更新 function.py

function.py

@@ -42,11 +42,10 @@ def classify(input_vector, dataSet, labels, k=2):
     - int: 预测的分类标签。
     """
     dataSet_size = dataSet.shape[0]
-    # 计算欧氏距离
+    # 计算曼哈顿距离
     diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
-    sq_diff_mat = diff_mat ** 2
+    abs_diff_mat = np.abs(diff_mat)
-    sq_distances = sq_diff_mat.sum(axis=1)
+    distances = abs_diff_mat.sum(axis=1)
-    distances = np.sqrt(sq_distances)
     # 对距离进行排序
     sorted_indices = distances.argsort()
     class_count = {}
@@ -56,27 +55,7 @@ def classify(input_vector, dataSet, labels, k=2):
     sorted_class_count = sorted(class_count.items(), key=lambda x: x[1], reverse=True)
     return sorted_class_count[0][0]
 
-def cross_validation(dataSet, labels, k_list=(2, 3, 5, 7, 9)):
+
-    from sklearn.model_selection import KFold
-    kf = KFold(n_splits=5)
-    best_k = None
-    best_accuracy = 0
-    for k in k_list:
-        accuracies = []
-        for train_index, test_index in kf.split(dataSet):
-            train_data, test_data = dataSet[train_index], dataSet[test_index]
-            train_labels, test_labels = np.array(labels)[train_index], np.array(labels)[test_index]
-            predictions = []
-            for vector in test_data:
-                predicted_label = classify(vector.reshape(1, -1), train_data, train_labels, k)
-                predictions.append(predicted_label)
-            accuracy = sum([1 for p, t in zip(predictions, test_labels) if p == t]) / len(test_labels)
-            accuracies.append(accuracy)
-        avg_accuracy = sum(accuracies) / len(accuracies)
-        if avg_accuracy > best_accuracy:
-            best_accuracy = avg_accuracy
-            best_k = k
-    return best_k
 
 def img_to_vector(filename):
     """
@@ -122,8 +101,6 @@ def load_dataset(directory):
 
 if __name__ == "__main__":
     train_data, train_labels = load_dataset("trainingDigits")
-    best_k = cross_validation(train_data, train_labels)
-    print("Best k value:", best_k)
 
     test_data = (
         "00000000000000110000000000000000"
@@ -163,7 +140,6 @@ if __name__ == "__main__":
         np.array([int(char) for char in test_data]).reshape(1, 1024),
         train_data,
         train_labels,
-        best_k
     )
 
     print(f"预测的标签: {predicted_label}")