更新 function.py

function.py

@@ -3,7 +3,6 @@ import numpy as np
 from collections import Counter
 from scipy.spatial import distance
 
-
 """
 挑战说明:
 - 自行编写实现 KNN 分类算法。
@@ -41,7 +40,7 @@ name = "程悦"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, inv_cov_matrix, k=9):
+def classify0(inX, dataSet, labels, k=9):
     """
     KNN 分类算法。
 
@@ -54,19 +53,25 @@ def classify0(inX, dataSet, labels, inv_cov_matrix, k=9):
     Returns:
     - int: 预测的分类标签。
     """
+    # 计算协方差矩阵并求逆矩阵
+    cov_matrix = np.cov(dataSet, rowvar=False)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
+
     # 计算输入样本与训练集样本的马氏距离
-    distances = distance.cdist(dataSet, np.array([inX]), 'mahalanobis', VI=inv_cov_matrix).flatten()
+    distances = [distance.mahalanobis(inX, data_point, inv_cov_matrix) for data_point in dataSet]
 
     # 按距离排序并选择前 k 个最近的邻居
-    k_indices = np.argpartition(distances, k)[:k]
-    k_nearest_labels = labels[k_indices]
+    k_indices = np.argsort(distances)[:k]
+    k_nearest_labels = [labels[i] for i in k_indices]
 
     # 统计最近邻居中最多的标签
-    most_common_label = Counter(k_nearest_labels).most_common(1)[0][0]
+    label_counts = Counter(k_nearest_labels)
+    most_common_label = label_counts.most_common(1)[0][0]
 
     return most_common_label
 
 
+
 def load_data(file_path):
     """
     加载 TSV 格式数据文件。
@@ -83,20 +88,17 @@ if __name__ == "__main__":
     train_data, train_labels = load_data(train_file)
     test_data, test_labels = load_data(test_file)
 
-    # 计算协方差矩阵并求逆矩阵
-    cov_matrix = np.cov(train_data, rowvar=False)
-    inv_cov_matrix = np.linalg.inv(cov_matrix)
-
     # 测试 classify0 函数
     test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试
-    predicted_label = classify0(test_sample, train_data, train_labels, inv_cov_matrix)
+    predicted_label = classify0(test_sample, train_data, train_labels)
     print(f"Predicted label: {predicted_label}, Actual label: {test_labels[0]}")
 
     # 遍历整个测试集来评估分类器的性能
-    correct_count = sum(
-        classify0(test_data[i], train_data, train_labels, inv_cov_matrix) == test_labels[i]
-        for i in range(len(test_data))
-    )
+    correct_count = 0
+    for i in range(len(test_data)):
+        predicted_label = classify0(test_data[i], train_data, train_labels)
+        if predicted_label == test_labels[i]:
+            correct_count += 1
     accuracy = correct_count / len(test_data)
     print(f"Accuracy: {accuracy * 100:.2f}%")