Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@gkirgizov
Copy link
Collaborator

This commit adds 2 functions: get_pipeline_evaluator and get_pipeline_fitness for straightforward fitness evaluation of pipelines

@gkirgizov gkirgizov added the enhancement New feature or request label May 3, 2023
@aim-pep8-bot
Copy link

aim-pep8-bot commented May 3, 2023

Hello @gkirgizov! Thanks for updating this PR. We checked the lines you've touched for PEP 8 issues, and found:

Line 1:1: F401 '.data_objective_eval.PipelineObjectiveEvaluate' imported but unused
Line 1:1: F401 '.data_objective_eval.get_pipeline_evaluator' imported but unused
Line 1:1: F401 '.data_objective_eval.get_pipeline_fitness' imported but unused
Line 2:1: F401 '.data_source_splitter.DataSource' imported but unused
Line 3:1: F401 '.metrics_objective.MetricsObjective' imported but unused

Comment last updated at 2023-05-04 11:12:52 UTC

@GrigoriJasnovidov
Copy link
Collaborator

При запуске get_pipeline_fitness с дефолтными параметрами cv_folds=None и validation_blocks=None все работает хорошо. При другом наборе, например cv_folds=1, validation_blocks=10 (или None) функция возвращает значение sys.maxsize. Еще после этого исходный пайплайн при запуске метода fit() часто выдает что-то вроде

ValueError: X has 2 features, but Ridge is expecting 10 features as input.

Для избегания таких ошибок может быть стоит работать с копией pipeline?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants