How can I use my own split method to divide train and valid?

timeseriesAI / tsai

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

https://timeseriesai.github.io/tsai/

Apache License 2.0

4.95k stars 625 forks source link

How can I use my own split method to divide train and valid? #729

Closed DennisShaw closed 10 months ago

DennisShaw commented 1 year ago

Dear developer, I see that the splits way given in the example and in the api documentation are the 'splits' provided by tsai, if I use KFold or StratifiedKFold in sklearn to split the training and validation sets, is there a function that can bring my own splits into TSClassifer? Thanks in advance!

oguiza commented 1 year ago

Hi @DennisShaw, In many examples, I'm using predefined public datasets that come with their own splits. However, tsai provides functionality to create your own splits. Which one you should use depends on the use case. I'd recommend you to take a look at the Splitting data section in the tsai docs.

oguiza commented 10 months ago

Closed due to lack of response.