def load(self, text: List[str]) -> np.ndarray:
"""
Function that extracts from the embeddings model
the vectors of the words contained in text
Args:
text (list<str>): list of words of which vectors will be extracted
Returns:
embedding_matrix (np.ndarray): bi-dimensional numpy vector, each row is a term vector
"""
embedding_matrix = np.ndarray(shape=(len(text),
self.get_vector_size()))
text = check_tokenized(text)
for i, word in enumerate(text):
word = word.lower()
try:
embedding_matrix[i, :] = self.get_model().get_word_vector(word)
except KeyError:
embedding_matrix[i, :] = np.zeros(self.get_vector_size())
return embedding_matrix
def process_data_granularity(self, doc_data: str) -> List[str]:
return check_tokenized(doc_data)
def process_data_granularity(
self, field_data: Union[List[str], str]) -> List[str]:
return check_tokenized(field_data)