add randomizedSearchCV example#14157
Conversation
|
related to #3846 the tests are failing |
|
Okay. Re-running. |
thomasjpfan
left a comment
There was a problem hiding this comment.
Please remove the checkpoint files and revert the change in .gitignore. Thank you for the PR!
|
Thanks @thomasjpfan |
Co-Authored-By: Thomas J Fan <thomasjpfan@gmail.com>
…into isaac-scikit
|
@Kasre96 You still have the .ipynb_checkpoint directory. You can remove it and make sure to not add it when doing |
glemaitre
left a comment
There was a problem hiding this comment.
Thanks for your contribution. This is super useful.
|
I've refined the example and I hope it passes. |
sklearn/model_selection/_search.py
Outdated
| >>> from scipy.stats import uniform | ||
| >>> iris = load_iris() | ||
| >>> logistic = LogisticRegression(max_iter=200) | ||
| >>> hyperparameters = dict(C=uniform(loc=0, scale=4), |
There was a problem hiding this comment.
| >>> hyperparameters = dict(C=uniform(loc=0, scale=4), | |
| >>> hyperparameters = dict(C=rng.uniform(loc=0, scale=4), |
There was a problem hiding this comment.
Maybe name this distributions?
|
fixed @glemaitre |
glemaitre
left a comment
There was a problem hiding this comment.
I just pushed a nitpick (reordering an import). I will merge it when it CIs are green.
|
Okay. Thank you. |
sklearn/model_selection/_search.py
Outdated
| >>> from scipy.stats import uniform | ||
| >>> iris = load_iris() | ||
| >>> logistic = LogisticRegression(max_iter=200) | ||
| >>> hyperparameters = dict(C=uniform(loc=0, scale=4), |
There was a problem hiding this comment.
Maybe name this distributions?
Are they distribution or just parameters? I find weird to call distrbutions when there is the |
|
It is a distribution (implied uniform) over penalties |
|
OK fair enough :)
…On Wed, 26 Jun 2019 at 11:39, Joel Nothman ***@***.***> wrote:
It is a distribution (implied uniform) over penalties
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#14157?email_source=notifications&email_token=ABY32P62KOQOVBG4ZURFUMTP4M2OTA5CNFSM4H2WYRP2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODYS6QRY#issuecomment-505800775>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABY32P3P2WWQEBDNMQHV4DLP4M2OTANCNFSM4H2WYRPQ>
.
--
Guillaume Lemaitre
INRIA Saclay - Parietal team
Center for Data Science Paris-Saclay
https://glemaitre.github.io/
|
|
One last comment @Kasre96 #14157 (comment),
otherwise this is ready to be merged. Thanks! |
|
@rth I'm following through and noting all suggestions and changes. I'm sure they'll in effectiveness for my future PRs. |
I meant that it would be necessary to address the above comment by jnothman for this PR to be merged. Thanks! |
|
@Kasre96 I made the small changes and I merged. Thanks for your contribution!!! |
|
Thanks @glemaitre |
Reference Issues/PRs
What does this implement/fix? Explain your changes.
The commit adds an example to the class
sklearn.model_selection.RandomizedSearchCVAny other comments?