Python K-Means 聚类算法实现

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[i]
        for i in range(self.max_iter_):
            self.clf_ = {}
            for i in range(self.k_):
                self.clf_[i] = []
            # print("质点:",self.centers_)
            for feature in data:
                # distances = [np.linalg.norm(feature-self.centers[center]) for center in self.centers]
                distances = []
                for center in self.centers_:
                    # 欧拉距离
                    # np.sqrt(np.sum((features-self.centers_[center])**2))
                    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]])
    ########## Begin ##########
    # 把数据点分为两组（非监督学习）
    k_means = K_Means(k=2)
    k_means.fit(x)
    ########## End ##########
    #打印两组数据的”中心点”
    print(k_means.centers_)

    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(predict)
        pyplot.scatter(feature[0], feature[1], c=('r' if cat == 0 else 'b'), marker='x')
    pyplot.show()
    pyplot.savefig('/data/workspace/myshixun/step2/picture1/pic1.jpg')