First test

function.py

@@ -1,5 +1,7 @@
 # function.py
 import numpy as np
+from scipy.spatial.distance import mahalanobis
+import operator
 
 """
 挑战说明:
@@ -23,8 +25,8 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
-name = "test_name"
+id = "202210423229"
+name = "向兴宇"
 
 
 """
@@ -50,6 +52,31 @@ def classify0(inX, dataSet, labels):
     Returns:
     - int: 预测的分类标签。
     """
+    # 获取数据集的大小
+    dataSetSize = dataSet.shape[0]
+
+    # 计算数据集的协方差矩阵的逆
+    VI = np.linalg.inv(np.cov(dataSet.T))
+
+    # 计算 Mahalanobis 距离
+    distances = np.zeros(dataSetSize)
+    for i in range(dataSetSize):
+        distances[i] = mahalanobis(inX, dataSet[i], VI)
+
+    # 对距离排序，获取前 k 个最近的样本索引
+    sortedDistIndices = distances.argsort()
+
+    # 统计前 k 个样本的标签
+    classCount = {}
+    for i in range(3):
+        voteLabel = labels[sortedDistIndices[i]]
+        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
+
+    # 返回出现次数最多的标签
+    sortedClassCount = sorted(
+        classCount.items(), key=operator.itemgetter(1), reverse=True
+    )
+    return sortedClassCount[0][0]
 
 
 def load_data(file_path):
@@ -71,8 +98,25 @@ def load_data(file_path):
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
 
+    # 加载训练集和测试集
     train_file = "datingTrainSet2.tsv"
+    test_file = "datingTestSet2.tsv"
 
     train_data, train_labels = load_data(train_file)
+    test_data, test_labels = load_data(test_file)
 
-    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))
+    correct = 0
+    total = len(test_data)
+
+    for i in range(total):
+        # 获取测试数据中的每个样本
+        result = classify0(test_data[i], train_data, train_labels)
+        if result == test_labels[i]:
+            correct += 1
+        else:
+            print(
+                f"第 {i+1} 次测试错误，数据 {test_data[i]} 被分类到 {result} 实际是 {test_labels[i]}"
+            )
+
+    accuracy = correct / total
+    print(f"测试集正确个数 {correct}，总个数 {total}，正确率 {accuracy}")