2.1爱情片动作片的分类算法实践
import numpy as np
import operator
def createDataSet():
group = np.array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]])
labels = ['爱情片','爱情片','爱情片','动作片','动作片','动作片']
return group, labels
"""
Parameters:
inX - 用于分类的数据(测试集)
dataSet - 用于训练的数据(训练集)
labes - 分类标签
k - kNN算法参数,选择距离最小的k个点
Returns:
sortedClassCount[0][0] - 分类结果
"""
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
sortedDistIndices = distances.argsort()
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDistIndices[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()
test = [101,20]
test_class = classify0(test, group, labels, 3)
print(test_class)
代码来源可参考https://github.com/TeFuirnever/Machine-Learning-in-Action