def cluster_user(self):
user_feature_matrix = self.__extract_user_feature()
user_feature_matrix = user_feature_matrix.tocsr()
user_feature_matrix= MaxAbsScaler().fit_transform(user_feature_matrix)
#model = DBSCAN(eps=0.5, min_samples=100).fit(user_feature_matrix)
model = MiniBatchKMeans(n_clusters=50,max_iter=10000).fit(user_feature_matrix.toarray())
labels = model.labels_
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
print('Estimated number of clusters: %d' % n_clusters_)
user_label_dict = dict()
for user in self.__user_ix_dict:
user_label_dict[user] = labels[self.__user_ix_dict[user]]
return user_label_dict
def create_read_tabular_file(path,
save_pref='_',
feature_normalization=None,
transpose=False,
override=False):
'''
:param path:
:param save_pref:
:param transpose: if isolates are columns
:param feature_normalization: 'binary': {0,1}, '0-1': [0-1], 'percent': {0,1,..,100}, 'zu': zero mean, unit variance
:return:
'''
print('Start creating ', save_pref)
if override or not os.path.exists('_'.join(
[save_pref, 'feature', 'vect.npz'])):
rows = [
l.strip() for l in codecs.open(path, 'r', 'utf-8').readlines()
]
tf_vec = sparse.csr_matrix([[
GenotypeReader.get_float_or_zero(x)
for x in entry.split('\t')[1::]
] for entry in rows[1::]])
if transpose:
tf_vec = sparse.csr_matrix(tf_vec.toarray().T)
isolates = [
feat.replace(' ', '')
for feat in rows[0].rstrip().split('\t')
]
feature_names = [row.split()[0] for row in rows[1::]]
else:
isolates = [row.split()[0] for row in rows[1::]]
feature_names = [
feat.replace(' ', '')
for feat in rows[0].rstrip().split('\t')
]
# normalizer / discretizer
if feature_normalization:
if feature_normalization == 'binary':
tf_vec = np.round(MaxAbsScaler().fit_transform(tf_vec))
elif feature_normalization == '01':
tf_vec = MaxAbsScaler().fit_transform(tf_vec)
elif feature_normalization == 'percent':
tf_vec = np.round(MaxAbsScaler().fit_transform(tf_vec) *
100)
elif feature_normalization == 'zu':
tf_vec = sparse.csr_matrix(
preprocessing.StandardScaler().fit_transform(
tf_vec.toarray()))
FileUtility.save_sparse_csr(
'_'.join([save_pref, 'feature', 'vect.npz']), tf_vec)
FileUtility.save_list(
'_'.join([save_pref, 'feature', 'list.txt']),
feature_names)
FileUtility.save_list(
'_'.join([save_pref, 'strains', 'list.txt']), isolates)
print(save_pref, ' created successfully containing ',
str(len(isolates)), ' strains and ',
str(len(feature_names)), ' features')
return (''.join([
save_pref, ' created successfully containing ',
str(len(isolates)), ' strains and ',
str(len(feature_names)), ' features'
]))
else:
print(save_pref, ' already exist ')
return (''.join([save_pref, ' already exist ']))
