K-means算法对data中数据进行聚类分析

实验要求(data.txt)

（1）算法原理描述

（2）算法结构

（3）写出K-means具体功能函数（不能直接调用sklearn.cluster(Means)功能函数)

具体函数功能中返回值包括 数据类标签，类中心，输入包括：数据，类别数

（4）可视化画图，不同类数据采用不同颜色

（5）算法分析 类类方差，平均方差，不同初始点对聚类结果的影响？如何解决？

python代码

import numpy as np
from matplotlib import pyplot as plt

plt.rcParams['font.family'] = ['Microsoft YaHei']


class K_Means(object):
    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+19]

        for i in range(self.max_iter_):
            self.clf_ = {}
            for i in range(self.k_):
                self.clf_[i] = []

            for feature in data:
                distances = []
                for center in self.centers_:
                    distances.append(np.linalg.norm(feature - self.centers_[center]))
                classification = distances.index(min(distances))
                self.clf_[classification].append(feature)

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

            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


# 读取data.txt里面的值
data = np.loadtxt('data.txt', dtype=float, delimiter=" ")
X = data[..., 0]
Y = data[..., 1]

plt.title("散点图观察特诊")
plt.xlabel("X轴")
plt.ylabel("Y轴")
plt.plot(X, Y, 'ob')
plt.show()

if __name__ == '__main__':
    k_means = K_Means(k=4)
    k_means.fit(data)
    print(k_means.centers_)

    rgb = ['r', 'g', 'b', 'y']
    for center in k_means.centers_:
        plt.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]:
            plt.scatter(point[0], point[1], c=rgb[cat])

    plt.show()

实验截图

散点图

聚类分析图