更新 function.py

function.py

@@ -1,6 +1,6 @@
 import numpy as np
 import os
-from sklearn.preprocessing import StandardScaler
+
 """
 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。
@@ -42,15 +42,11 @@ def classify(input_vector, dataSet, labels, k=2):
     - int: 预测的分类标签。
     """
     dataSet_size = dataSet.shape[0]
-    # 计算马氏距离
-    cov_matrix = np.cov(dataSet.T)
-    inv_cov_matrix = np.linalg.pinv(cov_matrix)
+    # 计算欧氏距离
     diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
-    distances = []
-    for i in range(dataSet_size):
-        distance = np.sqrt(np.dot(np.dot(diff_mat[i], inv_cov_matrix), diff_mat[i].T))
-        distances.append(distance)
-    distances = np.array(distances)
+    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 = {}
@@ -61,7 +57,6 @@ def classify(input_vector, dataSet, labels, k=2):
     return sorted_class_count[0][0]
 
 
-
 def img_to_vector(filename):
     """
     将二值图像转换为向量。
@@ -101,13 +96,11 @@ def load_dataset(directory):
                 label = int(file.split('_')[0])
                 labels.append(label)
                 data_set.append(img_to_vector(os.path.join(root, file)))
-    data_set = np.array(data_set).reshape(len(data_set), -1)
-    scaler = StandardScaler()
-    data_set = scaler.fit_transform(data_set)
-    return data_set, np.array(labels)
+    return np.array(data_set).reshape(len(data_set), -1), np.array(labels)
 
 
 if __name__ == "__main__":
+    # 以下代码可用于测试，可自行随意修改
     train_data, train_labels = load_dataset("trainingDigits")
 
     test_data = (
@@ -149,3 +142,5 @@ if __name__ == "__main__":
         train_data,
         train_labels,
     )
+
+    print(f"预测的标签: {predicted_label}")