schema: '2.0'
stages:
  train:
    cmd: python src/models/train_model.py
    deps:
    - path: data/processed/train.csv
      md5: 5331b9c32b2d097d8d7aca01de5524bc
      size: 1198550
    - path: data/processed/validation.csv
      md5: 6069153a075b00dfb6d9e0843dd2da89
      size: 52753
    - path: model_params.yml
      md5: 1bf2edf25e851cc9cd3be75fbd9905a3
      size: 188
    - path: src/models/train_model.py
      md5: f7d1121426c3d5530c2b9697cb7ac74a
      size: 991
    outs:
    - path: models
      md5: 687b74d21b979d09bfdfff0722eae305.dir
      size: 244268079
      nfiles: 6
    - path: reports/training_metrics.csv
      md5: e0f69aef2d1d7f02c561f8c7801c3a20
      size: 320
  eval:
    cmd: python src/models/evaluate_model.py
    deps:
    - path: data/processed/test.csv
      md5: 3eec94ac211c76363a3d968663b82d02
      size: 39586
    - path: model_params.yml
      md5: 1bf2edf25e851cc9cd3be75fbd9905a3
      size: 188
    - path: models
      md5: 687b74d21b979d09bfdfff0722eae305.dir
      size: 244268079
      nfiles: 6
    - path: src/models/evaluate_model.py
      md5: ba0f4c7aa238de433cd389e9d2e66d64
      size: 734
    outs:
    - path: reports/evaluation_metrics.csv
      md5: aef31e3b826508ffe01ab4f579715ff8
      size: 2117
  process_data:
    cmd: python src/data/process_data.py
    deps:
    - path: data/raw
      md5: 2ab20ac1b58df875a590b07d0e04eb5b.dir
      size: 1359144987
      nfiles: 3
    - path: data_params.yml
      md5: a68eabf79c3b3e28afb05baa1944bbc7
      size: 33
    - path: src/data/process_data.py
      md5: 112f5e26a26956c508da053b4e2a950e
      size: 530
    outs:
    - path: data/processed/test.csv
      md5: 3eec94ac211c76363a3d968663b82d02
      size: 39586
    - path: data/processed/train.csv
      md5: 5331b9c32b2d097d8d7aca01de5524bc
      size: 1198550
    - path: data/processed/validation.csv
      md5: 6069153a075b00dfb6d9e0843dd2da89
      size: 52753
  download_data:
    cmd: python src/data/make_dataset.py
    deps:
    - path: data_params.yml
      md5: a68eabf79c3b3e28afb05baa1944bbc7
      size: 33
    - path: src/data/make_dataset.py
      md5: a0667f4ad8c06551609bd0bf950167b7
      size: 801
    outs:
    - path: data/raw
      md5: 2ab20ac1b58df875a590b07d0e04eb5b.dir
      size: 1358833013
      nfiles: 3
  visualize:
    cmd: streamlit run src/visualization/visualize.py
    deps:
    - path: models
      md5: fc37870a93db61b94af9f0847577f09b.dir
      size: 243476333
      nfiles: 5
    - path: src/visualization/visualize.py
      md5: 4226e4148abb5ac186c0ab8c1d87b228
      size: 671
  push_to_hf_hub:
    cmd: python src/models/hf_upload.py
    deps:
    - path: model_params.yml
      md5: 1bf2edf25e851cc9cd3be75fbd9905a3
      size: 177
    - path: models
      md5: fc37870a93db61b94af9f0847577f09b.dir
      size: 243476333
      nfiles: 5
    - path: src/models/hf_upload.py
      md5: a953816a3eb7bef702313544103a1c11
      size: 1290