Mounting models folder as volume

brabbit61 · brabbit61 · commit c3e293ec90a4 · 2023-06-28T12:21:17.000-07:00
diff --git a/docker-compose.yml b/docker-compose.yml
@@ -5,8 +5,6 @@ services:
     build:
       dockerfile: ./docker/article-relevance/Dockerfile
       context: .
-      args:
-      - MODEL_PATH=models/article-relevance/logistic_regression_model.joblib
     environment:
       - N_RECENT=10
       - MIN_DATE=
@@ -21,6 +19,7 @@ services:
       - ./data/article-relevance/outputs:/output
       - ./data/article-relevance/processed/prediction_parquet:/parquet
       - ./data/article-relevance/raw:/raw
+      - ./models/article-relevance:/models
 
   data-review-tool:
     image: metaextractor-data-review-tool:v0.0.1
diff --git a/docker/article-relevance/Dockerfile b/docker/article-relevance/Dockerfile
@@ -1,12 +1,8 @@
 # Use the official Python 3.10 image as the base image
 FROM python:3.10
 
-ARG MODEL_PATH
-ARG DOI_FILE_PATH
-
 ENV DOI_PATH="/raw"
 ENV PARQUET_PATH="/parquet"
-ENV ENV_DOI_FILE_PATH=$DOI_FILE_PATH
 # Set the working directory inside the container
 WORKDIR /app/
 
@@ -19,9 +15,6 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Copy the entire repository folder into the container
 COPY src ./src
 
-# Copy the model folder into the container
-COPY $MODEL_PATH ./models/article-relevance
-
 # Copy the shell script to the container
 COPY docker/article-relevance/run-prediction.sh .
 
@@ -32,7 +25,8 @@ RUN chmod +x run-prediction.sh
 RUN mkdir -p /output
 RUN mkdir -p /raw
 RUN mkdir -p /parquet
-VOLUME ["/output", "/parquet", "/raw"]
+RUN mkdir -p /models
+VOLUME ["/output", "/parquet", "/raw", "/models"]
 
 # Set the entry point for the Docker container
 ENTRYPOINT ["./run-prediction.sh"]
diff --git a/docker/article-relevance/run-prediction.sh b/docker/article-relevance/run-prediction.sh
@@ -12,6 +12,5 @@ python src/article_relevance/gdd_api_query.py \
 
 python src/article_relevance/relevance_prediction_parquet.py \
   --doi_file_path="$DOI_FILE_PATH" \
-  --model_path="$MODEL_PATH" \
   --output_path="$OUTPUT_PATH" \
   --send_xdd="$SEND_XDD"
diff --git a/src/article_relevance/relevance_prediction_parquet.py b/src/article_relevance/relevance_prediction_parquet.py
@@ -422,9 +422,15 @@ def main():
     opt = docopt(__doc__)
 
     doi_list_file_path = opt["--doi_file_path"]
-    model_path = opt['--model_path']
     output_path = opt['--output_path']
     send_xdd = opt['--send_xdd']
+    
+    # /models directory is a mounted volume, containing the model object
+    models = os.lsitdir("/models")
+    if models:
+        model_path = os.path.join("/models", models[0])
+    else:
+        model_path = ""
 
     metadata_df = crossref_extract(doi_list_file_path)
 
