From 60273fb6bdcb30bae96df91cb6e7f07623cd78d0 Mon Sep 17 00:00:00 2001 From: simon987 Date: Sat, 28 Aug 2021 20:09:00 -0400 Subject: [PATCH] Use imap instead of map --- hexlib/text.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/hexlib/text.py b/hexlib/text.py index 7bbcbc5..d4916c0 100644 --- a/hexlib/text.py +++ b/hexlib/text.py @@ -24,11 +24,12 @@ nltk.download("wordnet", quiet=True) lemmatizer = WordNetLemmatizer() -def clean_multicore(texts, processes, **kwargs): +def clean_multicore(texts, processes, chunk_size=10000, **kwargs): pool = Pool(processes=processes) - return pool.map( + yield from pool.imap( func=partial(preprocess, **kwargs), iterable=texts, + chunksize=chunk_size )