generate_multilabel_component.yaml

name: Multilabel training
inputs:
- {name: tagset, type: String}
- {name: created_tags, type: String}
outputs:
- {name: modfile, type: String}
- {name: model, type: String}
implementation:
  container:
    image: lkorver/praxi-vw-base:0.320
    command:
    - sh
    - -ec
    - |
      program_path=$(mktemp)
      printf "%s" "$0" > "$program_path"
      python3 -u "$program_path" "$@"
    - "def _make_parent_dirs_and_return_path(file_path: str):\n    import os\n   \
      \ os.makedirs(os.path.dirname(file_path), exist_ok=True)\n    return file_path\n\
      \ndef multilabel_training(tagset_path, created_tags_path, modfile_path, model_path):\n\
      \    ''''''\n    import main\n    import os\n    import json\n    import pickle\n\
      \    import time\n\n    args = main.get_inputs() \n    data_loaded = []\n\n\
      \    with open(tagset_path, 'rb') as reader:\n        data_loaded = pickle.load(reader)\n\
      \n    print(len(data_loaded))\n\n    # with open(created_tags_path, 'r') as\
      \ stream:\n    #     for line in stream:\n    #         temp = json.loads(line)\n\
      \    #         if (type(temp) != None):\n    #             data_loaded.append(temp)\n\
      \n    # print(len(data_loaded))\n\n    model = main.multilabel_train(data_loaded,\
      \ args)\n    modfile = model.vw_modelfile\n    os.popen('cp {0} {1}'.format(modfile,\
      \ modfile_path))\n    with open(model_path, 'wb') as modfile:\n        pickle.dump(model,\
      \ modfile)\n\n    # with open(test_tags_path, 'wb') as testfile:\n    #    \
      \ pickle.dump(testdat, testfile)\n\nimport argparse\n_parser = argparse.ArgumentParser(prog='Multilabel\
      \ training', description='')\n_parser.add_argument(\"--tagset\", dest=\"tagset_path\"\
      , type=str, required=True, default=argparse.SUPPRESS)\n_parser.add_argument(\"\
      --created-tags\", dest=\"created_tags_path\", type=str, required=True, default=argparse.SUPPRESS)\n\
      _parser.add_argument(\"--modfile\", dest=\"modfile_path\", type=_make_parent_dirs_and_return_path,\
      \ required=True, default=argparse.SUPPRESS)\n_parser.add_argument(\"--model\"\
      , dest=\"model_path\", type=_make_parent_dirs_and_return_path, required=True,\
      \ default=argparse.SUPPRESS)\n_parsed_args = vars(_parser.parse_args())\n\n\
      _outputs = multilabel_training(**_parsed_args)\n"
    args:
    - --tagset
    - {inputPath: tagset}
    - --created-tags
    - {inputPath: created_tags}
    - --modfile
    - {outputPath: modfile}
    - --model
    - {outputPath: model}