Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

API: update code for updated pytools.parallelization API #301

Merged
merged 4 commits into from
Sep 16, 2021
Merged

API: update code for updated pytools.parallelization API #301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e807661
API: expect Iterable not positional args in run_jobs() and run_queues()
j-ittner Sep 9, 2021
6a9467c
Merge branch '2.0.x' into api/run_jobs_run_queues_iterable
j-ittner Sep 10, 2021
b238bd1
API: rename JobQueue.collate() to .aggregate()
j-ittner Sep 10, 2021
9d9d292
Merge branch '2.0.x' into api/run_jobs_run_queues_iterable
j-ittner Sep 13, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/facet/crossfit/_crossfit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,7 +480,7 @@ def on_run(self) -> None:
if do_fit:
crossfit._reset_fit()

def collate(self, job_results: List[FitResult]) -> Optional[np.ndarray]:
def aggregate(self, job_results: List[FitResult]) -> Optional[np.ndarray]:
models, scores = zip(*job_results)

if do_fit:
Expand Down
32 changes: 15 additions & 17 deletions src/facet/inspection/_shap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,23 +275,21 @@ def _make_explainer(_model: T_LearnerPipelineDF) -> BaseExplainer:

else:
shap_df_per_split = JobRunner.from_parallelizable(self).run_jobs(
*(
Job.delayed(self._get_shap_for_split)(
model,
sample,
_make_explainer(model),
self.feature_index_,
self._convert_raw_shap_to_df,
self.get_multi_output_type(),
self._get_multi_output_names(model=model, sample=sample),
)
for model, sample in zip(
crossfit.models(),
(
sample.subsample(iloc=oob_split)
for _, oob_split in crossfit.splits()
),
)
Job.delayed(self._get_shap_for_split)(
model,
sample,
_make_explainer(model),
self.feature_index_,
self._convert_raw_shap_to_df,
self.get_multi_output_type(),
self._get_multi_output_names(model=model, sample=sample),
)
for model, sample in zip(
crossfit.models(),
(
sample.subsample(iloc=oob_split)
for _, oob_split in crossfit.splits()
),
)
)

Expand Down
2 changes: 1 addition & 1 deletion src/facet/selection/_selection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -518,7 +518,7 @@ def _rank_learners(
)

pipeline_scorings: List[np.ndarray] = list(
JobRunner.from_parallelizable(self).run_queues(*queues)
JobRunner.from_parallelizable(self).run_queues(queues)
)

for crossfit, pipeline_parameters, pipeline_scoring in zip(
Expand Down
24 changes: 10 additions & 14 deletions src/facet/simulation/_simulation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -383,12 +383,10 @@ def simulate_actuals(self) -> pd.Series:
y_mean = self.expected_output()

result: List[float] = JobRunner.from_parallelizable(self).run_jobs(
*(
Job.delayed(self._simulate_actuals)(
model, subsample.features, y_mean, self._simulate
)
for model, subsample in self._get_simulations()
Job.delayed(self._simulate_actuals)(
model, subsample.features, y_mean, self._simulate
)
for model, subsample in self._get_simulations()
)

return pd.Series(
Expand Down Expand Up @@ -455,16 +453,14 @@ def _simulate_feature_with_values(
simulation_means_and_sems_per_split: List[
Tuple[Sequence[float], Sequence[float]]
] = JobRunner.from_parallelizable(self).run_jobs(
*(
Job.delayed(UnivariateUpliftSimulator._simulate_values_for_split)(
model=model,
subsample=subsample,
feature_name=feature_name,
simulated_values=simulation_values,
simulate_fn=self._simulate,
)
for (model, subsample) in self._get_simulations()
Job.delayed(UnivariateUpliftSimulator._simulate_values_for_split)(
model=model,
subsample=subsample,
feature_name=feature_name,
simulated_values=simulation_values,
simulate_fn=self._simulate,
)
for (model, subsample) in self._get_simulations()
)

index_name: str
Expand Down