kNN演算法及其python實現

1、knn演算法原理

k近鄰（k-nearest neighbor）是比較簡單的機器學習演算法，它通過計算向量（特徵值）間的距離衡量相似度來進行分類。它的思想很簡單：如果乙個樣本在特徵空間中的k個最近鄰（最相似）的樣本中的大多數屬於某一類別，則該樣本也屬於這個類別。說白了就是一句話：對某個樣本，與他最相似的k個樣本屬於哪一類，它就屬於哪一類。

2、knn的python實現（進行文字分類）

a、準備資料

準備資料，儲存在nbayes_lib.py中

import numpy as np

from numpy import *
defloaddataset
():                postinglist = [['my','dog','has','flea','problems','help','help','please'],
['maybe','not','take','him','to','dog','park','stupid'],
['my','dalmation','is','so','cute','i','love','him','my'],
['stop','posting','stupid','workless','garbage'],
['mr','licks','ate','my','steak','how','to','stop','him'],
['quit','buying','worthless','dog','food','stupid']]
classvec = [0,1,0,1,0,1]
return postinglist,classvec
class
nbayes
(object):
def__init__
(self):
self.vocabulary = 
self.idf = 0
self.tf = 0
self.tdm = 0
self.pcates = {}
self.labels = 
self.doclength = 0
self.vocablen = 0
self.testset = 0
deftrain_set
(self, trainset,classvec):
self.cate_prob(classvec)
self.doclength = len(trainset)
tempset = set()
[tempset.add(word) for doc in trainset for word in doc]
self.vocabulary = list(tempset)
self.vocablen = len(self.vocabulary)
self.calc_wordfreq(trainset)
self.build_tdm()
defcate_prob
(self,classvec):
self.labels = classvec
labeltemps = set(self.labels)
for labeltemp in labeltemps:
self.pcates[labeltemp] = float(self.labels.count(labeltemp)) / float(len(self.labels))
defcalc_wordfreq
(self,trainset):
self.idf = np.zeros([1,self.vocablen])
self.tf = np.zeros([self.doclength,self.vocablen])
for indx in range(self.doclength):
for word in trainset[indx]:
self.tf[indx,self.vocabulary.index(word)]+=1
for signleword in set(trainset[indx]):
self.idf[0,self.vocabulary.index(signleword)]+=1
defbuild_tdm
(self):
self.tdm = np.zeros([len(self.pcates),self.vocablen])
sumlist = np.zeros([len(self.pcates),1])
for indx in range(self.doclength):
self.tdm[self.labels[indx]]+= self.tf[indx]
sumlist[self.labels[indx]]=np.sum(self.tdm[self.labels[indx]])
self.tdm = self.tdm/sumlist
defmap2vocab
(self,testdata):
self.testset = np.zeros([1,self.vocablen])
for word in testdata:
self.testset[0,self.vocabulary.index(word)] +=1
defpredict
(self,testset):
if np.shape(testset)[1] !=self.vocablen:
print('輸入錯誤')
exit(0)
predvalue = 0
predclass = ""
for tdm_vect,keyclass in zip(self.tdm,self.pcates):
temp = np.sum(testset*tdm_vect*self.pcates[keyclass])
if temp > predvalue:
predvalue = temp
predclass = keyclass
return predclass
defcalc_tfidf
(self,trainset):
self.idf = np.zeros([1,self.vocablen])
self.tf = np.zeros([self.doclength,self.vocablen])
for indx in range(self.doclength):
for word in trainset[indx]:
self.tf[indx,self.vocabulary.index(word)]+=1
self.tf[indx] = self.tf[indx]/float(len(trainset[indx]))
for signleword in set(trainset[indx]):
self.idf[0,self.vocabulary.index(signleword)]+=1
self.idf = np.log(float(self.doclength)/self.idf)
self.tf = np.multiply(self.tf,self.idf)

import sys

import os
from numpy import *
import numpy as np
import operator
from nbayes_lib import *
import importlib
importlib.reload(sys)
k=3def
cosdist
(v1,v2):
return np.dot(v1,v2) / (linalg.norm(v1)*linalg.norm(v2))
defclassify
(testdata,traindata,listclass,k):
datasetsize = traindata.shape[0]    #返回樣本的行數，就是樣本的個數
distance = array(zeros(datasetsize))
for indx in range(datasetsize):      #計算測試集與訓練集之間的距離
distance[indx] = cosdist(testdata,traindata[indx])
sorteddistindicies = argsort(-distance)
#print(sorteddistindicies)
classcount = {}
for i in np.arange(k):     #獲取角度最小的前k項作為參考項
voteilabel = listclass[sorteddistindicies[i]]
classcount[voteilabel] = classcount.get(voteilabel,0) + 1
#print(classcount)
sortedclasscount = sorted(classcount.items(),key=operator.itemgetter(1),reverse = true)
return sortedclasscount[0][0]
dataset,listclasses = loaddataset()
print('資料集是')
print(dataset)
print('label是：')
print(listclasses)
nb = nbayes()
nb.train_set(dataset,listclasses)
print('tf[3]是：')
print(nb.tf[3])
print('tf是')
print(nb.tf)
print(classify(nb.tf[3],nb.tf,listclasses,k))

Python實現KNN演算法

from numpy import import operator def creatdataset group array 1.0,1.1 1.0,1.0 0,0 0,0.1 lables a a b b return group,lables def classify0 inx,dataset,...

python實現knn演算法

importnumpyasnp importoperator defcreatedataset group np.array 1.0 1.1 1.0 1.0 0.0 0.0 0.0 0.1 labels a a b b returngroup,labels 分類演算法 inx待分類的點 defcla...

python實現KNN演算法

具體 如下 import numpy as np import matplotlib.pyplot as plt class myknn def init self,k self.k k def compute self,x train,y train,x test dist i 0 計算歐式距離 ...