KNN算法

from sklearn import neighbors
from sklearn import datasets #引入sklearn自有的数据样本库

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

iris = datasets.load_iris() #iris数据样本，通过花瓣四个部分的长度来判别花的种类

print(iris)

knn.fit(iris.data, iris.target) 

predictedLabel = knn.predict([[0.1, 0.2, 0.3, 0.4]])

print('predictedLabel:', predictedLabel)

'''
KNN分类算法的具体实现
'''
import csv
import random
import math
import operator

def loadDataset(filename, split, trainingSet=[], testSet=[] ): #函数的作用是利用split，将数据集分成训练集和测试集两部分
    with open(filename, 'r') as csvfile:  
        lines = csv.reader(csvfile) 
        print('type of lines:', type(lines)) #<class '_csv.reader'>
        dataset = list(lines)  #将数据集转换成list
        for x in range(len(dataset)):
            for y in range(4):
                dataset[x][y] = float(dataset[x][y])
            if random.random() < split: #random.random()在0到1中随机生成一个数
                trainingSet.append(dataset[x])
            else:
                testSet.append(dataset[x])

def euclideanDistance(instance1, instance2, length): #对length维的向量求解距离（距离之差的平方和再求根号）
    distance = 0
    for x in range(length):
        distance += pow((instance1[x] - instance2[x]), 2)
    return math.sqrt(distance)

def getNeighbors(trainingSet, testInstance, k ): #找出在训练集trainingSet中距离某个实例testInstance最近的K个点
    distances = []
    length = len(testInstance) - 1 
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist)) #将训练集中数据以及其距离测试实例的距离，加入distances list中
    distances.sort(key=operator.itemgetter(1))#将distances list中按照第1位数据，进行从小到大排列
    neighbors = []
    #print(repr(distances)) #[([4.3, 3.0, 1.1, 0.1, 'Iris-setosa'], 4.631414470763764),....]输出类似这样，但类型仍然是list
    for x in range(k):
        neighbors.append(distances[x][0]) #输出前K个
    return neighbors

def getResponse(neighbors):
    classVotes = {}
    for x in range(len(neighbors)):
        response = neighbors[x][-1]  #-1表示输出最后一个元素，即花的类别名字
        if response in classVotes:
            classVotes[response] += 1
        else:
            classVotes[response] = 1 #classVotes是一个字典，字典第一个元素是花的类别，第二个是在K个neighbors中该类花名出现的次数
    sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True) #按照出现的次数进行进行由大到小的排名 operator.itemgetter(1)对第1个元素由小到大排列，reverse=True表示翻转
    return sortedVotes[0][0]

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('irisData.txt', split, trainingSet, testSet)
    print('Train set:', len(trainingSet))
    print('Test set:', len(testSet))
    
    predictions = []
    k = 5
    for x in range(len(testSet)):
        neighbors = getNeighbors(trainingSet, testSet[x], k)
        result = getResponse(neighbors)
        predictions.append(result)
        print('>prediction=' + repr(result) + ',actual=' + repr(testSet[x][-1]))
    accuracy = getAccuracy(testSet, predictions)
    print('Accuracy:' + repr(accuracy) + '%')
    

if __name__ == "__main__":
    main()