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

Jump to bottom

Base estimators other than default are not supported for AdaBoost #238

Closed
benbuleong opened this issue May 28, 2015 · 1 comment
Closed

Base estimators other than default are not supported for AdaBoost #238

benbuleong opened this issue May 28, 2015 · 1 comment
Assignees
@desilinguist
Labels
enhancement
Milestone
1.1

Comments

@benbuleong
Copy link
Member

Can we use SKLL's AdaBoost with LogisticRegression as the weak learner? We are interested to test out LogisticRegression instead of DecisionTreeClassifier.

In the config file, I set the base_estimator to be LogisticRegression as follows:

fixed_parameters=[{'base_estimator':'LogisticRegression', 'algorithm':'SAMME'}]

But I got the following error:

TypeError: Cannot clone object ''LogisticRegression'' (type <class 'str'>): it does not seem to be a scikit-learn estimator it does not implement a 'get_params' methods.

The input param is specified as a string but an object is needed. We can't do the conversion with the config file.
@desilinguist desilinguist added this to the 1.1 milestone Jun 29, 2015
@desilinguist desilinguist self-assigned this Jun 29, 2015
desilinguist added a commit that referenced this issue Jul 12, 2015
@desilinguist
Allow non-default base estimators for AdaBoost
6b06004 
- Correctly interpret the `base_estimator` fixed parameter for AdaBoostClassifiers and AdaBoostRegressors as objects instead of strings (#238).
- Add corresponding unit tests for both classification and regression.
- Update documentation.
@desilinguist desilinguist mentioned this issue Jul 14, 2015
Merged
@desilinguist
Copy link
Member

Addressed by #245.

desilinguist added a commit that referenced this issue Jul 19, 2015
@desilinguist @dan-blanchard
Allow non-default base estimators for AdaBoost
4135854 
- Correctly interpret the `base_estimator` fixed parameter for AdaBoostClassifiers and AdaBoostRegressors as objects instead of strings (#238).
- Add corresponding unit tests for both classification and regression.
- Update documentation.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@desilinguist desilinguist

Labels
enhancement
Projects
None yet
Milestone
1.1
Development

No branches or pull requests
2 participants
@desilinguist @benbuleong