How to test a prediction model?

[muhalim]

Hi,

How can I test a model (e.g. Random Forest) generated from training dataset to a testing (or new) dataset correctly?

[fmvizcaino]

Hi @muhalim ,

You have 2 tools developed by Alteryx and you can download from Alteryx gallery.

You can connect your test set and your model and check the outputs from both tools to have a better idea of what model to use or how well your model is doing against your test data.

Cross validation

https://gallery.alteryx.com/#!app/Cross-Validation-Tool/5d9267cc8a933711e4473950

Model comparison tool

https://gallery.alteryx.com/#!app/Model-Comparison/5d92741a826fd30b84537a27

Best,

Fernando Vizcaino

[huynv96]

You can use Score tool to test the model with new dataset

[diksha1107 · Accepted solution]

Hey @muhalim,

You can get the output of training or testing input data using the score tool as shown below. 

@huynv96  is also right but D input of score tool must be connected to Data and M input of score tool must be connected to O output of the Model.

Do let me know if you have any other doubt.

Warm Regards,

Diksha Adtani

[muhalim]

Thank you all