nltk one liner

InseeFrLab · Jan 30, 2024 · 7c4a3be · 7c4a3be
1 parent 58ea52b
commit 7c4a3be
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 8 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -2,9 +2,7 @@ FROM inseefrlab/onyxia-vscode-pytorch:py3.11.6
 
 RUN git clone https://github.com/InseeFrLab/codif-ape-train.git &&\
     cd codif-ape-train/ &&\
-    python - <<'END_SCRIPT' \
-    import nltk \
-    nltk.download('stopwords') \
-    END_SCRIPT
+    pip install --no-cache-dir --upgrade -r requirements.txt && \
+    python -m nltk.downloader stopwords
 
 WORKDIR ${WORKSPACE_DIR}/codif-ape-train/
diff --git a/setup.sh b/setup.sh
@@ -11,7 +11,4 @@ AWS_SECRET_ACCESS_KEY=`vault kv get -field=SECRET_KEY onyxia-kv/projet-ape/s3` &
 unset AWS_SESSION_TOKEN
 export MC_HOST_s3=https://$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY@$AWS_S3_ENDPOINT
 
-python - <<'END_SCRIPT'
-import nltk
-nltk.download('stopwords')
-END_SCRIPT
+python -m nltk.downloader stopwords