knn分类鸢尾花纯python代码

下面是纯 Python 实现的 KNN 分类鸢尾花代码：

import csv
import random
import math

# 读取数据集
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)-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])

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

# 获取最近的邻居
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

# 获取最多的投票
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]

# 计算准确率
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

# 测试 KNN 算法
def main():
    # prepare data
    trainingSet=[]
    testSet=[]
    split = 0.67
    loadDataset('iris.data', 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)):
        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()

这段代码中，我们使用了欧氏距离来计算样本之间的距离，并使用投票法来确定测试样本所属的类别。