# -*- coding: UTF-8 -*-

import math

import csv

import random

import operator

'''@author:hunter@time:2017.03.31'''

class KNearestNeighbor(object):

def __init__(self):

pass

def loadDataset(self,filename, split, trainingSet, testSet): # 加載數據集 split以某個值為界限分類train和test

with open(filename, 'r') as csvfile:

lines = csv.reader(csvfile) #讀取所有的行

dataset = list(lines) #轉化成列表

for x in range(len(dataset)-1):

for y in range(4):

dataset[x][y] = float(dataset[x][y])

if random.random() < split: # 將所有數據加載到train和test中

trainingSet.append(dataset[x])

else:

testSet.append(dataset[x])

def calculateDistance(self,testdata, traindata, length): # 計算距離

distance = 0 # length表示維度 數據共有幾維

for x in range(length):

distance += pow((testdata[x]-traindata[x]), 2)

return math.sqrt(distance)

def getNeighbors(self,trainingSet, testInstance, k): # 返回最近的k個邊距

distances = []

length = len(testInstance)-1

for x in range(len(trainingSet)): #對訓練集的每一個數計算其到測試集的實際距離

dist = self.calculateDistance(testInstance, trainingSet[x], length)

print('訓練集:{}-距離:{}'.format(trainingSet[x], dist))

distances.append((trainingSet[x], dist))

distances.sort(key=operator.itemgetter(1)) # 把距離從小到大排列

neighbors = []

for x in range(k): #排序完成后取前k個距離

neighbors.append(distances[x][0])

print(neighbors)

return neighbors

def getResponse(self,neighbors): # 根據少數服從多數，決定歸類到哪一類

classVotes = {}

for x in range(len(neighbors)):

response = neighbors[x][-1] # 統(tǒng)計每一個分類的多少

if response in classVotes:

classVotes[response] += 1

else:

classVotes[response] = 1

print(classVotes.items())

sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True) #reverse按降序的方式排列

return sortedVotes[0][0]

def getAccuracy(self,testSet, predictions): # 準確率計算

correct = 0

for x in range(len(testSet)):

if testSet[x][-1] == predictions[x]: #predictions是預測的和testset實際的比對

correct += 1

print('共有{}個預測正確，共有{}個測試數據'.format(correct,len(testSet)))

return (correct/float(len(testSet)))*100.0

def Run(self):

trainingSet = []

testSet = []

split = 0.75

self.loadDataset(r'testdata.txt', split, trainingSet, testSet) #數據劃分

print('Train set: ' + str(len(trainingSet)))

print('Test set: ' + str(len(testSet)))

#generate predictions

predictions = []

k = 3 # 取最近的3個數據

# correct = []

for x in range(len(testSet)): # 對所有的測試集進行測試

neighbors = self.getNeighbors(trainingSet, testSet[x], k) #找到3個最近的鄰居

result = self.getResponse(neighbors) # 找這3個鄰居歸類到哪一類

predictions.append(result)

# print(correct)

accuracy = self.getAccuracy(testSet,predictions)

print('Accuracy: ' + repr(accuracy) + '%')

if __name__ == '__main__':

a = KNearestNeighbor()

a.Run()

總結

以上是生活随笔為你收集整理的python数据分类_Python数据挖掘实践—KNN分类的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。