机器学习笔记——Nearest Neighbors

最近邻 Nearest Neighbors

1、利用自带鸢尾花数据简单实现最近邻算法

from sklearn import neighbors
from sklearn import datasets

# ##执行k最近邻的分类器
knn = neighbors.KNeighborsClassifier()
# ##加载鸢尾花数据集
iris = datasets.load_iris()

# print iris
# ##使用X作为训练数据拟合模型，y作为目标值
knn.fit(iris.data,iris.target)
# ##预测提供的数据的类标签
predictedLabel = knn.predict([[0.1,0.2,0.3,0.4]])
print predictedLabel
print iris.target_names[predictedLabel]

预测[萼片长，萼片宽度，花瓣长度，花瓣宽度]分别为[0.1,0.2,0.3,0.4]（cm）对应的类型
打印结果为：

[0]
['setosa']

即setosa花：

2、独立实现最近邻算法
利用鸢尾花数据集进行测试

#!/usr/bin/python
# -*- coding: utf-8 -*-

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:
                # ##将数据添加到训练集数据中
                trainingSet.append(dataset[x])
            else:
                # ##将数据添加到测试集数据中
                testSet.append(dataset[x])

# ##传入两个实例即其维度，输出两者之间的距离
def euclideanDistance(instance1,instance2,length):
    distances = 0
    for x in range(length):
        # ##对实例的每个维度进行做差并求所有维度的平方和
        distances += pow((instance1[x]-instance2[x]),2)
    return math.sqrt(distances)

# ##从训练集中选出和实例testInstance最邻近的k个实例
def getNeighobors(trainingSet,testInstance,k):
    distances = []
    # #计算testInstance的维度
    length = len(testInstance)-1
    # ##计算每一个实例和testInstance的距离
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        # #存储所有计算出的距离
        distances.append((trainingSet[x], dist))
    # #将计算出的距离进行排序
    distances.sort(key=operator.itemgetter(1))
    neighbors = []
    for x in range(k):
        # #取前k个距离
        neighbors.append(distances[x][0])
    return neighbors


# #统计每一个分类投票的多少
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
    # #按降序排列
    sortedVotes = sorted(classVotes.iteritems(),key=operator.itemgetter(1),reverse=True)
    # #返回投票最多的类别
    return sortedVotes[0][0]


# ##输出预测正确率
def getAccuracy(testSet,predictions):
    #  ##初始化预测正确的个数为0
    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 = []
    # #设定区分界限
    split = 0.67
    # #加载数据，传入空的训练集和测试集
    loadDataset(r'irisdata.txt', split, trainingSet, testSet)

    print 'Train set:' + repr(len(trainingSet))
    print 'Test set:' + repr(len(testSet))
    predictions = []
    # ##取最近的3个
    k = 3
    for x in range(len(testSet)):
        # #对每个测试集中的实例都照到其邻居
        neighbors = getNeighobors(trainingSet,testSet[x],k)

        result = getResponse(neighbors)
        predictions.append(result)
        print '>predicted='+repr(result)+',actual='+repr(testSet[x][-1])
    # #传入测试集以及预测值，计算预测百分比
    accuracy = getAccuracy(testSet,predictions)
    print 'Accuracy:'+repr(accuracy)+'%'

main()

输出：

Train set:100
Test set:50
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-setosa',actual='Iris-setosa'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-virginica',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-versicolor',actual='Iris-versicolor'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
>predicted='Iris-virginica',actual='Iris-virginica'
Accuracy:98.0%

则最终预测正确率为98.0%

---