explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5687 from svlandeg/bugfix/init-model

Browse Source 
Fixing init_model
This commit is contained in:
Ines Montani 2020-07-02 14:10:28 +02:00 committed by GitHub
commit ee8a830248
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/cli/init_model.py
View File

@ -37,7 +37,7 @@ def init_model_cli(
clusters_loc: Optional[Path] = Opt(None, "--clusters-loc", "-c", help="Optional location of brown clusters data", exists=True),
jsonl_loc: Optional[Path] = Opt(None, "--jsonl-loc", "-j", help="Location of JSONL-formatted attributes file", exists=True),
vectors_loc: Optional[Path] = Opt(None, "--vectors-loc", "-v", help="Optional vectors file in Word2Vec format", exists=True),
prune_vectors: int = Opt(-1 , "--prune-vectors", "-V", help="Optional number of vectors to prune to"),
prune_vectors: int = Opt(-1, "--prune-vectors", "-V", help="Optional number of vectors to prune to"),
truncate_vectors: int = Opt(0, "--truncate-vectors", "-t", help="Optional number of vectors to truncate to when reading in vectors file"),
vectors_name: Optional[str] = Opt(None, "--vectors-name", "-vn", help="Optional name for the word vectors, e.g. en_core_web_lg.vectors"),
model_name: Optional[str] = Opt(None, "--model-name", "-mn", help="Optional name for the model meta"),
@ -56,6 +56,7 @@ def init_model_cli(
freqs_loc=freqs_loc,
clusters_loc=clusters_loc,
jsonl_loc=jsonl_loc,
vectors_loc=vectors_loc,
prune_vectors=prune_vectors,
truncate_vectors=truncate_vectors,
vectors_name=vectors_name,
@ -228,7 +229,7 @@ def add_vectors(
else:
if vectors_loc:
with msg.loading(f"Reading vectors from {vectors_loc}"):
vectors_data, vector_keys = read_vectors(msg, vectors_loc)
vectors_data, vector_keys = read_vectors(msg, vectors_loc, truncate_vectors)
msg.good(f"Loaded vectors from {vectors_loc}")
else:
vectors_data, vector_keys = (None, None)
@ -247,7 +248,7 @@ def add_vectors(
nlp.vocab.prune_vectors(prune_vectors)
def read_vectors(msg: Printer, vectors_loc: Path, truncate_vectors: int = 0):
def read_vectors(msg: Printer, vectors_loc: Path, truncate_vectors: int):
f = open_file(vectors_loc)
shape = tuple(int(size) for size in next(f).split())
if truncate_vectors >= 1: