You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ignite.apache.org by "Saurabh Chhajed (Jira)" <ji...@apache.org> on 2021/06/29 05:48:00 UTC
[jira] [Updated] (IGNITE-15024) Add Categorical Features Support
for Catboost Inference
[ https://issues.apache.org/jira/browse/IGNITE-15024?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Saurabh Chhajed updated IGNITE-15024:
-------------------------------------
Description:
Currently Catboost inference code in Ignite ML doesn't support Categorical features, Float features only. We can add support for categorical features for both regression and classification models with small changes. I would be glad to contribute the same.
Original Issue on which this feature was added - https://issues.apache.org/jira/browse/IGNITE-13714
Below is the code in CatBoostClassificationModel.java which needs to be updated to reflect categorical features support, I already have code patch written, can update after proper test cases and testing.
{code:java}
try {
double predict = model.predict(floatInput, model.getFeatureNames())
.get(0, 0);
// use formula based on https://github.com/catboost/benchmarks/blob/61d62512f751325a14dd885bb71f8c2dabf7e24b/quality_benchmarks/catboost_experiment.py#L77
return Math.pow(1 + Math.exp(-predict), -1);
} catch (CatBoostError e) {{code}
was:
Currently Catboost inference code in Ignite ML doesn't support Categorical features, Float features only. We can add support for categorical features for both regression and classification models with small changes. I would be glad to contribute the same.
Original Issue on which this feature was added - https://issues.apache.org/jira/browse/IGNITE-13714
> Add Categorical Features Support for Catboost Inference
> -------------------------------------------------------
>
> Key: IGNITE-15024
> URL: https://issues.apache.org/jira/browse/IGNITE-15024
> Project: Ignite
> Issue Type: Improvement
> Components: ml
> Reporter: Saurabh Chhajed
> Priority: Major
> Labels: newbie
>
> Currently Catboost inference code in Ignite ML doesn't support Categorical features, Float features only. We can add support for categorical features for both regression and classification models with small changes. I would be glad to contribute the same.
>
> Original Issue on which this feature was added - https://issues.apache.org/jira/browse/IGNITE-13714
> Below is the code in CatBoostClassificationModel.java which needs to be updated to reflect categorical features support, I already have code patch written, can update after proper test cases and testing.
> {code:java}
> try {
> double predict = model.predict(floatInput, model.getFeatureNames())
> .get(0, 0);
> // use formula based on https://github.com/catboost/benchmarks/blob/61d62512f751325a14dd885bb71f8c2dabf7e24b/quality_benchmarks/catboost_experiment.py#L77
> return Math.pow(1 + Math.exp(-predict), -1);
> } catch (CatBoostError e) {{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)