dvc.lock

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: e22789fc9581cad11ef7a6fa3aa3f17b
      size: 4158
    params:
      params.yaml:
        featurize.max_features: 200
        featurize.ngrams: 2
    outs:
    - path: data/features
      hash: md5
      md5: f35d4cc2c552ac959ae602162b8543f3.dir
      size: 2232588
      nfiles: 2
  train:
    cmd: python src/train.py data/features model.pkl
    deps:
    - path: data/features
      hash: md5
      md5: f35d4cc2c552ac959ae602162b8543f3.dir
      size: 2232588
      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: d1f6e055f7f5e2827fcfae68d9b64d4c
      size: 1958115
  evaluate:
    cmd: python src/evaluate.py model.pkl data/features
    deps:
    - path: data/features
      hash: md5
      md5: f35d4cc2c552ac959ae602162b8543f3.dir
      size: 2232588
      nfiles: 2
    - path: model.pkl
      hash: md5
      md5: d1f6e055f7f5e2827fcfae68d9b64d4c
      size: 1958115
    - path: src/evaluate.py
      hash: md5
      md5: a1a59f55636170fb56e0c6afd3e28fa4
      size: 3315
    outs:
    - path: eval
      hash: md5
      md5: 80a081570c800c60b9b98ca4b3c91dd7.dir
      size: 1292342
      nfiles: 8