def get_input_vector(self, ind):
"""
Given an index, get the corresponding vector of the Input Matrix.
"""
dim = self.get_dimension()
b = fasttext.Vector(dim)
self.f.getInputVector(b, ind)
return np.array(b)
def get_sentence_vector(self, text, normalise=False):
"""
Given a string, get a single vector represenation. This function
assumes to be given a single line of text. We split words on
whitespace (space, newline, tab, vertical tab) and the control
characters carriage return, formfeed and the null character.
"""
if text.find('\n') != -1:
raise ValueError(
"predict processes one line at a time (remove \'\\n\')")
text += "\n"
dim = self.get_dimension()
b = fasttext.Vector(dim)
self.f.getSentenceVector(b, text, normalise)
return np.array(b)
def get_new_vector(self):
return fasttext.Vector(self.get_dimension())
def get_word_vector(self, word, normalise=False):
"""Get the vector representation of word."""
dim = self.get_dimension()
b = fasttext.Vector(dim)
self.f.getWordVector(b, word, normalise)
return np.array(b)
def get_subword_vector(self, word):
"""Get the vector representation of subword."""
dim = self.get_dimension()
b = fasttext.Vector(dim)
self.f.getSubwordVector(b, word)
return np.array(b)