yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-09-25 16:16:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

modify doc

Browse Source
This commit is contained in:
Andrea W 2023-01-26 14:31:54 +00:00
parent 297fc5ad7c
commit bdbba6e3bc
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
website/docs/Use-Cases/Task-Oriented-AutoML.md
View File

@ -365,16 +365,19 @@ For cross validation, you can also set `n_splits` of the number of folds. By def
#### Data split method #### Data split method
By default, flaml uses the following method to split the data: flaml relies on the provided task type to infer the default splitting strategy:
* stratified split for classification; * stratified split for classification;
* uniform split for regression; * uniform split for regression;
* time-based split for time series forecasting; * time-based split for time series forecasting;
* group-based split for learning to rank. * group-based split for learning to rank.
The data split method for classification can be changed into uniform split by setting `split_type="uniform"`. The data are shuffled when `split_type in ("uniform", "stratified")`. The data split method for classification can be changed into uniform split by setting `split_type="uniform"`. The data are shuffled when `split_type in ("uniform", "stratified")`.
For both classification and regression, time-based split can be enforced if the data are sorted by timestamps, by setting `split_type="time"`.
When `eval_method="cv"`, `split_type` can also be set as a custom splitter. It needs to be an instance of a derived class of scikit-learn For both classification and regression tasks more advanced split configurations are possible:
- time-based split can be enforced if the data are sorted by timestamps, by setting `split_type="time"`,
- group-based splits can be set by using `split_type="group"` while providing the group identifier for each sample through the `groups` argument.
More in general, `split_type` can also be set as a custom splitter object, when `eval_method="cv"`. It needs to be an instance of a derived class of scikit-learn
[KFold](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.KFold.html#sklearn.model_selection.KFold) [KFold](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.KFold.html#sklearn.model_selection.KFold)
and have ``split`` and ``get_n_splits`` methods with the same signatures. To disable shuffling, the splitter instance must contain the attribute `shuffle=False`. and have ``split`` and ``get_n_splits`` methods with the same signatures. To disable shuffling, the splitter instance must contain the attribute `shuffle=False`.