Repro:
from evalml.demos import load_breast_cancer
from evalml.pipelines import BinaryClassificationPipeline
from evalml.automl import AutoMLSearch
class PipeLine(BinaryClassificationPipeline):
component_graph = ["Drop Columns Transformer", "Random Forest Classifier"]
X , y = load_breast_cancer()
automl = AutoMLSearch(X, y, problem_type="binary", allowed_pipelines=[PipeLine],
pipeline_parameters={"Drop Columns Transformer": {"columns": ["mean texture"]}})
automl.search()
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/sources/evalml/evalml/pipelines/component_graph.py in instantiate(self, parameters)
77 try:
---> 78 new_component = component_class(**component_parameters, random_seed=self.random_seed)
79 except (ValueError, TypeError) as e:
~/sources/evalml/evalml/pipelines/components/transformers/column_selectors.py in __init__(self, columns, random_seed, **kwargs)
15 if columns and not isinstance(columns, list):
---> 16 raise ValueError(f"Parameter columns must be a list. Received {type(columns)}.")
17
ValueError: Parameter columns must be a list. Received <class 'str'>.
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-21-b4819258a317> in <module>
10 automl = AutoMLSearch(X, y, problem_type="binary", allowed_pipelines=[PipeLine],
11 pipeline_parameters={"Drop Columns Transformer": {"columns": ["mean texture"]}})
---> 12 automl.search()
~/sources/evalml/evalml/automl/automl_search.py in search(self, show_iteration_plot)
490 logger.info("Allowed model families: %s\n" % ", ".join([model.value for model in self.allowed_model_families]))
491 self.search_iteration_plot = None
--> 492 if self.plot:
493 self.search_iteration_plot = self.plot.search_iteration_plot(interactive_plot=show_iteration_plot)
494
~/sources/evalml/evalml/automl/automl_algorithm/iterative_algorithm.py in next_batch(self)
63 next_batch = []
64 if self._batch_number == 0:
---> 65 next_batch = [pipeline_class(parameters=self._transform_parameters(pipeline_class, {}), random_seed=self.random_seed)
66 for pipeline_class in self.allowed_pipelines]
67
~/sources/evalml/evalml/automl/automl_algorithm/iterative_algorithm.py in <listcomp>(.0)
63 next_batch = []
64 if self._batch_number == 0:
---> 65 next_batch = [pipeline_class(parameters=self._transform_parameters(pipeline_class, {}), random_seed=self.random_seed)
66 for pipeline_class in self.allowed_pipelines]
67
~/sources/evalml/evalml/pipelines/classification_pipeline.py in __init__(self, parameters, random_seed)
23 """
24 self._encoder = LabelEncoder()
---> 25 super().__init__(parameters, random_seed=random_seed)
26
27 def fit(self, X, y):
~/sources/evalml/evalml/pipelines/pipeline_base.py in __init__(self, parameters, random_seed)
77 else:
78 self._component_graph = ComponentGraph(component_dict=self.component_graph, random_seed=self.random_seed)
---> 79 self._component_graph.instantiate(parameters)
80
81 self.input_feature_names = {}
~/sources/evalml/evalml/pipelines/component_graph.py in instantiate(self, parameters)
80 self._is_instantiated = False
81 err = "Error received when instantiating component {} with the following arguments {}".format(component_name, component_parameters)
---> 82 raise ValueError(err) from e
83
84 component_instances[component_name] = new_component
ValueError: Error received when instantiating component Drop Columns Transformer with the following arguments {'columns': 'mean texture'}
The IterativeAlgorithm
selects the first element of the columns
list which is not the intended behavior.
This issue arises when IterativeAlgorithm
calls _transform_parameters
and tries to unpack the parameters. This code was added to address when the user passes in pipeline_parameters
to freeze or set the hyperparameters to a particular subset. For example:
params = {'Imputer': {'numeric_impute_strategy': ['median', 'most_frequent']},
'Decision Tree Regressor': {'max_depth': [17, 18, 19], 'max_features': Categorical(['auto'])},
'Elastic Net Regressor': {"alpha": Real(0, 0.5), "l1_ratio": (0.01, 0.02, 0.03)}}
automl = AutoMLSearch(X_train=X, y_train=y, problem_type='regression', pipeline_parameters=params, n_jobs=1)
automl.search()
In the first batch in _transform_parameters
, to handle list inputs such as max_depth
or numeric_impute_strategy
above, we simply choose or sample the first element in the list.
One way around this issue is thus to remove this line and enforce that lists aren't allowed.
@dsherry @freddyaboulton @bchen1116 @chukarsten FYI :)
@dsherry @chukarsten
In #1862 the plan is to add a Drop Columns Transformer
in _get_preprocessing_components
when an index column exists and then add those columns to self. pipeline_parameters
as well so this issue will blocking that as well.
Most helpful comment
@dsherry @chukarsten
In #1862 the plan is to add a
Drop Columns Transformer
in_get_preprocessing_components
when an index column exists and then add those columns toself. pipeline_parameters
as well so this issue will blocking that as well.