python实现k-means聚类

注释都在代码里了，就不细说。

聚类的数据集和提取的matlab代码会放在最后

import numpy as np
import matplotlib.pyplot as plt
import numpy.random as random
from scipy.io import loadmat
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans


class readData:
    def __init__(self, data_path='./data.mat'):
        # 读取数据集
        self.data = loadmat(data_path)

    def get_data(self):
        X = self.data['X']
        y = []
        j = 0
        for i in range(len(X)):
            y.append(j)
            if (i + 1) % 200 == 0:
                j = j + 1
        y = np.array(y)
        return X, y

    def plotData(self):
        X, y = self.get_data()
        plt.scatter(X[:, 0], X[:, 1])
        plt.show()
        return 1


class Kmeans:
    def __init__(self, data, k):
        """
        初始化
        :param data: 输入数据
        :param k: 输入要类别数量
        """
        self.data = data
        self.k = k
        self.pred_label = None
        self.skl_pre_label = None
        self.center = None

    def sklearn_kmeans(self):
        """
        使用sklearn中的k-means聚类
        :return: sk_label
        """
        skl_kmean = KMeans(self.k, random_state=1)
        skl_label = skl_kmean.fit(self.data).labels_
        # print(skl_label)
        self.skl_pre_label = skl_label
        return skl_label

    def k_means(self):
        """
        自己的k_means
        :ret