python实现knn与调用第三方库

python实现法：

import csv
import random
import math
import operator

#载入数据集
def loadDataset(filename, split, trainingSet = [], testSet = []):
    with open(filename, 'r') as csvfile:
        lines = csv.reader(csvfile)
        dataset = list(lines)
  
        for x in range(len(dataset)):
            for y in range(4):
                dataset[x][y] = float(dataset[x][y]) #目的将str转换成数字
                # print (dataset[x][y])    
            if random.random() < split:
                trainingSet.append(dataset[x])
            else:
                testSet.append(dataset[x])
                

#返回两点距离
def euclideanDistance(instance1, instance2, length):
    distance = 0
    for x in range(length):
        distance += math.pow((instance1[x]-instance2[x]), 2)
    return math.sqrt(distance)

#获取邻居
def getNeighbors(trainingSet, testInstance, k):
    distances = []
    length = len(testInstance)-1
    for x in range(len(trainingSet)):
        #testinstance
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist)) #distances[traningSet[x]] = dist
        #distances.append(dist)
    distances.sort(key=operator.itemgetter(1))
    neighbors = []
    for x in range(k):
        neighbors.append(distances[x][0])
        return neighbors

#返回最大可能的Label
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.items(), key=operator.itemgetter(1), reverse=True)
    return sortedVotes[0][0]
classVotes = {'Iris-setosa':2}
sortedVotes = [('Iris-setosa',2)]

#得到精确度
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():
    #prepare data
    trainingSet = []
    testSet = []
    split = 0.67
    loadDataset(r'E:\python资料\2018Python大礼包\机器学习与深度学习视频教程\02_深度学习基础\代码与素材(1)\02KNN\iris_data.txt', split, trainingSet, testSet)
    print ('Train set: ' + repr(len(trainingSet)))
    print ('Test set: ' + repr(len(testSet)))
    #generate predictions
    predictions = []
    k = 3
    for x in range(len(testSet)):
        # trainingsettrainingSet[x]
        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()

调用sklearn:

from sklearn import neighbors
from sklearn import datasets
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,iris['target_names'][predictedLabel])

 

转载于:https://my.oschina.net/u/3786144/blog/1796731