How to use the fklearn.metrics.pd_extractors.extract function in fklearn
To help you get started, we’ve selected a few fklearn examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
nubank / fklearn / tests / metrics / test_pd_extractors.py View on Github 
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)# Define extractors
base_extractors = combined_evaluator_extractor(base_extractors=[
evaluator_extractor(evaluator_name="r2_evaluator__target"),
evaluator_extractor(evaluator_name="spearman_evaluator__target")
])
splitter_extractor = split_evaluator_extractor(split_col='RAD', split_values=[4.0, 5.0, 24.0],
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)splitter_extractor = split_evaluator_extractor(split_col='RAD', split_values=[4.0, 5.0, 24.0],
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)evaluator_extractor(evaluator_name="spearman_evaluator__target")
])
splitter_extractor = split_evaluator_extractor(split_col='RAD', split_values=[4.0, 5.0, 24.0],
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)])
splitter_extractor = split_evaluator_extractor(split_col='RAD', split_values=[4.0, 5.0, 24.0],
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)base_extractors = combined_evaluator_extractor(base_extractors=[
evaluator_extractor(evaluator_name="r2_evaluator__target"),
evaluator_extractor(evaluator_name="spearman_evaluator__target")
])
splitter_extractor = split_evaluator_extractor(split_col='RAD', split_values=[4.0, 5.0, 24.0],
base_extractor=base_extractors)
temporal_week_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y-%W', base_extractor=base_extractors)
temporal_year_splitter_extractor = temporal_split_evaluator_extractor(
time_col='time', time_format='%Y', base_extractor=base_extractors)
assert extract(cv_results, base_extractors).shape == (5, 9)
assert extract(cv_results, splitter_extractor).shape == (15, 10)
assert extract(tlc_results, base_extractors).shape == (12, 9)
assert extract(tlc_results, splitter_extractor).shape == (36, 10)
assert extract(sc_results, base_extractors).shape == (5, 9)
assert extract(sc_results, splitter_extractor).shape == (15, 10)
assert extract(fw_sc_results, base_extractors).shape == (3, 9)
assert extract(fw_sc_results, splitter_extractor).shape == (9, 10)
n_time_week_folds = len(df['time'].dt.strftime('%Y-%W').unique())
n_time_year_folds = len(df['time'].dt.strftime('%Y').unique())
assert temporal_week_splitter_extractor(temporal_week_results).shape == (n_time_week_folds, 3)
assert temporal_year_splitter_extractor(temporal_year_results).shape == (n_time_year_folds, 3)def get_avg_metric_from_extractor(logs: LogType, extractor: ExtractorFnType, metric_name: str) -> float:
metric_folds = extract(logs["validator_log"], extractor)
return metric_folds[metric_name].mean()
Popular fklearn functions
- fklearn.common_docstrings.learner_pred_fn_docstring
- fklearn.common_docstrings.learner_return_docstring
- fklearn.metrics.pd_extractors.evaluator_extractor
- fklearn.metrics.pd_extractors.extract
- fklearn.training.classification.logistic_classification_learner
- fklearn.training.classification.xgb_classification_learner
- fklearn.training.pipeline.build_pipeline
- fklearn.training.transformation.custom_transformer
- fklearn.training.transformation.ecdfer
- fklearn.training.utils.expand_features_encoded
- fklearn.training.utils.log_learner_time
- fklearn.tuning.stoppers.stop_by_iter_num
- fklearn.tuning.utils.get_avg_metric_from_extractor
- fklearn.tuning.utils.get_used_features
- fklearn.validation.evaluators.combined_evaluators
- fklearn.validation.evaluators.r2_evaluator
- fklearn.validation.evaluators.roc_auc_evaluator
- fklearn.validation.evaluators.split_evaluator
- fklearn.validation.validator.parallel_validator
- fklearn.validation.validator.validator