def _fit_vbgmm(self, x):
# clustering
for c in xrange(len(self.crange)):
k = self.crange[c]
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (
self.clus_type, self.crange[c], r + 1),
idx = c * self.repeats + r
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
model = VBGMM(n_components=k, covariance_type=self.cvtype,
**model_kwargs)
model.n_features = self.input_dim
fit_kwargs = {}
if 'max_iter' in self.clus_kwargs:
fit_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model.fit(x, params='wmc', init_params='wmc', **fit_kwargs)
self._labels[idx] = model.predict(x)
self._parameters[idx] = model.means
self._ll[idx] = model.score(x).sum()
# evaluate goodness of fit
self._gof[idx] = self.gof(x, self._ll[idx], k)
# debug
if self.debug is True:
print self._gof[idx], model.converged_
def _fit_vbgmm(self, x):
# clustering
for c in xrange(len(self.crange)):
k = self.crange[c]
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (self.clus_type,
self.crange[c], r + 1),
idx = c * self.repeats + r
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
model = VBGMM(n_components=k,
covariance_type=self.cvtype,
**model_kwargs)
model.n_features = self.input_dim
fit_kwargs = {}
if 'max_iter' in self.clus_kwargs:
fit_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model.fit(x, params='wmc', init_params='wmc', **fit_kwargs)
self._labels[idx] = model.predict(x)
self._parameters[idx] = model.means
self._ll[idx] = model.score(x).sum()
# evaluate goodness of fit
self._gof[idx] = self.gof(x, self._ll[idx], k)
# debug
if self.debug is True:
print self._gof[idx], model.converged_
def test_vbgmm_no_modify_alpha():
alpha = 2.
n_components = 3
X, y = make_blobs(random_state=1)
vbgmm = VBGMM(n_components=n_components, alpha=alpha, n_iter=1)
assert_equal(vbgmm.alpha, alpha)
assert_equal(vbgmm.fit(X).alpha_, float(alpha) / n_components)
def test_vbgmm_no_modify_alpha():
alpha = 2.
n_components = 3
X, y = make_blobs(random_state=1)
vbgmm = VBGMM(n_components=n_components, alpha=alpha, n_iter=1)
assert_equal(vbgmm.alpha, alpha)
assert_equal(vbgmm.fit(X).alpha_, float(alpha) / n_components)
def main(method,cluster_num=30,alpha=.5):
f ='/Users/davidgreenfield/Downloads/features_csv_tmp.csv'
#f ='/Users/davidgreenfield/Downloads/features_f500.csv'
cols=range(1,4096)
feats =np.loadtxt(open(f,"rb"),delimiter=",",skiprows=1,usecols=(cols))
asins = np.loadtxt(open(f,"rb"),delimiter=",",skiprows=1,usecols=([0]),dtype=str)
if method == 'kmeans':
k_means=cluster.KMeans(n_clusters=cluster_num)
k_means.fit(feats)
y = k_means.labels_
if MAKE_GRAPH==1:
print "hello 1"
create_graph(k_means)
elif method == 'GMM_VB':
gmm_vb = VBGMM.fit(feats,n_components=50,alpha=.5)
y = gmm_vb.predict(feats)
cluster_no = len(np.unique(y))
elif method == 'GMM_DP':
gmm_dp = DPGMM(n_components=50,alpha=alpha)
gmm_dp.fit(feats)
y = gmm_dp.predict(feats)
cluster_no = len(np.unique(y))
clusters=[]
groups={}
data=load_data('./data/boots_aws.csv')
for i in range(0,cluster_num):
groups[i]=np.where(y==i)
ids=asins[groups[i]]
clusters.append(ids)
links=[data[x]['url'] for x in ids]
create_html(links,"templates/groups/group"+str(i)+".html")
output_clusters(clusters,"outputs/clusters.csv")