Hi Organizers,
In the provided docker baseline model, the _run_model.py_ file only loads existing models and makes predictions. Is it fine for you to provide codes on how you preprocess data and extract features?
Thanks,
Jifan
Created by Jifan Gao ggggfan Hi @jgolob and @toskotsky ,
Just wonder is it supposed to use _pt_ra_5e_1_test_early_ instead of _pt_ra_5e_1_test_ when predicting early preterm at line 4 in cell #17 in the baseline notebook?
Best,
Jifan That's helpful! Thank you so much.
Best,
Jifan Greetings.
After discussion we have decided to provide the python code used to generate the baseline mode as a [jupyter notebook](https://github.com/jgolob/ptb_microbiome_samples/blob/main/Random%20Forest%201.4-ForChallenge.ipynb).
This is a very basic random forest model but does demonstrate the use of the phylotypes specifically. The advice (and example) should be taken as not definitive but rather sketching out a way to approach this data to build a model.
Thank you!
Jonathan Golob on behalf of the 'Preterm Birth Prediction - Microbiome DREAM Challenge' team
Hi @ggggfan,
Just wanted to let you know that your question is one that our team is actively discussing. We'll provide an answer for you as soon as we can.
Thanks so much,
Tomiko on behalf of the 'Preterm Birth Prediction - Microbiome DREAM Challenge' team