更新 function.py

function.py

@@ -1,6 +1,5 @@
 import numpy as np
 import os
-from scipy.spatial import KDTree
 
 """
 实验说明:
@@ -29,7 +28,7 @@ id = "202210423117"
 name = "程悦"
 
 
-def classify(input_vector, dataSet, labels, k=5):
+def classify(input_vector, dataSet, labels, k=2):
     """
     KNN 分类算法。
 
@@ -42,9 +41,11 @@ def classify(input_vector, dataSet, labels, k=5):
     Returns:
     - int: 预测的分类标签。
     """
-    kdtree = KDTree(dataSet)
-    distances, indices = kdtree.query(input_vector, k=k)
-    k_nearest_labels = [labels[i] for i in indices]
+    num_samples = dataSet.shape[0]
+    diffs = np.tile(input_vector, (num_samples, 1)) - dataSet
+    distances = np.sum(diffs**2, axis=1)**0.5
+    sorted_indices = np.argsort(distances)
+    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
     unique_labels, counts = np.unique(k_nearest_labels, return_counts=True)
     return unique_labels[np.argmax(counts)]
 
@@ -86,35 +87,49 @@ def load_dataset(directory):
             labels.append(label)
     return np.array(data), np.array(labels)
 
-def load_test_dataset(directory):
-    return load_dataset(directory)
-
-def calculate_accuracy():
-    train_data, train_labels = load_dataset("trainingDigits")
-    test_data, test_labels = load_test_dataset("testDigits")
-    correct_count = 0
-    for i in range(len(test_data)):
-        predicted_label = classify(test_data[i].reshape(1, 1024), train_data, train_labels)
-        if predicted_label == test_labels[i]:
-            correct_count += 1
-    accuracy = correct_count / len(test_data)
-    print(f"分类精度: {accuracy}")
-
-def test_different_k():
-    train_data, train_labels = load_dataset("trainingDigits")
-    test_data, test_labels = load_test_dataset("testDigits")
-    k_values = [1, 3, 5, 7, 9]
-    for k in k_values:
-        correct_count = 0
-        for i in range(len(test_data)):
-            predicted_label = classify(test_data[i].reshape(1, 1024), train_data, train_labels, k=k)
-            if predicted_label == test_labels[i]:
-                correct_count += 1
-        accuracy = correct_count / len(test_data)
-        print(f"k = {k}时的分类精度: {accuracy}")
 
 if __name__ == "__main__":
-    # 测试不同k值的分类精度
-    test_different_k()
-    # 计算分类精度
-    calculate_accuracy()
+    # 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 = (
+        "00000000000000110000000000000000"
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111111111000000000000"
+        "00000001111111111111111000000000"
+        "00000001111111111111111100000000"
+        "00000011111111111111111110000000"
+        "00000011111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000000111111111100111111100000"
+        "00000000111111111000111111100000"
+        "00000000011111111001111111100000"
+        "00000000011111111111111111000000"
+        "00000000001111111111111111000000"
+        "00000000000111111111111111000000"
+        "00000000000011111111111100000000"
+        "00000000000001111111110000000000"
+        "00000000000000000111100000000000"
+    )
+    predicted_label = classify(
+        np.array([int(char) for char in test_data]).reshape(1, 1024),
+        train_data,
+        train_labels,
+    )
+
+    print(f"预测的标签: {predicted_label}")