Download the nltk data during container image build

Amsterdam · Nov 18, 2024 · 5a68553 · 5a68553
1 parent ae858aa
commit 5a68553
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -32,10 +32,10 @@ CMD uwsgi
 
 FROM signals-classification-base AS signals-classification-train
 
-RUN mkdir /tmp/nltk
-
-ENV NLTK_DATA /tmp/nltk
+ENV NLTK_DATA /usr/local/share/nltk_data
 
 RUN poetry install --with train
 
+RUN python -m nltk.downloader -d /usr/local/share/nltk_data stopwords
+
 ENTRYPOINT ["python", "/app/app/train/run.py"]