一、數據參考
二、代碼
import numpy as np
import operator
def createDataSet():
"""
函數說明:創建數據集
Parameters:
None
Returns:
group - 數據集
labels - 分類標籤
"""
group = np.array([[3, 104],
[2, 100],
[1, 81],
[101, 10],
[99, 5],
[98, 2],
[18, 90]])
labels = ['愛情片', '愛情片', '愛情片', '動作片', '動作片', '動作片', "未知"]
return group, labels
def classify0(inX, dataSet, labels, k):
"""
函數說明:kNN算法,分類器
Parameters:
inX - 用於分類的數據(測試集)(1*m向量)
dataSet - 用於訓練的數據(訓練集)(n*m向量array)
labels - 分類標準(n*1向量array)
k - kNN算法參數,選擇距離最小的k個點
Returns:
sortedClassCount[0][0] - 分類結果
"""
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、運行結果