ML基础---KNN的应用

算法详述

     步骤：

     为了判断未知实例的类别，以所有已知类别的实例作为参照

     选择参数K

     计算未知实例与所有已知实例的距离

     选择最近K个已知实例

     根据少数服从多数的投票法则(majority-voting)，让未知实例归类为K个最邻近样本中最多数的类别

     细节:

     关于K

     关于距离的衡量方法:

         Euclidean Distance 定义

数据集采用Iris数据集，

下面是直接调用sklearn的库进行KNN的分类：

from sklearn import neighbors
from sklearn import datasets

knn = neighbors.KNeighborsClassifier()

iris = datasets.load_iris()
# save data
# f = open("iris.data.csv", 'wb')
# f.write(str(iris))
# f.close()

print iris

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

predictedLabel = knn.predict([[0.1, 0.2, 0.3, 0.4]])
print "hello"
#print ("predictedLabel is :" + predictedLabel)
print predictedLabel

如果自己实现KNN的代码，那么代码如下所示：

import csv
import random
import math
import operator


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:
                trainingSet.append(dataset[x])
            else:
                testSet.append(dataset[x])


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


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.append(dist)
    distances.sort(key=operator.itemgetter(1))
    neighbors = []
    for x in range(k):
        neighbors.append(distances[x][0])
        return neighbors


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)
    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():
    #prepare data
    trainingSet = []
    testSet = []
    split = 0.67
    loadDataset('irisdata.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()