使用各个群集的外部坐标可视化群集

如何解决使用各个群集的外部坐标可视化群集

我想可视化群集。

通过使用以下代码：

import matplotlib.pyplot as plt
import matplotlib.patches as mpatches

X = np.array([[28,7],[36,5],[32,2],[56,8],[47,[50,100],[100,[26,59],[19,71],[75,9],[34,4],[28,1],[33,6]])
col = ['blue','green','c','m','y','k',"violet","indigo"]
ncluster = 2
kmeans = KMeans(n_clusters=ncluster,max_iter=500).fit(X)
y = kmeans.labels_
centroids = kmeans.cluster_centers_
clusters_centroids = dict()
clusters_radii = dict()
for cluster in range(ncluster):
    clusters_centroids[cluster] = list(
        zip(centroids[:,0],centroids[:,1]))[cluster]
    clusters_radii[cluster] = max([np.linalg.norm(np.subtract(
        i,clusters_centroids[cluster])) for i in zip(X[y == cluster,X[y == cluster,1])])

fig,ax = plt.subplots(1,figsize=(7,5))

def drawclusters():
    for i in range(ncluster):
        plt.scatter(X[y == i,X[y == i,s=100,c=col[i],label=f'Cluster {i + 1}')
        art = mpatches.Circle(
            clusters_centroids[i],clusters_radii[i],edgecolor=col[i],fill=False)
        ax.add_patch(art)
    plt.scatter(centroids[:,s=200,c='red',label='Centroids',marker='x')


drawclusters()
plt.legend()
plt.tight_layout()
plt.show()

我正在圈子：

但是我想使用类似于此点的点来可视化忽略我只需要可视化部分的数据部分（我需要形状）：

我需要python中的代码。 R中有一个功能 fviz_cluster 。

解决方法

您可以使用scipy.spatial.ConvexHull()创建每个群集的凸包。请注意，X[y == i]需要转换为新数组，因为ConvexHull()会将索引返回短数组。返回的点形成一个多边形。首先需要复制第一点以进行绘图，以包括封闭多边形的线段。

import matplotlib.pyplot as plt
import numpy as np
from sklearn.cluster import KMeans
from scipy.spatial import ConvexHull

def drawclusters(ax):
    for i in range(ncluster):
        points = X[y == i]
        ax.scatter(points[:,0],points[:,1],s=100,c=col[i],label=f'Cluster {i + 1}')
        hull = ConvexHull(points)
        vert = np.append(hull.vertices,hull.vertices[0])  # close the polygon by appending the first point at the end
        ax.plot(points[vert,points[vert,'--',c=col[i])
        ax.fill(points[vert,alpha=0.2)
    ax.scatter(centroids[:,centroids[:,s=200,c='red',label='Centroids',marker='x')

X = np.array([[28,7],[36,5],[32,2],[56,8],[47,[50,100],[100,[26,59],[19,71],[75,9],[34,4],[28,[33,6]])
col = ['blue','green']
ncluster = 2
kmeans = KMeans(n_clusters=ncluster,max_iter=500).fit(X)
y = kmeans.labels_
centroids = kmeans.cluster_centers_
fig,ax = plt.subplots(1,figsize=(7,5))
drawclusters(ax)
ax.legend()
plt.tight_layout()
plt.show()