CoCalc Shared Filesanaconda-python.htmlOpen in CoCalc with one click!
Authors: Jennifer Balakrishnan, JMM2016 Booth, Harald Schilly, William A. Stein
Views : 36
Description: Jupyter html version of anaconda-python.ipynb
anaconda-python
In [2]:
%matplotlib inline
In [3]:
import time as time
import numpy as np
import scipy as sp
import matplotlib.pyplot as plt
from sklearn.feature_extraction.image import grid_to_graph
from sklearn.cluster import AgglomerativeClustering

###############################################################################
# Generate data
lena = sp.misc.lena()
# Downsample the image by a factor of 4
lena = lena[::2, ::2] + lena[1::2, ::2] + lena[::2, 1::2] + lena[1::2, 1::2]
X = np.reshape(lena, (-1, 1))

###############################################################################
# Define the structure A of the data. Pixels connected to their neighbors.
connectivity = grid_to_graph(*lena.shape)

###############################################################################
# Compute clustering
print("Compute structured hierarchical clustering...")
st = time.time()
n_clusters = 15  # number of regions
ward = AgglomerativeClustering(n_clusters=n_clusters,
        linkage='ward', connectivity=connectivity).fit(X)
label = np.reshape(ward.labels_, lena.shape)
print("Elapsed time: ", time.time() - st)
print("Number of pixels: ", label.size)
print("Number of clusters: ", np.unique(label).size)

###############################################################################
# Plot the results on an image
plt.figure(figsize=(5, 5))
plt.imshow(lena, cmap=plt.cm.gray)
for l in range(n_clusters):
    plt.contour(label == l, contours=1,
                colors=[plt.cm.spectral(l / float(n_clusters)), ])
plt.xticks(())
plt.yticks(())
plt.show()
Compute structured hierarchical clustering...
Elapsed time:  8.225772380828857
Number of pixels:  65536
Number of clusters:  15
In [4]:
import time as time
import numpy as np
import matplotlib.pyplot as plt
import mpl_toolkits.mplot3d.axes3d as p3
from sklearn.cluster import AgglomerativeClustering
from sklearn.datasets.samples_generator import make_swiss_roll

###############################################################################
# Generate data (swiss roll dataset)
n_samples = 1500
noise = 0.05
X, _ = make_swiss_roll(n_samples, noise)
# Make it thinner
X[:, 1] *= .5

###############################################################################
# Compute clustering
print("Compute unstructured hierarchical clustering...")
st = time.time()
ward = AgglomerativeClustering(n_clusters=6, linkage='ward').fit(X)
elapsed_time = time.time() - st
label = ward.labels_
print("Elapsed time: %.2fs" % elapsed_time)
print("Number of points: %i" % label.size)

###############################################################################
# Plot result
fig = plt.figure()
ax = p3.Axes3D(fig)
ax.view_init(7, -80)
for l in np.unique(label):
    ax.plot3D(X[label == l, 0], X[label == l, 1], X[label == l, 2],
              'o', color=plt.cm.jet(np.float(l) / np.max(label + 1)))
plt.title('Without connectivity constraints (time %.2fs)' % elapsed_time)


###############################################################################
# Define the structure A of the data. Here a 10 nearest neighbors
from sklearn.neighbors import kneighbors_graph
connectivity = kneighbors_graph(X, n_neighbors=10, include_self=False)

###############################################################################
# Compute clustering
print("Compute structured hierarchical clustering...")
st = time.time()
ward = AgglomerativeClustering(n_clusters=6, connectivity=connectivity,
                               linkage='ward').fit(X)
elapsed_time = time.time() - st
label = ward.labels_
print("Elapsed time: %.2fs" % elapsed_time)
print("Number of points: %i" % label.size)

###############################################################################
# Plot result
fig = plt.figure()
ax = p3.Axes3D(fig)
ax.view_init(7, -80)
for l in np.unique(label):
    ax.plot3D(X[label == l, 0], X[label == l, 1], X[label == l, 2],
              'o', color=plt.cm.jet(float(l) / np.max(label + 1)))
plt.title('With connectivity constraints (time %.2fs)' % elapsed_time)

plt.show()
Compute unstructured hierarchical clustering...
Elapsed time: 0.82s
Number of points: 1500
Compute structured hierarchical clustering...
Elapsed time: 0.18s
Number of points: 1500
In [ ]: