k-近邻算法入门代码

代码

from numpy import *
import operator


# 构造四个点的坐标
def createDataSet():
    group = array([
        [1.0, 1.1],
        [1.0, 1.0],
        [0, 0],
        [0, 0.1]
    ])
    labels = ['A', 'A', 'B', 'B']
    return group, labels


# 4个参数分别为用于分类的输入向量inX, 输入的训练样本集为dataSet, 标签向量为labels， k为用于选择最近邻居的数目
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances ** 0.5    # 距离计算
    sortedDistIndicies = distances.argsort()
    classCount = {}
    for i in range(k):     # 选择距离最小的k个点
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


if __name__ == '__main__':
    group, labels = createDataSet()
    print(classify0([0, 0], group, labels, 3))    # 求[0, 0]的类别

 

输出：

B