k-近鄰算法入門代碼

代碼

from numpy import *
import operator


# 構造四個點的座標
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個參數分別爲用於分類的輸入向量inX, 輸入的訓練樣本集爲dataSet, 標籤向量爲labels， k爲用於選擇最近鄰居的數目
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    # 距離計算
    sortedDistIndicies = distances.argsort()
    classCount = {}
    for i in range(k):     # 選擇距離最小的k個點
        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]的類別

 

輸出：

B