Skip to content

Union

This file is part of the TPOT library.

The current version of TPOT was developed at Cedars-Sinai by: - Pedro Henrique Ribeiro (https://github.com/perib, https://www.linkedin.com/in/pedro-ribeiro/) - Anil Saini (anil.saini@cshs.org) - Jose Hernandez (jgh9094@gmail.com) - Jay Moran (jay.moran@cshs.org) - Nicholas Matsumoto (nicholas.matsumoto@cshs.org) - Hyunjun Choi (hyunjun.choi@cshs.org) - Miguel E. Hernandez (miguel.e.hernandez@cshs.org) - Jason Moore (moorejh28@gmail.com)

The original version of TPOT was primarily developed at the University of Pennsylvania by: - Randal S. Olson (rso@randalolson.com) - Weixuan Fu (weixuanf@upenn.edu) - Daniel Angell (dpa34@drexel.edu) - Jason Moore (moorejh28@gmail.com) - and many more generous open-source contributors

TPOT is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

TPOT is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details.

You should have received a copy of the GNU Lesser General Public License along with TPOT. If not, see http://www.gnu.org/licenses/.

UnionPipeline

Bases: SearchSpace

Source code in tpot2/search_spaces/pipelines/union.py 
106
107
108
109
110
111
112
113
114
115
116
class UnionPipeline(SearchSpace):
    def __init__(self, search_spaces : List[SearchSpace] ) -> None:
        """
        Takes in a list of search spaces. will produce a pipeline of Sequential length. Each step in the pipeline will correspond to the the search space provided in the same index.
        """

        self.search_spaces = search_spaces

    def generate(self, rng=None):
        rng = np.random.default_rng(rng)
        return UnionPipelineIndividual(self.search_spaces, rng=rng)

__init__(search_spaces)

Takes in a list of search spaces. will produce a pipeline of Sequential length. Each step in the pipeline will correspond to the the search space provided in the same index.

Source code in tpot2/search_spaces/pipelines/union.py 
107
108
109
110
111
112
def __init__(self, search_spaces : List[SearchSpace] ) -> None:
    """
    Takes in a list of search spaces. will produce a pipeline of Sequential length. Each step in the pipeline will correspond to the the search space provided in the same index.
    """

    self.search_spaces = search_spaces

UnionPipelineIndividual

Bases: SklearnIndividual

Takes in a list of search spaces. each space is a list of SearchSpaces. Will produce a FeatureUnion pipeline. Each step in the pipeline will correspond to the the search space provided in the same index. The resulting pipeline will be a FeatureUnion of the steps in the pipeline.

Source code in tpot2/search_spaces/pipelines/union.py 
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
class UnionPipelineIndividual(SklearnIndividual):
    """
    Takes in a list of search spaces. each space is a list of SearchSpaces.
    Will produce a FeatureUnion pipeline. Each step in the pipeline will correspond to the the search space provided in the same index.
    The resulting pipeline will be a FeatureUnion of the steps in the pipeline.

    """

    def __init__(self, search_spaces : List[SearchSpace], rng=None) -> None:
        super().__init__()
        self.search_spaces = search_spaces

        self.pipeline = []
        for space in self.search_spaces:
            self.pipeline.append(space.generate(rng))

    def mutate(self, rng=None):
        rng = np.random.default_rng(rng)
        step = rng.choice(self.pipeline)
        return step.mutate(rng)


    def crossover(self, other, rng=None):
        #swap a random step in the pipeline with the corresponding step in the other pipeline
        rng = np.random.default_rng(rng)

        cx_funcs = [self._crossover_node, self._crossover_swap_node]
        rng.shuffle(cx_funcs)
        for cx_func in cx_funcs:
            if cx_func(other, rng):
                return True

        return False

    def _crossover_swap_node(self, other, rng):
        rng = np.random.default_rng(rng)
        idx = rng.integers(1,len(self.pipeline))

        self.pipeline[idx], other.pipeline[idx] = other.pipeline[idx], self.pipeline[idx]
        return True

    def _crossover_node(self, other, rng):
        rng = np.random.default_rng(rng)

        crossover_success = False
        for idx in range(len(self.pipeline)):
            if rng.random() < 0.5:
                if self.pipeline[idx].crossover(other.pipeline[idx], rng):
                    crossover_success = True

        return crossover_success

    def export_pipeline(self, **kwargs):
        return sklearn.pipeline.make_union(*[step.export_pipeline(**kwargs) for step in self.pipeline])

    def unique_id(self):
        l = [step.unique_id() for step in self.pipeline]
        l = ["FeatureUnion"] + l
        return TupleIndex(tuple(l))