Skip to content

throw away similar stemmed words of lesser frequency #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mrscoopers wants to merge 1 commit into
base: master
Choose a base branch
from
Open

throw away similar stemmed words of lesser frequency #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions mini_coil/data_pipeline/combine_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
from mini_coil.data_pipeline.vocab_resolver import VocabResolver
from mini_coil.model.encoder import Encoder
from mini_coil.model.word_encoder import WordEncoder

from py_rust_stemmers import SnowballStemmer

def load_vocab(vocab_path):
vocab = []
Expand All @@ -27,17 +27,25 @@ def main():
parser.add_argument("--output-path", type=str)
parser.add_argument("--input-dim", type=int, default=512)
parser.add_argument("--output-dim", type=int, default=4)

stemmer = SnowballStemmer("english")
args = parser.parse_args()

vocab = load_vocab(args.vocab_path)
filtered_vocab = []
stemmed_words_vocab = set()

for word in vocab:
if word in english_stopwords:
continue
model_path = os.path.join(args.models_dir, f"model-{word}.ptch")
if os.path.exists(model_path):
filtered_vocab.append(word)
stemmed_word = stemmer.stem_word(word)
if stemmed_word in stemmed_words_vocab:
continue
else:
stemmed_words_vocab.add(stemmed_word)
model_path = os.path.join(args.models_dir, f"model-{word}.ptch")
if os.path.exists(model_path):
filtered_vocab.append(word)

params = [torch.zeros(args.input_dim, args.output_dim)] # Extra zero tensor, as first word is vocab starts from 1

Expand Down