config.yaml

defaults:
#  - hydra/launcher: joblib
- dataset: states

# system
hydra:
  run:
    dir: 'outputs'
  output_subdir: null
  job_logging:
    formatters:
      simple:
        format: '%(levelname).1s %(asctime)s %(name)s:%(lineno)d %(message)s'
        datefmt: '%Y%m%d_%H%M%S'



dataset:
  # Dataset defaults to override
  sources_file: ${data_root}/urls.yaml
  mapping_file: ${data_root}/mappings.yaml
  extras_module: fetcher.extras.${dataset.name}
  # TODO: should index be part of the columns? not mandatory for state?
  index: STATE


# Base filename: it'll be ${output}.csv and ${output}_${date}.csv
output: ${dataset.name}
data_root: ${hydra:runtime.cwd}/dataset/${dataset.name}
output_date_format: "%Y%m%d"

# fetch a single state (or a list)
state: null