首先是直接调用sklearn库里面KNN相关的函数使用KNN算法。
数据集采用datasets中的iris,iris是常用的分类实验数据集。
from sklearn import neighbors
#邻近算法的包
from sklearn import datasets
#导入数据集
knn = neighbors.KNeighborsClassifier()
iris = datasets.load_iris()
#print iris
knn.fit(iris.data, iris.target)
predictedLabel = knn.predict([0.1,0.2,0.3,0.4])
print predictedLabel
直接调用sklearn中的KNN算法很简单,下面用Python自己实现以下。
import csv
import random
import math
import operator
#载入dataset,将其按split比例分为训练集和测试集装入trainingSet[]和testSet[]中
def loadDataset(filename, split, trainingSet=[], testSet=[]):
with open(filename, 'rb') as csvfile:
lines = csv.reader(csvfile)
dataset = list(lines)
for x in range(len(dataset)-1):
for y in range(4):
dataset[x][y] = float(dataset[x][y])
if random.random()>=split:
testSet.append(dataset[x])
else:
trainingSet.append(dataset[x])
#计算两个length维实例的距离,运用math中的函数,将结果返回
def euclideanDistance(instance1, instance2, length):
distance = 0
for x in range(length):
distance += pow((instance1[x] - instance2[x]), 2)
return math.sqrt(distance)
#将训练集和需要测试的样例和K传入,得到与测试样例最近的k个样例,将其类型放入neighbors[]中,返回neighbors
def getNeighbors(trainingSet, testInstance, k):
distances = []
length = len(testInstance)-1
for x in range(len(trainingSet)):
dist = euclideanDistance(testInstance, trainingSet[x], length)
distances.append((trainingSet[x], dist))
distances.sort(key = operator.itemgetter(1))
neighbors = []
for x in range (k):
neighbors.append(distances[x][0])
return neighbors
#用一个字典classVotes,以少数服从多数,将类型最多的一种结果返回
def getResponse(neighbors):
classVotes = {}
for x in range(len(neighbors)):
response = neighbors[x][-1]
if response in classVotes:
classVotes[response] += 1
else:
classVotes[response] = 1
sortedVotes = sorted(classVotes.iteritems(), key = operator.itemgetter(1), reverse = True)
#降序排列
return sortedVotes[0][0]
#将测试集列表和预测结果列表传入,一一比对,对测试的正确率进行计算返回结果
def getAccuracy(testSet, predictions):
correct = 0
for x in range(len(testSet)):
if testSet[x][-1] == predictions[x]:
correct += 1
return (correct/float(len(testSet))) * 100.0
def main():
trainingSet = []
testSet = []
split = 0.67
loadDataset(r'D:\irisdata.txt', split, trainingSet, testSet)
#导入iris数据集的txt文件
print 'Train set:' + repr(len(trainingSet))
print 'Test set:' + repr(len(testSet))
predictions = []
k = 3
for x in range(len(testSet)):
neighbors = getNeighbors(trainingSet, testSet[x], k)
result = getResponse(neighbors)
predictions.append(result)
print('> predicted=' + repr(result) + ', octual=' + repr(testSet[x][-1]))
accuracy = getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')
#调用自定义的函数进行实践打印结果
main()