2. 利用Python的机器学习库sklearn: SkLearnExample.pyfrom sklearn import neighbors
from sklearn import datasetsknn = neighbors.KNeighborsClassifier()iris = datasets.load_iris()print irisknn.fit(iris.data, iris.target)predictedLabel = knn.predict([[0.1, 0.2, 0.3, 0.4]])print predictedLabel3. KNN 实现Implementation:# Example of kNN implemented from Scratch in Pythonimport csv
import random
import math
import operatordef 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:trainingSet.append(dataset[x])else:testSet.append(dataset[x])def euclideanDistance(instance1, instance2, length):distance = 0for x in range(length):distance += pow((instance1[x] - instance2[x]), 2)return math.sqrt(distance)def getNeighbors(trainingSet, testInstance, k):distances = []length = len(testInstance)-1for 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 neighborsdef getResponse(neighbors):classVotes = {}for x in range(len(neighbors)):response = neighbors[x][-1]if response in classVotes:classVotes[response] += 1else:classVotes[response] = 1sortedVotes = sorted(classVotes.iteritems(), key=operator.itemgetter(1), reverse=True)return sortedVotes[0][0]def getAccuracy(testSet, predictions):correct = 0for x in range(len(testSet)):if testSet[x][-1] == predictions[x]:correct += 1return (correct/float(len(testSet))) * 100.0def main():# prepare datatrainingSet=[]testSet=[]split = 0.67loadDataset(r'D:\MaiziEdu\DeepLearningBasics_MachineLearning\Datasets\iris.data.txt', split, trainingSet, testSet)print 'Train set: ' + repr(len(trainingSet))print 'Test set: ' + repr(len(testSet))# generate predictionspredictions=[]k = 3for 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) + '%')main()