three kinds of label VS. hyper parameter "task" binary

aksnzhy / xlearn

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

https://xlearn-doc.readthedocs.io/en/latest/index.html

Apache License 2.0

3.09k stars 519 forks source link

three kinds of label VS. hyper parameter "task" binary #197

Open HuXiLiFeng opened 5 years ago

HuXiLiFeng commented 5 years ago

Hi，i use a data which has three kinds of labels,such as 0,1,2, In xlearn, the hyper parameter “task” only can be "reg" or "binary", i choose “binary” and run the cod, it generates result as usual。 Why i use a dataset with three kinds of label and choose “binary”，there are no errors？ Are the final result reliable?

aksnzhy commented 5 years ago

Hi, Thank you . For now, xLearn can only solve the binary classification (0 or 1), if you have 0, 1, 2, xLearn will treat both 1 & 2 as 1. For multi-classificaiton problem , you can choose the package like xgboost and lightgbm.