Skip to content

add sklearn version to external version in sklearn flows, #742

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

Merged
mfeurer merged 6 commits into from
Jul 26, 2019
Merged

add sklearn version to external version in sklearn flows, #742

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
dcd8a35
add sklearn version to external version in sklearn flows,
amueller Jul 22, 2019
17f7242
use dummy classifier instead of linear regression
amueller Jul 22, 2019
f0e8214
use MyDummy instead of MyLR
amueller Jul 23, 2019
6eccbb5
typo aaah
amueller Jul 23, 2019
50065fa
all the typos
amueller Jul 23, 2019
32f58bf
use custom pipeline instead of dummy class because sklearn 0.18 can't…
amueller Jul 24, 2019
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
4 changes: 4 additions & 0 deletions openml/extensions/sklearn/extension.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,6 +432,7 @@ def _serialize_model(self, model: Any) -> OpenMLFlow:
# annotate a class of sklearn.svm.SVC() with the
# tag svm?
],
extension=self,
language='English',
# TODO fill in dependencies!
dependencies=dependencies)
Expand All @@ -455,9 +456,12 @@ def _get_external_version_string(
model_package_name, model_package_version_number,
)
openml_version = self._format_external_version('openml', openml.__version__)
sklearn_version = self._format_external_version('sklearn', sklearn.__version__)

external_versions = set()
external_versions.add(external_version)
external_versions.add(openml_version)
external_versions.add(sklearn_version)
for visitee in sub_components.values():
for external_version in visitee.external_version.split(','):
external_versions.add(external_version)
Expand Down
8 changes: 5 additions & 3 deletions openml/flows/flow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ def __init__(self, name, description, model, components, parameters,
dependencies, class_name=None, custom_name=None,
binary_url=None, binary_format=None,
binary_md5=None, uploader=None, upload_date=None,
flow_id=None, version=None):
flow_id=None, extension=None, version=None):
self.name = name
self.description = description
self.model = model
Expand Down Expand Up @@ -131,8 +131,10 @@ def __init__(self, name, description, model, components, parameters,
self.language = language
self.dependencies = dependencies
self.flow_id = flow_id

self._extension = get_extension_by_flow(self)
if extension is None:
Copy link
Contributor Author

@amueller amueller Jul 23, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you want me to remove this? Would work without it but I found it more explicit to directly give the extension.

Copy link
Collaborator

@mfeurer mfeurer Jul 24, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is totally fine by me.

self._extension = get_extension_by_flow(self)
else:
self._extension = extension

@property
def extension(self):
Expand Down
8 changes: 8 additions & 0 deletions tests/test_extensions/test_sklearn_extension/test_sklearn_extension.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1219,6 +1219,14 @@ def setUp(self):
################################################################################################
# Test methods for performing runs with this extension module

def test_run_model_on_task(self):
class MyPipe(sklearn.pipeline.Pipeline):
pass
task = openml.tasks.get_task(1)
pipe = MyPipe([('imp', Imputer()),
('dummy', sklearn.dummy.DummyClassifier())])
openml.runs.run_model_on_task(pipe, task)

def test_seed_model(self):
# randomized models that are initialized without seeds, can be seeded
randomized_clfs = [
Expand Down