更新 function.py

function.py

@@ -5,7 +5,7 @@ import numpy as np
 import os
 from collections import Counter
 from sklearn.preprocessing import MinMaxScaler
-from sklearn.neighbors import KDTree  # 正确导入 KDTree
+from sklearn.neighbors import KDTree  # 确保正确导入 KDTree
 
 # 加载数据集
 def load_dataset(directory):
@@ -24,18 +24,19 @@ def load_dataset(directory):
 
 # 将32x32的二值图像转换为1x1024的向量
 def img_to_vector(file_path):
-    vector = np.zeros((1, 1024))
+    vector = np.zeros((1024,))  # 注意这里改成一维向量
     with open(file_path, 'r') as f:
         lines = f.readlines()
         for i in range(32):
             for j in range(32):
-                vector[0, 32 * i + j] = int(lines[i][j])
+                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=3):
+def classify(input_vector, tree, labels, k=7):
     # 使用 KDTree 查找最近邻
-    distances, indices = tree.query(input_vector.reshape(1, -1), k=k)
+    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()]
     
     # 投票，返回出现次数最多的标签
@@ -44,10 +45,8 @@ def classify(input_vector, tree, labels, k=3):
 
 # 数据归一化
 def normalize_data(dataSet):
-    num_samples = dataSet.shape[0]
-    dataSet_reshaped = dataSet.reshape(num_samples, -1)
     scaler = MinMaxScaler()
-    return scaler.fit_transform(dataSet_reshaped)
+    return scaler.fit_transform(dataSet)
 
 def main():
     # 加载训练集和测试集
@@ -59,7 +58,7 @@ def main():
     test_data = normalize_data(test_data)
 
     # 使用 KDTree 构建训练集的树结构
-    tree = KDTree(training_data)  # 构建 KDTree
+    tree = KDTree(training_data)
 
     # 测试 kNN 算法
     total_tests = len(test_data)
@@ -67,7 +66,7 @@ def main():
 
     for i in range(total_tests):
         test_sample = test_data[i]
-        prediction = classify(test_sample, tree, training_labels, k=3)
+        prediction = classify(test_sample, tree, 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}")