聚类分析K-Means三维坐标版Python设计实践分享

效果图

操作过程

1. Python源代码Kmeans

import csv

import matplotlib.pyplot as plt
import numpy as np
import xlrd2
from sklearn import preprocessing
from mpl_toolkits.mplot3d import Axes3D
# 标准化数据集 X
from xlsxwriter import worksheet


def normalize(X, axis=-1, p=2):
    lp_norm = np.atleast_1d(np.linalg.norm(X, p, axis))
    lp_norm[lp_norm == 0] = 1
    return X / np.expand_dims(lp_norm, axis)


# 计算一个样本与数据集中所有样本的欧氏距离的平方
def euclidean_distance(one_sample, X):
    one_sample = one_sample.reshape(1, -1)
    X = X.reshape(X.shape[0], -1)
    distances = np.power(np.tile(one_sample, (X.shape[0], 1)) - X, 2).sum(axis=1)
    return distances


class Kmeans():
    """Kmeans聚类算法.
    Parameters:
    -----------
    k: int
        聚类的数目.
    max_iterations: int
        最大迭代次数.
    varepsilon: float
        判断是否收敛, 如果上一次的所有k个聚类中心与本次的所有k个聚类中心的差都小于varepsilon,
        则说明算法已经收敛
    """

    def __init__(self, k=4, max_iterations=500, varepsilon=0.001):
        self.k = k
        self.max_iterations = max_iterations
        self.varepsilon = varepsilon

    # 从所有样本中随机选取self.k样本作为初始的聚类中心
    def