NeotomaDB · shaunhutch · Jun 27, 2023 · Jun 26, 2023 · Jun 26, 2023 · Jun 27, 2023
diff --git a/README.md b/README.md
@@ -97,7 +97,7 @@ The Data Review Tool can be launched by running the following command from the r
 docker-compose up --build data-review-tool
 ```
 
-Once the image is built and the container is running, the Data Review Tool can be accessed at http://localhost:8050/. There is a sample "extracted entities" JSON file provided for demo purposes.
+Once the image is built and the container is running, the Data Review Tool can be accessed at <http://localhost:8050/>. There is a sample "extracted entities" JSON file provided for demo purposes.
 
 ### Data Requirements
 
@@ -109,7 +109,7 @@ The article relevance prediction component requires a list of journals that are
 
 #### Data Extraction Pipeline
 
-As the full text articles provided by the xDD team are not publicly available we cannot create a public link to download the labelled training data. For access requests please contact Ty Andrews at [email protected].
+As the full text articles provided by the xDD team are not publicly available we cannot create a public link to download the labelled training data. For access requests please contact Ty Andrews at <[email protected]>.
 
 ### Development Workflow Overview
 
@@ -143,9 +143,6 @@ WIP
 │   │   ├── processed/                  <- Processed data
 │   │   └── interim/                    <- Temporary data location
 │   ├── data-review-tool/               <- Directory for data related to data review tool
-│   │   ├── raw/                        <- Raw unprocessed data
-│   │   ├── processed/                  <- Processed data
-│   │   └── interim/                    <- Temporary data location
 ├── results/                            <- Directory for results
 │   ├── article-relevance/              <- Directory for results related to article relevance prediction
 │   ├── ner/                            <- Directory for results related to named entity recognition
@@ -172,7 +169,7 @@ The UBC MDS project team consists of:
 
 - **Ty Andrews**
 - **Kelly Wu**
-- **Jenit Jain**
+- [![ORCID](https://img.shields.io/badge/orcid-0009--0007--8913--2403-brightgreen.svg)](https://orcid.org/0000-0002-7926-4935) [Jenit Jain](https://ht-data.com/)
 - **Shaun Hutchinson**
 
 Sponsors from Neotoma supporting the project are:

diff --git a/data/data-review-tool/article-relevance-output.parquet b/data/data-review-tool/article-relevance-output.parquet
diff --git a/data/data-review-tool/entity-extraction-output.zip b/data/data-review-tool/entity-extraction-output.zip
diff --git a/data/data-review-tool/interim/.gitkeep b/data/data-review-tool/interim/.gitkeep
diff --git a/data/data-review-tool/processed/.gitkeep b/data/data-review-tool/processed/.gitkeep
diff --git a/data/data-review-tool/raw/.gitkeep b/data/data-review-tool/raw/.gitkeep
diff --git a/data/data-review-tool/raw/5681abe7cf58f1ba274d47fb.json b/data/data-review-tool/raw/5681abe7cf58f1ba274d47fb.json
diff --git a/docker-compose.yml b/docker-compose.yml
@@ -5,10 +5,13 @@ services:
     build:
       dockerfile: ./docker/data-review-tool/Dockerfile
       context: .
+    environment:
+      - ARTICLE_RELEVANCE_BATCH=article-relevance-output.parquet
+      - ENTITY_EXTRACTION_BATCH=entity-extraction-output.zip
     ports:
       - "8050:8050"
     volumes:
-      - ./data/data-review-tool:/MetaExtractor/data/data-review-tool
+      - ./data/data-review-tool:/MetaExtractor/inputs:rw
   entity-extraction-pipeline:
     image: metaextractor-entity-extraction-pipeline:v0.0.3
     build: 
@@ -17,8 +20,8 @@ services:
     ports:
       - "5000:5000"
     volumes:
-    - ./data/entity-extraction/raw/original_files/:/inputs/
-    - ./data/entity-extraction/processed/processed_articles/:/outputs/
+      - ./data/entity-extraction/raw/original_files/:/inputs/
+      - ./data/entity-extraction/processed/processed_articles/:/outputs/
     environment:
       - USE_NER_MODEL_TYPE=huggingface
       - LOG_OUTPUT_DIR=/outputs/

diff --git a/docker/data-review-tool/Dockerfile b/docker/data-review-tool/Dockerfile
@@ -13,16 +13,16 @@ ENV LOG_LEVEL=DEBUG
 # Copy the entire repository folder into the container
 COPY src ./src
 
-# RUN git clone https://github.com/NeotomaDB/MetaExtractor
-# WORKDIR MetaExtractor/
-# RUN git switch dev
-
 # Expose the port your Dash app is running on
 EXPOSE 8050
 
+RUN pip install pyarrow
+
+RUN mkdir -p ./inputs
+
+VOLUME ["/MetaExtractor/inputs"]
+
 # Set the entrypoint command to run your Dash app
 #CMD ["python", "src/data_review_tool/app.py"]
 
-ENTRYPOINT python src/data_review_tool/app.py
-
-# VOLUME [ "/MetaExtractor/data/data-review-tool" ]
+ENTRYPOINT python src/data_review_tool/app.py