def __init__(self, input_embs_dir, graph_file, ignore_langs=[]):
"""Contructor
:param input_embs_dir: the folder with pre-computed embeddings
:param graph_file: the graph file of type graphml
:param ignore_langs: used when learning embedding from scratch, the
embeddings for these languages are considered 0
"""
# Read pre-computed embeddings
self.embeddings = {}
for lang in utils.langs:
emb_path = os.path.join(input_embs_dir, lang, 'wavg.csv')
embs, _ = utils.read_embeddings(emb_path, sep=',', binary=False)
if lang in ignore_langs:
print(lang)
self.embeddings.update(
{lang + ':' + k: np.zeros(embs[k].shape)
for k in embs})
else:
self.embeddings.update({lang + ':' + k: embs[k] for k in embs})
if ignore_langs != []:
self.name = ''.join([
os.path.basename(graph_file).split('.')[0], '_unknown_',
'_'.join(ignore_langs)
])
else:
self.name = os.path.basename(graph_file).split('.')[0]
# Read graph
self._read_graph(graph_file)
def _read_embs(self, emb_dir):
all_embs = {}
self.name = self.get_name()
for lang in utils.langs:
lang_embs_path = os.path.join(emb_dir, lang,
self.emb_type + '.csv')
embs, _ = utils.read_embeddings(lang_embs_path,
sep=',',
binary=True)
all_embs.update({lang + ':' + k: embs[k] for k in embs})
return all_embs
def __init__(self, path):
"""Constructor
:param path: fastText embeddings file in text format
"""
self.embeddings, self.emb_dim = utils.read_embeddings(path)
self.estimate_word_freqs()
def _read_embs(self, emb_file):
file_name = os.path.basename(emb_file).split('.')[0]
self.name = ''.join([self.get_name(), '_', file_name])
all_embs, _ = utils.read_embeddings(emb_file, sep=',', binary=True)
return all_embs