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.

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

Add SplineCV: a cross-validated Spline #185

Merged
merged 9 commits into from
May 14, 2019
Merged

Add SplineCV: a cross-validated Spline #185

merged 9 commits into from
May 14, 2019

Conversation

leouieda
Copy link
Member

The SplineCV class perfoms grid search cross-validation to auto-tune a Spline.
It uses cross_val_score to cross-validate and can be configured to run in parallel
with a dask.distributed.Client and take different scikit-learn splitters besides
KFold. Tested on the checkerboard function and add a gallery example using the
Texas temperature data.

Reminders

  • Run make format and make check to make sure the code follows the style guide.
  • Add tests for new features or tests that would have caught the bug that you're fixing.
  • Add new public functions/methods/classes to doc/api/index.rst and verde/__init__.py.
  • Write detailed docstrings for all functions/classes/methods.
  • If adding new functionality, add an example to the docstring, gallery, and/or tutorials.

@leouieda leouieda requested a review from santisoler May 14, 2019 04:54
@leouieda
Copy link
Member Author

@santisoler finally had some time to finish this PR. Would you mind taking a look at it?

I didn't edit the tutorial because I'm thinking that we should split the "Model Selection" tutorial into "Model Performance" and "Model Tuning". The first only focuses on running cross_val_score and friends. The second does the auto-tuning by hand and introduces SplineCV. What do you think?

@leouieda leouieda merged commit 803da81 into master May 14, 2019
@leouieda leouieda deleted the splinecv branch May 14, 2019 23:17
leouieda added a commit that referenced this pull request May 15, 2019
The previous model selection tutorial covered both scoring and automatic
tuning. Separate into two tutorials "Evaluating Performance" and "Model
Selection" so they are both shorter.
Include a section in "Model Selection" about the new `SplineCV` class
from #185.
@santisoler
Copy link
Member

Sorry for missing the review! Great to have this merged! Nice work @leouieda!

leouieda added a commit that referenced this pull request May 16, 2019
The previous model selection tutorial covered both scoring and automatic
tuning. Separate into two tutorials "Evaluating Performance" and "Model
Selection" so they are both shorter.
Include a section in "Model Selection" about the new `SplineCV` class
from #185.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants