knn分类鸢尾花纯python代码

以下是纯 Python 实现 KNN 分类鸢尾花数据集的代码：

import csv
import random
import math

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)-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)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist))
    distances.sort(key=lambda x: x[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.items(), key=lambda x: x[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():
    trainingSet=[]
    testSet=[]
    split = 0.67
    loadDataset('iris.data', split, trainingSet, testSet)
    print('Train set: ' + repr(len(trainingSet)))
    print('Test set: ' + repr(len(testSet)))
    predictions=[]
    k = 3
    for 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()

其中，`loadDataset` 函数将数据集文件读入内存，并将其随机拆分为训练集和测试集。`euclideanDistance` 函数计算两个实例之间的欧几里得距离。`getNeighbors` 函数找到测试实例的 k 个最近邻居。`getResponse` 函数根据最近邻居的类别投票，返回最终的类别。`getAccuracy` 函数计算测试集上的分类准确率。`main` 函数将所有代码组合起来，输出分类结果和准确率。