generated from LufsX/Challenge-kNN
73 lines
2.3 KiB
Python
73 lines
2.3 KiB
Python
import numpy as np
|
|
|
|
def mahalanobis_distance(x1, x2, cov_inv, mean):
|
|
"""
|
|
计算两点之间的马氏距离。
|
|
|
|
Args:
|
|
x1 (numpy array): 第一个点。
|
|
x2 (numpy array): 第二个点。
|
|
cov_inv (numpy array): 协方差矩阵的逆矩阵。
|
|
mean (numpy array): 数据集的均值。
|
|
|
|
Returns:
|
|
float: 两点之间的马氏距离。
|
|
"""
|
|
delta = x1 - x2
|
|
dist = delta @ cov_inv @ delta.T
|
|
return np.sqrt(dist)
|
|
|
|
def classify0(inX, dataSet, labels, k=3):
|
|
"""
|
|
使用马氏距离的 KNN 分类算法。
|
|
|
|
Args:
|
|
- inX (numpy array): 输入待分类的样本。
|
|
- dataSet (numpy array): 训练数据集。
|
|
- labels (list or numpy array): 训练集对应的标签。
|
|
- k (int): kNN 算法参数，默认值为 3。
|
|
|
|
Returns:
|
|
- int: 预测的分类标签。
|
|
"""
|
|
# 计算训练数据集的协方差矩阵和均值
|
|
cov_matrix = np.cov(dataSet, rowvar=False)
|
|
mean = np.mean(dataSet, axis=0)
|
|
cov_inv = np.linalg.inv(cov_matrix + np.eye(cov_matrix.shape[0]) * 1e-5) # 加上一个小的单位矩阵以避免奇异矩阵
|
|
|
|
# 计算待分类样本与训练集中每个样本的马氏距离
|
|
distances = np.array([mahalanobis_distance(inX, x, cov_inv, mean) for x in dataSet])
|
|
|
|
# 获取距离最近的 k 个样本的索引
|
|
sortedDistIndices = distances.argsort()[:k]
|
|
|
|
# 获取这些样本对应的标签
|
|
classCount = {}
|
|
for i in sortedDistIndices:
|
|
voteLabel = labels[i]
|
|
classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
|
|
|
|
# 选择出现次数最多的标签作为预测标签
|
|
sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
|
|
return sortedClassCount[0][0]
|
|
|
|
|
|
def load_data(file_path):
|
|
"""
|
|
加载 TSV 格式数据文件。
|
|
"""
|
|
data = np.loadtxt(file_path, delimiter="\t")
|
|
features = data[:, :-1]
|
|
labels = data[:, -1].astype(int)
|
|
return features, labels
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# 以下代码可用于测试，可自行随意修改
|
|
train_file = "datingTrainSet2.tsv"
|
|
train_data, train_labels = load_data(train_file)
|
|
|
|
# 测试一个样本
|
|
test_sample = np.array([65915, 3.868359, 0.128078])
|
|
predicted_label = classify0(test_sample, train_data, train_labels)
|
|
print(f"The predicted label for the test sample is: {predicted_label}") |