schema: '2.0'
stages:
  train:
    cmd: python src/models/train_model.py
    deps:
    - path: data/processed/train.csv
      md5: 5331b9c32b2d097d8d7aca01de5524bc
      size: 1198262
    - path: data/processed/validation.csv
      md5: 6069153a075b00dfb6d9e0843dd2da89
      size: 52739
    - path: model_params.yml
      md5: 1bf2edf25e851cc9cd3be75fbd9905a3
      size: 177
    - path: src/models/train_model.py
      md5: f7d1121426c3d5530c2b9697cb7ac74a
      size: 951
    outs:
    - path: models
      md5: fc37870a93db61b94af9f0847577f09b.dir
      size: 243476333
      nfiles: 5
    - path: reports/training_metrics.csv
      md5: 3b309def91a32e521acd23b163742522
      size: 320
  eval:
    cmd: python src/models/evaluate_model.py
    deps:
    - path: data/processed/test.csv
      md5: 3eec94ac211c76363a3d968663b82d02
      size: 39574
    - path: model_params.yml
      md5: 1bf2edf25e851cc9cd3be75fbd9905a3
      size: 177
    - path: models
      md5: fc37870a93db61b94af9f0847577f09b.dir
      size: 243476333
      nfiles: 5
    - path: src/models/evaluate_model.py
      md5: 89edb77aaab3055605ae6db2e21eab82
      size: 705
    outs:
    - path: reports/evaluation_metrics.csv
      md5: eaa3bf017026aa1be31560f308fff78e
      size: 2122
  process_data:
    cmd: python src/data/process_data.py
    deps:
    - path: data/raw
      md5: 2ab20ac1b58df875a590b07d0e04eb5b.dir
      size: 1358833013
      nfiles: 3
    - path: data_params.yml
      md5: a68eabf79c3b3e28afb05baa1944bbc7
      size: 32
    - path: src/data/process_data.py
      md5: 68db554a69a0c8ce807907afa2be5e9c
      size: 521
    outs:
    - path: data/processed/test.csv
      md5: 3eec94ac211c76363a3d968663b82d02
      size: 39574
    - path: data/processed/train.csv
      md5: 5331b9c32b2d097d8d7aca01de5524bc
      size: 1198262
    - path: data/processed/validation.csv
      md5: 6069153a075b00dfb6d9e0843dd2da89
      size: 52739
  download_data:
    cmd: python src/data/make_dataset.py
    deps:
    - path: data_params.yml
      md5: a68eabf79c3b3e28afb05baa1944bbc7
      size: 32
    - path: src/data/make_dataset.py
      md5: a0667f4ad8c06551609bd0bf950167b7
      size: 776
    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