def load_dataset(directory):
 
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
+    # # 以下代码可用于测试，可自行随意修改
-    train_data, train_labels = load_dataset("trainingDigits")
+    # train_data, train_labels = load_dataset("trainingDigits")
 
-    test_data = (
+    # test_data = (
-        "00000000000000110000000000000000"
+    #     "00000000000000110000000000000000"
-        "00000000000011111000000000000000"
+    #     "00000000000011111000000000000000"
-        "00000000000011111100000000000000"
+    #     "00000000000011111100000000000000"
-        "00000000001111111110000000000000"
+    #     "00000000001111111110000000000000"
-        "00000000001111111110000000000000"
+    #     "00000000001111111110000000000000"
-        "00000000001111111100000000000000"
+    #     "00000000001111111100000000000000"
-        "00000000011111111000000000000000"
+    #     "00000000011111111000000000000000"
-        "00000000111111111000000000000000"
+    #     "00000000111111111000000000000000"
-        "00000000111111110000000000000000"
+    #     "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
+    #     "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
+    #     "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
+    #     "00000000111111110000000000000000"
-        "00000000111111100000000000000000"
+    #     "00000000111111100000000000000000"
-        "00000001111111100000000000000000"
+    #     "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
+    #     "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
+    #     "00000001111111100000000000000000"
-        "00000001111111111111000000000000"
+    #     "00000001111111111111000000000000"
-        "00000001111111111111111000000000"
+    #     "00000001111111111111111000000000"
-        "00000001111111111111111100000000"
+    #     "00000001111111111111111100000000"
-        "00000011111111111111111110000000"
+    #     "00000011111111111111111110000000"
-        "00000011111111111111111110000000"
+    #     "00000011111111111111111110000000"
-        "00000001111111111111111110000000"
+    #     "00000001111111111111111110000000"
-        "00000001111111111111111110000000"
+    #     "00000001111111111111111110000000"
-        "00000000111111111100111111100000"
+    #     "00000000111111111100111111100000"
-        "00000000111111111000111111100000"
+    #     "00000000111111111000111111100000"
-        "00000000011111111001111111100000"
+    #     "00000000011111111001111111100000"
-        "00000000011111111111111111000000"
+    #     "00000000011111111111111111000000"
-        "00000000001111111111111111000000"
+    #     "00000000001111111111111111000000"
-        "00000000000111111111111111000000"
+    #     "00000000000111111111111111000000"
-        "00000000000011111111111100000000"
+    #     "00000000000011111111111100000000"
-        "00000000000001111111110000000000"
+    #     "00000000000001111111110000000000"
-        "00000000000000000111100000000000"
+    #     "00000000000000000111100000000000"
-    )
+    # )
-    predicted_label = classify(
+    # predicted_label = classify(
-        np.array([int(char) for char in test_data]).reshape(1, 1024),
+    #     np.array([int(char) for char in test_data]).reshape(1, 1024),
-        train_data,
+    #     train_data,
-        train_labels,
+    #     train_labels,
-    )
+    # )
 
-    print(f"预测的标签: {predicted_label}")
+    # print(f"预测的标签: {predicted_label}")