def demo():
"""
Non-interactive demonstration of the clusterers with simple 2-D data.
"""
from nltk import cluster
# use a set of tokens with 2D indices
vectors = [
numpy.array(f)
for f in [[3, 3], [1, 2], [4, 2], [4, 0], [2, 3], [3, 1]]
]
# test the GAAC clusterer with 4 clusters
clusterer = cluster.GAAClusterer(4)
clusters = clusterer.cluster(vectors, True)
print 'Clusterer:', clusterer
print 'Clustered:', vectors
print 'As:', clusters
print
# show the dendrogram
clusterer.dendrogram().show()
# classify a new vector
vector = numpy.array([3, 3])
print 'classify(%s):' % vector,
print clusterer.classify(vector)
print
def main():
try:
f = open("small_clusters.dat", "r")
lines = f.read().splitlines()
f.close()
except IOError:
print("Couldn't find contexts file.")
sys.exit(-1)
# Load data to memory, this can take a while
contexts = []
for line in lines:
l = line.split()
values = []
word = l[0]
for v in l[1:]:
values.append(np.float32(v))
if any(values):
contexts.append((word, np.array(values)))
only_values = []
for elem in contexts:
only_values.append(elem[1])
print "Finish loading files."
# Begin clustering
clusterer = cluster.GAAClusterer(1000)
clusters = clusterer.cluster(only_values, True)
final_clusters = []
for i, elem in enumerate(clusters):
final_clusters.append((contexts[i][0], elem))
f = open("resultados_cluster.dat", "w")
for clus, group in groupby(final_clusters, itemgetter(1)):
print str(clus) + ":"
for word, clust in group:
s = set()
s.add(word)
for w in s:
print w
f.close()
print("Terminado procesamiento. Comenzando con input.")
lin = sys.stdin.read()
while lin:
lin = lin.strip().split()
for v in lin:
values.append(np.float32(v))
lin = np.array(values)
print(clusterer.classify(lin))
lin = sys.stdin.read()
def createCluster(data, cltype):
# pprint(data)
vectors = []
labels = []
for row in data:
rowval = []
labels = []
labelval = True
if row[1] == 'unfair':
labelval = False
labels.append(labelval)
for k, v in row[0].iteritems():
if k == 'hasPrivacy' or k == 'hasDeveloperEmail' or k == 'hasDeveloperWebsite':
v = int(bool(v))
rowval.append(v)
vectors.append(np.array(rowval))
pprint(vectors)
# vectors = np.asarray(vectors)
data = np.vstack(vectors)
means = [vectors[20].tolist(), vectors[21].tolist()]
if cltype == 'GAAC':
clusterer = cluster.GAAClusterer(num_clusters=4)
clusters = clusterer.cluster(vectors, True)
clusterer.dendrogram().show()
elif cltype == 'kmeans':
centroids, variance = vq.kmeans(data, 3)
identified, distance = vq.vq(data, centroids)
print identified
print centroids
print variance
elif cltype == 'hy':
# Creating a cluster of clusters function
def clusters(number=20, cnumber=5, csize=10):
# Note that the way the clusters are positioned is Gaussian randomness.
rnum = np.random.rand(cnumber, 2)
rn = rnum[:, 0] * number
rn = rn.astype(int)
rn[np.where(rn < 5)] = 5
rn[np.where(rn > number / 2.)] = round(number / 2., 0)
ra = rnum[:, 1] * 2.9
ra[np.where(ra < 1.5)] = 1.5
cls = np.random.randn(number, 3) * csize
# Random multipliers for central point of cluster
rxyz = np.random.randn(cnumber - 1, 3)
for i in xrange(cnumber - 1):
tmp = np.random.randn(rn[i + 1], 3)
x = tmp[:, 0] + (rxyz[i, 0] * csize)
y = tmp[:, 1] + (rxyz[i, 1] * csize)
z = tmp[:, 2] + (rxyz[i, 2] * csize)
tmp = np.column_stack([x, y, z])
cls = np.vstack([cls, tmp])
return cls
# Generate a cluster of clusters and distance matrix.
cls = clusters()
D = pdist(cls[:, 0:2])
D = squareform(D)
# Compute and plot first dendrogram.
fig = plt.figure(figsize=(8, 8))
ax1 = fig.add_axes([0.09, 0.1, 0.2, 0.6])
Y1 = hy.linkage(D, method='complete')
cutoff = 0.3 * np.max(Y1[:, 2])
Z1 = hy.dendrogram(Y1, orientation='right', color_threshold=cutoff)
ax1.xaxis.set_visible(False)
ax1.yaxis.set_visible(False)
# Compute and plot second dendrogram.
ax2 = fig.add_axes([0.3, 0.71, 0.6, 0.2])
Y2 = hy.linkage(D, method='average')
cutoff = 0.3 * np.max(Y2[:, 2])
Z2 = hy.dendrogram(Y2, color_threshold=cutoff)
ax2.xaxis.set_visible(False)
ax2.yaxis.set_visible(False)
# Plot distance matrix.
ax3 = fig.add_axes([0.3, 0.1, 0.6, 0.6])
idx1 = Z1['leaves']
idx2 = Z2['leaves']
D = D[idx1, :]
D = D[:, idx2]
ax3.matshow(D, aspect='auto', origin='lower', cmap=plt.cm.YlGnBu)
ax3.xaxis.set_visible(False)
ax3.yaxis.set_visible(False)
# Plot colorbar.
fig.savefig('scipy_352_ex1.pdf', bbox='tight')
print 'Means:', clusterer.means()
#print vectors
# classify a new vector
#vector = array([3, 3])
#print 'classify(%s):' % vector,
#print clusterer.classify(vector)
#print
#"""
print "GAAC Clustering"
# use a set of tokens with 2D indices
#vectors = [array(f) for f in [[3, 3], [1, 2], [4, 2], [4, 0], [2, 3], [3, 1]]]
# test the GAAC clusterer with 4 clusters
clusterer = cluster.GAAClusterer(2)
clusters = clusterer.cluster(vectors, True)
print 'Clusterer:', clusterer
#print 'Clustered:', vectors
print 'As:' # clusters
i = 2
for clst in clusters:
print i, clst
i = i + 1
# show the dendrogram
#print "The dendogram"
#clusterer.dendrogram().show()
# classify a new vector
#print "Classify the vector [3,3]"