python实现knn分类算法

本文非原创，原博主地址

目的

原生python实现knn分类算法（使用鸢尾花数据集）

KNN算法核心思想就是，要确定测试样本属于哪一类，就寻找所有训练样本中与该测试样本“距离”最近的前K个样本，然后看这K个样本大部分属于哪一类，那么就认为这个测试样本也属于哪一类。简单的说就是让最相似的K个样本来投票决定。因此，实现 K 近邻算法时，主要考虑的问题是如何对训练数据进行快速 K 近邻搜索。

算法设计

源码展示

# -*- coding: utf-8 -*-
import string
import csv  # 用于处理csv文件
import random  # 用于随机数
import math
import operator  #


# 加载数据集
def loadDataset(filename, split, trainingSet=[], testSet=[]):
    dataset = []
    temp = []
    mid_temp = []

    for line in open(filename, "r"):
        temp.append(line)

    for i in temp:
        i = i[0:-2]
        mid_temp.append(i)

    for i in mid_temp:
        dataset.append(list(i.split(",")))


    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)


# 返回K个最近邻
def getNeighbors(trainingSet, testInstance, k):
    distances = []
    length = len(testInstance) - 1
    # 计算每一个测试实例到训练集实例的距离
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x], dist))
        # 对所有的距离进行排序
    distances.sort(key=operator.itemgetter(1))
    neighbors = []
    # 返回k个最近邻
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors


# 对k个近邻进行合并，返回value最大的key
def getResponse(neighbors):
    class_votes = {}
    for x in range(len(neighbors)):
        response = neighbors[x][-1]
        if response in class_votes:
            class_votes[response] += 1
        else:
            class_votes[response] = 1
            # 排序
    sorted_votes = sorted(class_votes.items(), key=lambda x: x[1], reverse=True)
    return sorted_votes[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


def main():
    trainingSet = []  # 训练数据集
    testSet = []  # 测试数据集
    split = 0.67# 分割的比例
    loadDataset(r"iris.txt", 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) + "%")


if __name__ == "__main__":
    main()

结果展示