Random Forest PMML output

[deepak_kanaka]

Hi All,

@AlexanderFillbrunn, @mlauber71,

I have done the Random Forest, now I need to get that output in PMML file.

Please help me here with workflow also in the PMML output I want probability of 1.

[mlauber71]

I think you would have to elaborate further what you want to do. A sample workflow with random forest can be found here

Training a Random Forest – knime

Then you might want to consider what @nemad wrote in this entry

Random Forest classification model to PMML Error

Hello @Einavtam, regarding your questions: This seems to be a bug in the PMML Ensemble Predictor since the PMML standard states that the probabilities in case of the multiple model method “Majority” should be calculated according to the distribution of votes. Note that this means that the probabilities should be available if you export the model to a different platform. I guess by the performance you mean runtime, right? This is to be expected because a PMML document is just an XML file which…

From my experience complex PMML models tend not to be too stable besides the claim of offering wide range compatibility.

[deepak_kanaka]

@mlauber71,

Thanks for your reply. Can you please suggest how to get that output in PMML file?

Also, if you extract output in PMML will I get decision boundaries (either zero or one) or probabilities as prediction?

[mlauber71]

@deepak_kanaka

Also, if you extract output in PMML will I get decision boundaries (either zero or one) or probabilities as prediction?

The

PMML Compiling Predictor

offers the possibility of extracting probabilities although I have experienced problems with the PMML models from the mentioned example. This could be because with the conversion to PMML a relative modest model increases in size dramatically.

[deepak_kanaka]

Thank you…