def __init__(self,
embedding,
analyzer,
name="WCD",
n_jobs=1,
normalize=True,
verbose=0,
oov=None,
matching=True,
**kwargs):
self.name = name
self._embedding = embedding
self._normalize = normalize
self._oov = oov
self.verbose = verbose
self.n_jobs = n_jobs
self._neighbors = NearestNeighbors(**kwargs)
self._analyzer = analyzer
if matching is True:
self._matching = Matching()
elif matching is False or matching is None:
self._matching = None
else:
self._matching = Matching(**dict(matching))
def __init__(self, embedding, analyzer='word', matching=None, name="FWCD",
n_jobs=1, use_idf=True):
"""TODO: to be defined1. """
self.name = name
self.matching = Matching(**dict(matching)) if matching else None
self.vect = EmbeddedVectorizer(embedding, analyzer=analyzer, norm='l2',
use_idf=use_idf)
self.nn = NearestNeighbors(n_jobs=n_jobs, metric='cosine',
algorithm='brute')
def __init__(self, embedding, analyzer=None, oov=None,
matching_params=None,
name="ppwmd", verbose=0, n_jobs=1):
"""initalize parameters"""
self.embedding = embedding
self.analyzer = analyzer
self.oov = oov
self.matching = (Matching(**dict(matching_params)) if matching_params
else None)
self.verbose = verbose
self.name = name
def __init__(self,
analyzer=None,
matching=None,
name=None,
verbose=0,
n_epochs=10,
alpha=0.25,
min_alpha=0.05,
n_jobs=4,
**kwargs):
# self.model = model
self.alpha = alpha
self.min_alpha = min_alpha
self.verbose = verbose
self.name = "paragraph-vectors" if name is None else name
if matching is True:
self._matching = Matching()
elif matching is False or matching is None:
self._matching = None
else:
self._matching = Matching(**dict(matching))
self.analyzer = analyzer
self.model = Doc2Vec(
alpha=alpha,
min_alpha=alpha,
size=500,
window=8,
min_count=1,
sample=1e-5,
workers=n_jobs,
negative=20,
dm=0,
dbow_words=1, # words only with dm!=0?
dm_mean=0, # unused when in concat mode
dm_concat=1,
dm_tag_count=1)
self.n_epochs = n_epochs
self._neighbors = NearestNeighbors(**kwargs)
