Merge pull request #1789 from sorenlind/init_model_args

Fix CLI arguments for init-model
This commit is contained in:
Ines Montani 2018-01-03 12:08:07 +00:00 committed by GitHub
commit 03a2f540ca
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions

View File

@ -25,7 +25,7 @@ from ..util import prints, ensure_path, get_lang_class
prune_vectors=("optional: number of vectors to prune to", prune_vectors=("optional: number of vectors to prune to",
"option", "V", int) "option", "V", int)
) )
def init_model(lang, output_dir, freqs_loc, clusters_loc=None, vectors_loc=None, prune_vectors=-1): def init_model(_cmd, lang, output_dir, freqs_loc, clusters_loc=None, vectors_loc=None, prune_vectors=-1):
""" """
Create a new model from raw data, like word frequencies, Brown clusters Create a new model from raw data, like word frequencies, Brown clusters
and word vectors. and word vectors.
@ -36,7 +36,7 @@ def init_model(lang, output_dir, freqs_loc, clusters_loc=None, vectors_loc=None,
vectors_loc = ensure_path(vectors_loc) vectors_loc = ensure_path(vectors_loc)
probs, oov_prob = read_freqs(freqs_loc) probs, oov_prob = read_freqs(freqs_loc)
vectors_data, vector_keys = read_vectors(vectors_loc) if vectors_loc else None vectors_data, vector_keys = read_vectors(vectors_loc) if vectors_loc else None, None
clusters = read_clusters(clusters_loc) if clusters_loc else {} clusters = read_clusters(clusters_loc) if clusters_loc else {}
nlp = create_model(lang, probs, oov_prob, clusters, vectors_data, vector_keys, prune_vectors) nlp = create_model(lang, probs, oov_prob, clusters, vectors_data, vector_keys, prune_vectors)
@ -69,7 +69,7 @@ def create_model(lang, probs, oov_prob, clusters, vectors_data, vector_keys, pru
lex_added += 1 lex_added += 1
nlp.vocab.cfg.update({'oov_prob': oov_prob}) nlp.vocab.cfg.update({'oov_prob': oov_prob})
if len(vectors_data): if vectors_data:
nlp.vocab.vectors = Vectors(data=vectors_data, keys=vector_keys) nlp.vocab.vectors = Vectors(data=vectors_data, keys=vector_keys)
if prune_vectors >= 1: if prune_vectors >= 1:
nlp.vocab.prune_vectors(prune_vectors) nlp.vocab.prune_vectors(prune_vectors)