def ap(z):
sim_matrix = -squareform(pdist(z, 'euclidean'))
p = np.median(sim_matrix) * 1
center, labels = affinity_propagation(sim_matrix, p=p, verbose=True, max_iter=2000)
return labels
def ap(z):
sim_matrix = -squareform(pdist(z, 'euclidean'))
p = np.median(sim_matrix) * 1
center, labels = affinity_propagation(sim_matrix,
p=p,
verbose=True,
max_iter=2000)
return labels
def remove_duplicates(cc, sim_func=intersection_sim):
"""
Use affinity propagation to remove duplicate candidates.
"""
from scikits.learn.cluster import affinity_propagation
li = cc.keys()
sim_matrix = np.zeros((len(li), len(li)))
for i, e1 in enumerate(li):
for j, e2 in enumerate(li):
sim_matrix[i, j] = sim_func(e1, e2)
centers, _ = affinity_propagation(sim_matrix)
for i, e in enumerate(li):
if i not in centers:
del cc[e]
def remove_duplicates(cc, sim_func=intersection_sim):
"""
Use affinity propagation to remove duplicate candidates.
"""
from scikits.learn.cluster import affinity_propagation
li = cc.keys()
sim_matrix = np.zeros((len(li), len(li)))
for i, e1 in enumerate(li):
for j, e2 in enumerate(li):
sim_matrix[i,j] = sim_func(e1, e2)
centers, _ = affinity_propagation(sim_matrix)
for i, e in enumerate(li):
if i not in centers:
del cc[e]
################################################################################
X_norms = np.sum(X*X, axis=1)
S = - X_norms[:,np.newaxis] - X_norms[np.newaxis,:] + 2 * np.dot(X, X.T)
p = 12*np.median(S)
################################################################################
# Compute Affinity Propagation
################################################################################
#af = AffinityPropagation()
#af.fit(S, p)
#cluster_centers_indices = af.cluster_centers_indices_
#labels = af.labels_
#import affinity
cluster_centers_indices,labels=affinity_propagation(S,p)
n_clusters_ = len(cluster_centers_indices)
print 'Estimated number of clusters: %d' % n_clusters_
################################################################################
# Plot result
################################################################################
import pylab as pl
from itertools import cycle
pl.close('all')
pl.figure(1)
pl.clf()
'WAG' : 'Walgreen',
'HD' : 'Home Depot',
'GSK' : 'GlaxoSmithKline',
'PFE' : 'Pfizer',
'SNY' : 'Sanofi-Aventis',
'NVS' : 'Novartis',
'KMB' : 'Kimberly-Clark',
'R' : 'Ryder',
'GD' : 'General Dynamics',
'RTN' : 'Raytheon',
'CVS' : 'CVS',
'CAT' : 'Caterpillar',
'DD' : 'DuPont de Nemours',
}
symbols, names = np.array(symbol_dict.items()).T
quotes = [finance.quotes_historical_yahoo(symbol, d1, d2, asobject=True)
for symbol in symbols]
#volumes = np.array([q.volume for q in quotes]).astype(np.float)
open = np.array([q.open for q in quotes]).astype(np.float)
close = np.array([q.close for q in quotes]).astype(np.float)
variation = close - open
correlations = np.corrcoef(variation)
_, labels = cluster.affinity_propagation(correlations)
for i in range(labels.max()+1):
print 'Cluster %i: %s' % ((i+1),
', '.join(names[labels==i]))
charfeat.set_features(li)
#Get alphabet.
feats_train = StringUlongFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
#CommUlongStringKernel needs sorted features.
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
use_sign = False
#Compute kernel matrix between train features.
kernel = CommUlongStringKernel(feats_train, feats_train, use_sign)
km_train = kernel.get_kernel_matrix()
return km_train
if __name__ == "__main__":
li = read_reviews()
li = [" ".join(e) for e in li if e]
mat = get_kernel_matrix(li)
center, labels = affinity_propagation(mat)
li = np.array(li)
for i in range(len(center)):
sents = li[np.where(labels==i)]
for e in sents:
print e, "#",
print i, li[center[i]]
charfeat.set_features(li)
#Get alphabet.
feats_train = StringUlongFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
#CommUlongStringKernel needs sorted features.
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
use_sign = False
#Compute kernel matrix between train features.
kernel = CommUlongStringKernel(feats_train, feats_train, use_sign)
km_train = kernel.get_kernel_matrix()
return km_train
if __name__ == "__main__":
li = read_reviews()
li = [" ".join(e) for e in li if e]
mat = get_kernel_matrix(li)
center, labels = affinity_propagation(mat)
li = np.array(li)
for i in range(len(center)):
sents = li[np.where(labels == i)]
for e in sents:
print e, "#",
print i, li[center[i]]
