Fasttext meta --> run workflow

.github/workflows/build-image.yaml

@@ -3,14 +3,16 @@ name: Image Build
 on:
   push:
     branches:
-      - naf2008
+      - fasttext-meta
     tags:
       - "*"
     paths:
       - requirements.txt
       - Dockerfile
   # Allows you to run this workflow manually from the Actions tab
+  pull_request:
   workflow_dispatch:
+
 
 jobs:
   image-build:
@@ -27,13 +29,6 @@ jobs:
         with:
           images: inseefrlab/codif-ape-train
 
-      - name: Make free space
-        # https://github.com/actions/virtual-environments/issues/2840
-        run: |
-          sudo rm -rf /usr/share/dotnet /opt/ghc /usr/local/share/boost "$AGENT_TOOLSDIRECTORY"
-          docker rmi -f $(docker images -aq)
-        shell: bash
-
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
 

argo-workflows/train-workflow.yaml

@@ -72,10 +72,10 @@ spec:
           - name: MODEL_CLASS
           - name: EXPERIMENT_NAME
       container:
-        image: inseefrlab/codif-ape-train:naf2008
+        image: inseefrlab/codif-ape-train:fasttext-meta
         imagePullPolicy: Always
         command: ["/bin/bash", -c]
-        args: ["git clone -b naf2008 https://github.com/InseeFrLab/codif-ape-train.git &&\
+        args: ["git clone -b fasttext-meta https://github.com/InseeFrLab/codif-ape-train.git &&\
                 cd codif-ape-train/ &&\
                 export MLFLOW_EXPERIMENT_NAME={{inputs.parameters.EXPERIMENT_NAME}} &&\
                 mlflow run ~/work/codif-ape-train/ \

requirements.txt

@@ -16,4 +16,3 @@ sentencepiece
 accelerate
 datasets
 evaluate
-torchFastText @ git+https://github.com/inseefrlab/torch-fastText@package

src/utils/data.py

@@ -44,9 +44,9 @@ def get_sirene_4_data(
     fs = get_file_system()
 
     if revision == "NAF2008":
-        path = "projet-ape/extractions/20241027_sirene4.parquet"
+        path = "projet-ape/extractions/domain_specific_cleaned/full_dataset_20241027_sirene4_nacerev2_fuzzy_regex_similarity.parquet"
     elif revision == "NAF2025":
-        path = "projet-ape/NAF-revision/relabeled-data/20241027_sirene4_nace2025.parquet"
+        path = "projet-ape/extractions/domain_specific_cleaned/full_dataset_20241027_sirene4_nace2025_fuzzy_regex_similarity.parquet"
     else:
         raise ValueError("Revision must be either 'NAF2008' or 'NAF2025'.")