# inspired by http://scikit-
# learn.org/dev/auto_examples/cluster/plot_kmeans_digits.html#example-
# cluster-plot-kmeans-digits-py
import os
import scipy as sp
from scipy.stats import norm
from matplotlib import pylab
from sklearn.cluster import KMeans

seed = 2
sp.random.seed(seed)  # to reproduce the data later on
num_clusters = 3

def plot_clustering(x, y, title, mx=None, ymax=None, xmin=None, km=None):
    pylab.figure(num=None, figsize=(8, 6))
    if km:
        pylab.scatter(x, y, s=50, c=km.predict(list(zip(x, y))))
    else:
        pylab.scatter(x, y, s=50)

    pylab.title(title)
    pylab.xlabel("Occurrence word 1")
    pylab.ylabel("Occurrence word 2")
    # pylab.xticks([w*7*24 for w in range(10)], ['week %i'%w for w in range(10)])
    pylab.autoscale(tight=True)
    pylab.ylim(ymin=0, ymax=1)
    pylab.xlim(xmin=0, xmax=1)
    pylab.grid(True, linestyle='-', color='0.75')
    return pylab

xw1 = norm(loc=0.3, scale=.15).rvs(20)
yw1 = norm(loc=0.3, scale=.15).rvs(20)

xw2 = norm(loc=0.7, scale=.15).rvs(20)
yw2 = norm(loc=0.7, scale=.15).rvs(20)

xw3 = norm(loc=0.2, scale=.15).rvs(20)
yw3 = norm(loc=0.8, scale=.15).rvs(20)

x = sp.append(sp.append(xw1, xw2), xw3)
y = sp.append(sp.append(yw1, yw2), yw3)

i = 1
plot_clustering(x, y, "Vectors")
pylab.savefig(os.path.join("..", "1400_03_0%i.png" % i))
#pylab.show()
pylab.clf()

i += 1
#################### 1 iteration ####################

mx, my = sp.meshgrid(sp.arange(0, 1, 0.001), sp.arange(0, 1, 0.001))

km = KMeans(init='random', n_clusters=num_clusters, verbose=1,
            n_init=1, max_iter=1,
            random_state=seed)

km.fit(sp.array(list(zip(x, y))))
print(len(sp.array(list(zip(x, y)))))
#print(sp.array(list(zip(x, y))))

Z = km.predict(sp.c_[mx.ravel(), my.ravel()]).reshape(mx.shape)

plot_clustering(x, y, "Clustering iteration 1", km=km)
pylab.imshow(Z, interpolation='nearest',
           extent=(mx.min(), mx.max(), my.min(), my.max()),
           cmap=pylab.cm.Blues,
           aspect='auto', origin='lower')

c1a, c1b, c1c = km.cluster_centers_
pylab.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
            marker='x', linewidth=2, s=100, color='black')
pylab.savefig(os.path.join("..", "1400_03_0%i.png" % i))
#pylab.show()
pylab.clf()

i += 1

#################### 2 iterations ####################
km = KMeans(init='random', n_clusters=num_clusters, verbose=1,
            n_init=1, max_iter=2,
            random_state=seed)
km.fit(sp.array(list(zip(x, y))))

Z = km.predict(sp.c_[mx.ravel(), my.ravel()]).reshape(mx.shape)

plot_clustering(x, y, "Clustering iteration 2", km=km)
pylab.imshow(Z, interpolation='nearest',
           extent=(mx.min(), mx.max(), my.min(), my.max()),
           cmap=pylab.cm.Blues,
           aspect='auto', origin='lower')

c2a, c2b, c2c = km.cluster_centers_
pylab.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
            marker='x', linewidth=2, s=100, color='black')
# import pdb;pdb.set_trace()
pylab.gca().add_patch(
    pylab.Arrow(c1a[0], c1a[1], c2a[0] - c1a[0], c2a[1] - c1a[1], width=0.1))
pylab.gca().add_patch(
    pylab.Arrow(c1b[0], c1b[1], c2b[0] - c1b[0], c2b[1] - c1b[1], width=0.1))
pylab.gca().add_patch(
    pylab.Arrow(c1c[0], c1c[1], c2c[0] - c1c[0], c2c[1] - c1c[1], width=0.1))

pylab.savefig(os.path.join("..", "1400_03_0%i.png" % i))
pylab.clf()

i += 1

#################### 3 iterations ####################
km = KMeans(init='random', n_clusters=num_clusters, verbose=1,
            n_init=1, max_iter=10,
            random_state=seed)
km.fit(sp.array(list(zip(x, y))))

Z = km.predict(sp.c_[mx.ravel(), my.ravel()]).reshape(mx.shape)

plot_clustering(x, y, "Clustering iteration 10", km=km)
pylab.imshow(Z, interpolation='nearest',
           extent=(mx.min(), mx.max(), my.min(), my.max()),
           cmap=pylab.cm.Blues,
           aspect='auto', origin='lower')

pylab.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
            marker='x', linewidth=2, s=100, color='black')
pylab.savefig(os.path.join("..", "1400_03_0%i.png" % i))
pylab.clf()

i += 1
 

在20newsgroup上進行文件匹配

rel_post_mlcomp.py