from sklearn import neighbors

from sklearn import datasets

knn = neighbors.KNeighborsClassifier()            #调用KNN分类器

iris = datasets.load_iris()                #载入iris数据集

print("featureList: " + "\n" + str(iris.data))

print("labelList: " + "\n" + str(iris.target))

knn.fit(iris.data, iris.target)  #将数据传入Knn分类器

predictedLabel = knn.predict([[0.1, 0.2, 0.3, 0.4]])       #进行预测

print ("predictedLabel is : " + str(predictedLabel))      #打印预测结果

 import csv

 import random

 import math

 import operator

 #载入数据集

 def loadDataset(filename, split, trainingSet=[], testSet=[]):

     with open (filename) 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:                        #通过split比较，随机将数据集分成训练集（占约三分之二）和测试集（占约三分之一）

                 trainingSet.append(dataset[x])

             else:

                 testSet.append(dataset[x])

 #计算任意两个实例间的欧氏距离

 def euclideanDistance(instance1, instance2, length):

     distance = 0

     for x in range(length):      #实现任意维度距离的计算

         distance += pow((instance1[x]-instance2[x]), 2)

     return math.sqrt(distance)

 #获取待测实例最临近的K个已知点

 def getNeighbors(trainingSet, testInstance, k):

     distances = []

     length = len(testInstance)-1

     for x in range(len(trainingSet)):

         dist = euclideanDistance(testInstance, trainingSet[x], length)           #计算每一个待测实例与已知实例的欧氏距离

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

     distances.sort(key=operator.itemgetter(1))  #list.sort(*, key=None, reverse=None)，sort()是Python列表的一个内置的排序方法，key是带一个参数的函数，返回一个值用来排序，默认为 None。reverse表示排序结果是否反转

     neighbors = []

     for x in range(k):

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

         return neighbors

 #每一个测试实例所对应的分类结果根据临近样本的结果进行获取（少数服从多数原则）

 def getResponse(neighbors):

     classVotes = {}

     for x in range(len(neighbors)):

         response = neighbors[x][-1]          #测试实例周围已知实例的结果获取

         if response in classVotes:

             classVotes[response] += 1

         else:

             classVotes[response] = 1

     sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)

     return sortedVotes[0][0]

 #测试集准确率的计算

 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 = 0.70

     loadDataset(r'irisdata.txt', split, trainingSet, testSet)            #数据集载入

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

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

     predictions = []

     k = 3               #选3个临近的样本点

     for x in range(len(testSet)):

         neighbors = getNeighbors(trainingSet, testSet[x], k)

         result = getResponse(neighbors)

         predictions.append(result)

         print('>predicted=' + repr(result) + ', actual=' + repr(testSet[x][-1]))

     accuracy = getAccuracy(testSet, predictions)

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

 if __name__ == '__main__':

     main()