一、数据参考
二、代码
import numpy as np
import operator
def createDataSet():
"""
函数说明:创建数据集
Parameters:
None
Returns:
group - 数据集
labels - 分类标签
"""
group = np.array([[3, 104],
[2, 100],
[1, 81],
[101, 10],
[99, 5],
[98, 2],
[18, 90]])
labels = ['爱情片', '爱情片', '爱情片', '动作片', '动作片', '动作片', "未知"]
return group, labels
def classify0(inX, dataSet, labels, k):
"""
函数说明:kNN算法,分类器
Parameters:
inX - 用于分类的数据(测试集)(1*m向量)
dataSet - 用于训练的数据(训练集)(n*m向量array)
labels - 分类标准(n*1向量array)
k - kNN算法参数,选择距离最小的k个点
Returns:
sortedClassCount[0][0] - 分类结果
"""
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)
print("sortedClassCount:", sortedClassCount)
return sortedClassCount[0][0]
if __name__ == '__main__':
group, labels = createDataSet()
result = classify0([70, 5], group, labels, 3)
print(result)
result = classify0([9, 79], group, labels, 3)
print(result)
三、运行结果