如何在Python中创建一个径向集群,如下面的代码示例?

时间:2011-02-23 09:28:11

标签: python numpy scipy cluster-analysis dendrogram

我已经找到了几个关于如何创建这些确切层次结构的示例(至少我相信它们是这样的),如下所示stackoverflow.com/questions/2982929/哪个很好用,几乎可以执行我正在寻找的内容。

[编辑]这是Paul代码的简化版本,现在应该更容易让某人帮助将其转换为径向集群而不是当前的集群形状

right structure, wrong display - needs to be a radial cluster

import scipy
import pylab
import scipy.cluster.hierarchy as sch

def fix_verts(ax, orient=1):
    for coll in ax.collections:
        for pth in coll.get_paths():
            vert = pth.vertices
            vert[1:3,orient] = scipy.average(vert[1:3,orient]) 

# Generate random features and distance matrix.
x = scipy.rand(40)
D = scipy.zeros([40,40])
for i in range(40):
    for j in range(40):
        D[i,j] = abs(x[i] - x[j])

fig = pylab.figure(figsize=(8,8))

# Compute and plot the dendrogram.
ax2 = fig.add_axes([0.3,0.71,0.6,0.2])
Y = sch.linkage(D, method='single')
Z2 = sch.dendrogram(Y)
ax2.set_xticks([])
ax2.set_yticks([])

fix_verts(ax2,0)
fig.savefig('test.png')

但是,我需要一个径向集群,而不是树状结构,如下图所示。

enter image description here radial cluster 1

4 个答案:

答案 0 :(得分:7)

我相信您可以使用networkx包与matplotlib一起使用此功能。请查看networkx图库中的以下示例:

http://networkx.lanl.gov/examples/drawing/circular_tree.html

一般来说,networkx有许多非常好的图形分析和绘图方法

enter image description here

答案 1 :(得分:6)

我添加了一个函数fix_verts,它在树形图中合并每个“U”底部的顶点。

试试这个:

import scipy
import pylab
import scipy.cluster.hierarchy as sch

def fix_verts(ax, orient=1):
    for coll in ax.collections:
        for pth in coll.get_paths():
            vert = pth.vertices
            vert[1:3,orient] = scipy.average(vert[1:3,orient]) 

# Generate random features and distance matrix.
x = scipy.rand(40)
D = scipy.zeros([40,40])
for i in range(40):
    for j in range(40):
        D[i,j] = abs(x[i] - x[j])


fig = pylab.figure(figsize=(8,8))

# Compute and plot first dendrogram.
ax1 = fig.add_axes([0.09,0.1,0.2,0.6])
Y = sch.linkage(D, method='centroid')
Z1 = sch.dendrogram(Y, orientation='right')
ax1.set_xticks([])
ax1.set_yticks([])

# Compute and plot second dendrogram.
ax2 = fig.add_axes([0.3,0.71,0.6,0.2])
Y = sch.linkage(D, method='single')
Z2 = sch.dendrogram(Y)
ax2.set_xticks([])
ax2.set_yticks([])

# Plot distance matrix.
axmatrix = fig.add_axes([0.3,0.1,0.6,0.6])
idx1 = Z1['leaves']
idx2 = Z2['leaves']
D = D[idx1,:]
D = D[:,idx2]
im = axmatrix.matshow(D, aspect='auto', origin='lower', cmap=pylab.cm.YlGnBu)
axmatrix.set_xticks([])
fix_verts(ax1,1)
fix_verts(ax2,0)
fig.savefig('test.png')

结果如下: enter image description here

我希望你就是这样。

答案 2 :(得分:5)

我已经研究了这个问题,现在似乎最好创建一个新函数来直接从radial cluster输出绘制linkage(而不是黑客绘制的那个)。我最终可能会做些什么,但很快就会没事。

我假设您的数据自然会承认这种径向嵌入。你验证了吗?在linkage中是否存在适合您目的的方法?

似乎任何方法linkage都会返回二叉树结构。在您的示例中,您有更多的常规树。您需要一些额外的知识来整合树节点。这一切都准备好了黑客攻击原始树状图的想法。

<强>更新
这个天真的例子情节是否足够合理地适合您的目的?如果是这样,我将能够发布一些非常简单的代码来实现它。 "Radial dendrogram"

更新2

以下是代码:

radial_demo.py

from numpy import r_, ones, pi, sort
from numpy.random import rand
from radial_grouper import tree, pre_order, post_order
from radial_visualizer import simple_link
from pylab import axis, figure, plot, subplot

# ToDo: create proper documentation
def _s(sp, t, o):
    subplot(sp)
    t.traverse(simple_link, order= o)
    axis('equal')

def demo1(n):
    p= r_[2* pi* rand(1, n)- pi, ones((1, n))]
    t= tree(p)
    f= figure()
    _s(221, t, pre_order)
    _s(222, t, post_order)
    t= tree(p, tols= sort(2e0* rand(9)))
    _s(223, t, pre_order)
    _s(224, t, post_order)
    f.show()
    # f.savefig('test.png')

# ToDO: implement more demos

if __name__ == '__main__':
    demo1(123)

radial_grouper.py

"""All grouping functionality is collected here."""
from collections import namedtuple
from numpy import r_, arange, argsort, array, ones, pi, where
from numpy import logical_and as land
from radial_support import from_polar

__all__= ['tree', 'pre_order', 'post_order']

Node= namedtuple('Node', 'ndx lnk')

# ToDo: enhance documentation
def _groub_by(p, tol, r):
    g, gm, gp= [], [], p- p[0]
    while True:
        if gp[-1]< 0: break
        ndx= where(land(0.<= gp, gp< tol))[0]
        if 0< len(ndx):
            g.append(ndx)
            gm.append(p[ndx].mean())
        gp-= tol
    return g, array([gm, [r]* len(gm)])

def _leafs(p):
    return argsort(p[0])

def _create_leaf_nodes(ndx):
    nodes= []
    for k in xrange(len(ndx)):
        nodes.append(Node(ndx[k], []))
    return nodes

def _link_and_create_nodes(_n, n_, cn, groups):
    nodes, n0= [], 0
    for k in xrange(len(groups)):
        nodes.append(Node(n_+ n0, [cn[m] for m in groups[k]]))
        n0+= 1
    return n_, n_+ n0, nodes

def _process_level(nodes, polar, p, tol, scale, _n, n_):
    groups, p= _groub_by(p, tol, scale* polar[1, _n])
    _n, n_, nodes= _link_and_create_nodes(_n, n_, nodes, groups)
    polar[:, _n: n_]= p
    return nodes, polar, _n, n_

def _create_tree(p, r0, scale, tols):
    if None is tols:
        tols= .3* pi/ 2** arange(5)[::-1]
    _n, n_= 0, p.shape[1]
    polar= ones((2, (len(tols)+ 2)* n_))
    polar[0, :n_], polar[1, :n_]= p[0], r0
    # leafs
    nodes= _create_leaf_nodes(_leafs(p))
    nodes, polar, _n, n_= _process_level(
    nodes, polar, polar[0, _leafs(p)], tols[0], scale, _n, n_)
    # links
    for tol in tols[1:]:
        nodes, polar, _n, n_= _process_level(
        nodes, polar, polar[0, _n: n_], tol, scale, _n, n_)
    # root
    polar[:, n_]= [0., 0.]
    return Node(n_, nodes), polar[:, :n_+ 1]

def _simplify(self):
    # ToDo: combine single linkages
    return self._root

def _call(self, node0, node1, f, level):
    f(self, [node0.ndx, node1.ndx], level)

def pre_order(self, node0, f, level= 0):
    for node1 in node0.lnk:
        _call(self, node0, node1, f, level)
        pre_order(self, node1, f, level+ 1)

def post_order(self, node0, f, level= 0):
    for node1 in node0.lnk:
        post_order(self, node1, f, level+ 1)
        _call(self, node0, node1, f, level)

class tree(object):
    def __init__(self, p, r0= pi, scale= .9, tols= None):
        self._n= p.shape[1]
        self._root, self._p= _create_tree(p, r0, scale, tols)

    def traverse(self, f, order= pre_order, cs= 'Cartesian'):
        self.points= self._p
        if cs is 'Cartesian':
            self.points= from_polar(self._p)
        order(self, self._root, f, 0)
        return self

    def simplify(self):
        self._root= _simplify(self)
        return self

    def is_root(self, ndx):
        return ndx== self._p.shape[1]- 1

    def is_leaf(self, ndx):
        return ndx< self._n

if __name__ == '__main__':
    # ToDO: add tests
    from numpy import r_, round
    from numpy.random import rand
    from pylab import plot, show

    def _l(t, n, l):
        # print round(a, 3), n, l, t.is_root(n[0]), t.is_leaf(n[1])
        plot(t.points[0, n], t.points[1, n])
        if 0== l:
            plot(t.points[0, n[0]], t.points[1, n[0]], 's')
        if t.is_leaf(n[1]):
            plot(t.points[0, n[1]], t.points[1, n[1]], 'o')

    n= 123
    p= r_[2* pi* rand(1, n)- pi, ones((1, n))]
    t= tree(p).simplify().traverse(_l)
    # t= tree(p).traverse(_l, cs= 'Polar')
    show()
    # print
    # t.traverse(_l, post_order, cs= 'Polar')

radial_support.py

"""All supporting functionality is collected here."""
from numpy import r_, arctan2, cos, sin
from numpy import atleast_2d as a2d

# ToDo: create proper documentation strings
def _a(a0, a1):
    return r_[a2d(a0), a2d(a1)]

def from_polar(p):
    """(theta, radius) to (x, y)."""
    return _a(cos(p[0])* p[1], sin(p[0])* p[1])

def to_polar(c):
    """(x, y) to (theta, radius)."""
    return _a(arctan2(c[1], c[0]), (c** 2).sum(0)** .5)

def d_to_polar(D):
    """Distance matrix to (theta, radius)."""
    # this functionality is to adopt for more general situations
    # intended functionality:
    # - embedd distance matrix to 2D
    # - return that embedding in polar coordinates
    pass

if __name__ == '__main__':
    from numpy import allclose
    from numpy.random import randn
    c= randn(2, 5)
    assert(allclose(c, from_polar(to_polar(c))))

    # ToDO: implement more tests

radial_visualizer.py

"""All visualization functionality is collected here."""
from pylab import plot

# ToDo: create proper documentation
def simple_link(t, ndx, level):
    """Simple_link is just a minimal example to demonstrate what can be
    achieved when it's called from _grouper.tree.traverse for each link.
    - t, tree instance
    - ndx, a pair of (from, to) indicies
    - level, of from, i.e. root is in level 0
    """
    plot(t.points[0, ndx], t.points[1, ndx])
    if 0== level:
        plot(t.points[0, ndx[0]], t.points[1, ndx[0]], 's')
    if t.is_leaf(ndx[1]):
        plot(t.points[0, ndx[1]], t.points[1, ndx[1]], 'o')

# ToDO: implement more suitable link visualizers
# No doubt, this will the part to burn most of the dev. resources

if __name__ == '__main__':
    # ToDO: implement tests
    pass

您可以找到源代码here。无论如何,请随时修改它,但请保持未来的修改与要点同步。

答案 3 :(得分:1)

Vegaexample非常类似于您的第一个图表。

enter image description here

您可以在其在线编辑器上进行游戏。超级酷,易于使用。