【KNN】K最邻近法Python实现

py文件示例

import numpy as np
import operator


def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()     
    classCount = {}
    for i in range(k):
        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]


def createDataSet():
    group = np.array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels


def main():
    group, labels = createDataSet()
    result = classify0([0, 0], group, labels, 3)
    print(result)


if __name__ == '__main__':
    main()

ipynb文件示例

import numpy as np

dataSet = np.array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
labels = ['A', 'A', 'B', 'B']

dataSetSize = dataSet.shape[0]
print(dataSetSize)

inX = [0, 0]
k = 3
diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
print(diffMat)

sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()  
print(distances)
print(sortedDistIndicies)

classCount = {}
for i in range(k):
    voteIlabel = labels[sortedDistIndicies[i]]
    classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
print(classCount)
sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
print(sortedClassCount)

---