explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Change get_freqs to take a list of files

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-14 10:55:56 +02:00
parent 935ac53ee3
commit 3de1b3ef1d
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
bin/get_freqs.py
View File

@ -40,8 +40,7 @@ def null_props(string):
def count_freqs(input_loc, output_loc): def count_freqs(input_loc, output_loc):
nlp = spacy.en.English(data_dir=os.environ['SPACY_DATA'], Parser=None, nlp = spacy.en.English(Parser=None, Tagger=None, Entity=None, load_vectors=False)
Tagger=None, Entity=None, load_vectors=False)
nlp.vocab.lexeme_props_getter = null_props nlp.vocab.lexeme_props_getter = null_props
counts = PreshCounter() counts = PreshCounter()
@ -76,15 +75,17 @@ def merge_counts(locs, out_loc):
@plac.annotations( @plac.annotations(
input_dir=("Directory of input files"), input_loc=("Location of input file list"),
freqs_dir=("Directory for frequency files"), freqs_dir=("Directory for frequency files"),
output_loc=("Location for output file"), output_loc=("Location for output file"),
n_jobs=("Number of workers", "option", "n", int), n_jobs=("Number of workers", "option", "n", int),
) )
def main(input_dir, freqs_dir, output_loc, n_jobs=2): def main(input_loc, freqs_dir, output_loc, n_jobs=2):
tasks = [] tasks = []
for filename in os.listdir(input_dir): for input_path in open(input_loc):
input_path = path.join(input_dir, filename) input_path = input_path.strip()
if not input_path: continue
filename = input_path.split('/')[-1]
output_path = path.join(freqs_dir, filename.replace('bz2', 'freq')) output_path = path.join(freqs_dir, filename.replace('bz2', 'freq'))
tasks.append((input_path, output_path)) tasks.append((input_path, output_path))