stackexchange-data-pr/dvc.yaml

stages:
  split:
    cmd: python3 main.py split
    deps:
    - data/raw/CrossValidated-Questions.csv
    outs:
    - data/processed/test.csv.zip
    - data/processed/train.csv.zip
  train:
    cmd: python3 main.py train
    deps:
    - data/processed/test.csv.zip
    - data/processed/train.csv.zip
    - main.py
    outs:
    - outputs
    - params.yml:
        cache: false
    metrics:
    - metrics.csv:
        cache: false