modifyCode: Modify production code to be model specific
In XanderHorn/autoML: Automated machine learning

Description Usage Arguments Value Author(s) Examples

Modifies the production code generated by the autoPreProcess function to be specific to a trained model object. Results in less code and only uses the features used in the final trained model. The saveCode function can then be used to save the code.

1	modifyCode(trainedModel, edaFrame, codeFrame)

`trainedModel`	[mlrObject \| Required] A trained model from the mlr R library or models returned from autoML / autoLearn
`edaFrame`	[data.frame \| Required] EDA frame returned by autoPreProcess
`codeFrame`	[data.frame \| Required] Code frame returned by autoPreProcess

Data.frame object containing the modified code

Xander Horn

1
2
3

res <- autoPreProcess(train = iris, target = "Species")
models <- autoLearn(train = res$data, target = "Species", trainMode = "reduced")
code <- modifyCode(trainedModel = models$RandomForest_reduced$model, edaFrame = res$dataSummary, codeFrame = res$code)