上传文件至 /

function.py

@@ -7,9 +7,12 @@ name = "张钦诚"
 
 def classify0(inX, dataSet, labels, k=5):
     inX = np.array(inX)
+    # 计算欧氏距离的平方，避免开平方以提高效率
     distances = np.sum((dataSet - inX) ** 2, axis=1)
+    # 获取距离最小的k个样本的索引
     nearest_indices = np.argpartition(distances, k)[:k]
     nearest_labels = labels[nearest_indices]
+    # 统计k个最近邻中出现次数最多的标签
     label_count = Counter(nearest_labels)
     return label_count.most_common(1)[0][0]
 
@@ -20,8 +23,12 @@ def load_data(file_path):
     return features, labels
 
 def standardize(train_data, test_data):
+    """
+    对训练数据和测试数据进行标准化处理。
+    """
     mean = np.mean(train_data, axis=0)
     std = np.std(train_data, axis=0)
+    # 防止标准差为零
     std[std == 0] = 1
     train_standardized = (train_data - mean) / std
     test_standardized = (test_data - mean) / std
@@ -31,17 +38,24 @@ if __name__ == "__main__":
     train_file = "datingTrainSet2.tsv"
     test_file = "datingTestSet2.tsv"
 
+    # 加载训练数据
     train_data, train_labels = load_data(train_file)
+    # 加载测试数据
     test_data, test_labels = load_data(test_file)
 
+    # 数据标准化
     train_data, test_data = standardize(train_data, test_data)
 
+    # 测试样本
     test_sample = [65915, 3.868359, 0.128078]
+    # 标准化测试样本
     test_sample = (np.array(test_sample) - np.mean(train_data, axis=0)) / np.std(train_data, axis=0)
 
+    # 预测标签
     predicted_label = classify0(test_sample, train_data, train_labels)
     print(f"预测的分类标签: {predicted_label}")
 
+    # 计算准确率
     predictions = np.array([classify0(sample, train_data, train_labels) for sample in test_data])
     accuracy = np.mean(predictions == test_labels) * 100
     print(f"准确率: {accuracy:.2f}%")