search

microsoft / LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
https://lightgbm.readthedocs.io/en/latest/
MIT License
16.69k stars 3.83k forks source link

Regression coefficient for LGBMRegressor #5558

Closed Lucienxhh closed 2 years ago

Lucienxhh commented 2 years ago

Summary

I use lightgbm.LGBMRegressor for regression prediction. however, i cannot find any API for regression coefficient.

Motivation

Provide regression coefficient for lightgbm.LGBMRegressor, as the name LGBMRegressor implies.

jameslamb commented 2 years ago

Thanks for using LightGBM!

LightGBM does not fit a regression model like y = mx + b the way you may be used to with something like linear regression. Instead, it fits a sequence of trees.

So there is not a concept of "regression coefficients" for LightGBM the way that you might be used to with other types of regression.

If you're new to gradient boosting with trees, XGBoost's docs have an excellent guide: https://xgboost.readthedocs.io/en/stable/tutorials/model.html.

For LightGBM-specific details, see https://lightgbm.readthedocs.io/en/v3.3.2/Features.html.

Lucienxhh commented 2 years ago

thanks a lot, i get it.

github-actions[bot] commented 1 year ago

This issue has been automatically locked since there has not been any recent activity since it was closed. To start a new related discussion, open a new issue at https://github.com/microsoft/LightGBM/issues including a reference to this.