def __init__()

in bayesmark/sklearn_funcs.py [0:0]

• 15 lines of code
• 4 McCabe index (conditional complexity)

    def __init__(self, model, dataset, scorer, path):
        """Build class that wraps sklearn classifier/regressor CV score for use as an objective function surrogate.

        Parameters
        ----------
        model : str
            Which classifier to use, must be key in `MODELS_CLF` or `MODELS_REG` dict depending on if dataset is
            classification or regression.
        dataset : str
            Which data set to use, must be key in `DATA_LOADERS` dict, or name of custom csv file.
        scorer : str
            Which sklearn scoring metric to use, in `SCORERS_CLF` list or `SCORERS_REG` dict depending on if dataset is
            classification or regression.
        path : str
            Root directory to look for all pickle files.
        """
        TestFunction.__init__(self)

        # Find the space class, we could consider putting this in pkl too
        problem_type = get_problem_type(dataset)
        assert problem_type in (ProblemType.clf, ProblemType.reg)
        _, _, self.api_config = MODELS_CLF[model] if problem_type == ProblemType.clf else MODELS_REG[model]
        self.space = JointSpace(self.api_config)

        # Load the pre-trained model
        fname = SklearnModel.test_case_str(model, dataset, scorer) + ".pkl"

        if isinstance(path, bytes):
            # This is for test-ability, we could use mock instead.
            self.model = pkl.loads(path)
        else:
            path = os.path.join(path, fname)  # pragma: io
            assert os.path.isfile(path), "Model file not found: %s" % path

            with absopen(path, "rb") as f:  # pragma: io
                self.model = pkl.load(f)  # pragma: io
        assert callable(getattr(self.model, "predict", None))