stages:
  preprocess:
    cmd: python src/data/preprocess.py
    deps:
      - src/data/preprocess.py
      - data/raw
    params:
      - preprocess.test_size
      - preprocess.random_state
    outs:
      - data/processed/features.csv
      - data/processed/train.csv
      - data/processed/test.csv
    metrics:
      - data/processed/data_metrics.json:
          cache: false

  train:
    cmd: python src/models/train.py
    deps:
      - src/models/train.py
      - data/processed/train.csv
      - data/processed/test.csv
    params:
      - train.n_estimators
      - train.max_depth
      - train.random_state
    outs:
      - models/model.pkl
    metrics:
      - models/metrics.json:
          cache: false