更新 function.py

function.py

@@ -5,7 +5,6 @@ import numpy as np
 import os
 from collections import Counter
 from sklearn.preprocessing import MinMaxScaler
-from sklearn.neighbors import KDTree  # 确保正确导入 KDTree
 
 # 加载数据集
 def load_dataset(directory):
@@ -32,12 +31,13 @@ def img_to_vector(file_path):
                 vector[32 * i + j] = int(lines[i][j])
     return vector
 
-# 使用 KDTree 进行 kNN 分类
-def classify(input_vector, tree, labels, k=7):
-    # 使用 KDTree 查找最近邻
-    input_vector = input_vector.reshape(1, -1)  # 确保 input_vector 是二维数组
-    distances, indices = tree.query(input_vector, k=k)
-    nearest_labels = labels[indices.flatten()]
+# 使用欧式距离进行 kNN 分类
+def classify(input_vector, dataSet, labels, k=7):
+    # 计算所有训练样本与输入样本的欧式距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    # 获取距离最近的k个样本的标签
+    nearest_neighbors = np.argsort(distances)[:k]
+    nearest_labels = labels[nearest_neighbors]
     
     # 投票，返回出现次数最多的标签
     most_common = Counter(nearest_labels).most_common(1)
@@ -57,16 +57,13 @@ def main():
     training_data = normalize_data(training_data)
     test_data = normalize_data(test_data)
 
-    # 使用 KDTree 构建训练集的树结构
-    tree = KDTree(training_data)
-
     # 测试 kNN 算法
     total_tests = len(test_data)
     correct_predictions = 0
 
     for i in range(total_tests):
         test_sample = test_data[i]
-        prediction = classify(test_sample, tree, training_labels, k=7)
+        prediction = classify(test_sample, training_data, training_labels, k=7)
         actual_label = test_labels[i]
 
         print(f"测试样本 {i+1}: 预测值 = {prediction}, 实际值 = {actual_label}")