python实现k-means算法

聚类属于无监督学习，K-means算法是很典型的基于距离的聚类算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。该算法认为簇是由距离靠近的对象组成的，因此把得到紧凑且独立的簇作为最终目标。

下面来看看python实现k-means算法的详细代码吧：

# -*- coding:utf-8 -*-
import random

import numpy as np
from matplotlib import pyplot


class K_Means(object):
    # k是分组数；tolerance‘中心点误差'；max_iter是迭代次数
    def __init__(self, k=2, tolerance=0.0001, max_iter=300):
        self.k_ = k
        self.tolerance_ = tolerance
        self.max_iter_ = max_iter

    def fit(self, data):
        self.centers_ = {}
        for i in range(self.k_):
            self.centers_[i] = data[random.randint(0,len(data))]
        # print('center', self.centers_)
        for i in range(self.max_iter_):
            self.clf_ = {} #用于装归属到每个类中的点[k,len(data)]
            for i in range(self.k_):
                self.clf_[i] = []
            # print("质点:",self.centers_)
            for feature in data:
                distances = [] #装中心点到每个点的距离[k]
                for center in self.centers_:
                    # 欧拉距离
                    distances.append(np.linalg.norm(feature - self.centers_[center]))
                classification = distances.index(min(distances))
                self.clf_[classification].append(feature)

            # print("分组情况:",self.clf_)
            prev_centers = dict(self.centers_)

            for c in self.clf_:
                self.centers_[c] = np.average(self.clf_[c], axis=0)

            # '中心点'是否在误差范围
            optimized = True
            for center in self.centers_:
                org_centers = prev_centers[center]
                cur_centers = self.centers_[center]
                if np.sum((cur_centers - org_centers) / org_centers * 100.0) > self.tolerance_:
                    optimized = False
            if optimized:
                break

    def predict(self, p_data):
        distances = [np.linalg.norm(p_data - self.centers_[center]) for center in self.centers_]
        index = distances.index(min(distances))
        return index


if __name__ == '__main__':
    x = np.array([[1, 2], [1.5, 1.8], [5, 8], [8, 8], [1, 0.6], [9, 11]])
    k_means = K_Means(k=2)
    k_means.fit(x)
    for center in k_means.centers_:
        pyplot.scatter(k_means.centers_[center][0], k_means.centers_[center][1], marker='*', s=150)

    for cat in k_means.clf_:
        for point in k_means.clf_[cat]:
            pyplot.scatter(point[0], point[1], c=('r' if cat == 0 else 'b'))

    predict = [[2, 1], [6, 9]]
    for feature in predict:
        cat = k_means.predict(feature)
        pyplot.scatter(feature[0], feature[1], c=('r' if cat == 0 else 'b'), marker='x')

    pyplot.show()

到此这篇关于python实现k-means算法的文章就介绍到这了,更多相关python实现k-means算法内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！