schema: '2.0'
stages:
  prepare:
    cmd: python src/prepare.py data/data.xml
    deps:
    - path: data/data.xml
      hash: md5
      md5: 22a1a2931c8370d3aeedd7183606fd7f
      size: 14445097
    - path: src/prepare.py
      hash: md5
      md5: f54d670ac8a4f63206781fc31d1f2651
      size: 2231
    params:
      params.yaml:
        prepare.seed: 20170428
        prepare.split: 0.2
    outs:
    - path: data/prepared
      hash: md5
      md5: 153aad06d376b6595932470e459ef42a.dir
      size: 8437363
      nfiles: 2
  featurize:
    cmd: python src/featurization.py data/prepared data/features
    deps:
    - path: data/prepared
      hash: md5
      md5: 153aad06d376b6595932470e459ef42a.dir
      size: 8437363
      nfiles: 2
    - path: src/featurization.py
      hash: md5
      md5: 29660042a8c24019fa7392f2e1a735b9
      size: 4175
    params:
      params.yaml:
        featurize.max_features: 100
        featurize.ngrams: 1
    outs:
    - path: data/features
      hash: md5
      md5: 74642e90419272839886d8e51f730b44.dir
      size: 1556292
      nfiles: 2
  train:
    cmd: python src/train.py data/features model.pkl
    deps:
    - path: data/features
      hash: md5
      md5: 74642e90419272839886d8e51f730b44.dir
      size: 1556292
      nfiles: 2
    - path: src/train.py
      hash: md5
      md5: 324001573ed724e5ae092226fcf9ca30
      size: 1666
    params:
      params.yaml:
        train.min_split: 0.01
        train.n_est: 50
        train.seed: 20170428
    outs:
    - path: model.pkl
      hash: md5
      md5: 67e469e0d6578012431be0cd8db6325c
      size: 1855076