Expose shapley flag in mojo 2

[NidhiMehta]

Allow user to get shap predictions in from h2o-3 mojo model like we do in driverless(https://docs.h2o.ai/driverless-ai/1-10-lts/docs/userguide/scoring-mojo-scoring-pipeline.html?highlight=shapley%20mojo)

[wendycwong]

The user already can get the shap contributions from h2o-3 mojo model. You just need to add --predictContributions to the original command you use to invoke H2O-3 mojo.

[NidhiMehta]

can you share an equivalent h2o-3 command -
https://docs.h2o.ai/driverless-ai/1-10-lts/docs/userguide/scoring-mojo-scoring-pipeline.html?#a-quick-run

[NidhiMehta]

https://github.com/h2oai/mojo2/issues/1821

[wendycwong]

In h2o-3, first, use this to generate a mojo:

---

1. Open a terminal window and start python.

2. Run the following commands to build a simple GBM model.

The model, along with the h2o-genmodel.jar file will

then be downloaded to an experiment folder.

import h2o
from h2o.estimators.gbm import H2OGradientBoostingEstimator
h2o.init()
h2o_df = h2o.load_dataset("prostate.csv")
h2o_df["CAPSULE"] = h2o_df["CAPSULE"].asfactor()
model=H2OGradientBoostingEstimator(distribution="bernoulli",
ntrees=100,
max_depth=4,
learn_rate=0.1)
model.train(y="CAPSULE",
x=["AGE","RACE","PSA","GLEASON"],
training_frame=h2o_df)

Download the MOJO and the resulting h2o-genmodel.jar file

to a new experiment folder. Note that the h2o-genmodel.jar file

is a library that supports scoring and contains the required readers

and interpreters. This file is required when MOJO models are deployed

to production. Be sure to specify the entire path, not just the relative path.

modelfile = model.download_mojo(path="~/experiment/", get_genmodel_jar=True)
print("Model saved to " + modelfile)
Model saved to /Users/user/GBM_model_python_1475248925871_888.zip

[wendycwong]

Next, generate a java class and called it main.java as follows:

---

import java.io.;
import hex.genmodel.easy.RowData;
import hex.genmodel.easy.EasyPredictModelWrapper;
import hex.genmodel.easy.prediction.;
import hex.genmodel.MojoModel;

public class main {
public static void main(String[] args) throws Exception {
EasyPredictModelWrapper.Config config = new EasyPredictModelWrapper.Config()
.setModel(MojoModel.load("/Users/user/GBM_model_python_1475248925871_888.zip"))
.setEnableLeafAssignment(true)
.setEnableContributions(true); // note this is set to true to enable shapley values to be returned.
EasyPredictModelWrapper model = new EasyPredictModelWrapper(config);

RowData row = new RowData();
row.put("AGE", "68");
row.put("RACE", "2");
row.put("DCAPS", "2");
row.put("VOL", "0");
row.put("GLEASON", "6");

BinomialModelPrediction p = model.predictBinomial(row);
System.out.println("Has penetrated the prostatic capsule (1=yes; 0=no): " + p.label);
System.out.print("Class probabilities: ");
for (int i = 0; i < p.classProbabilities.length; i++) {
  if (i > 0) {
    System.out.print(",");
  }
  System.out.print(p.classProbabilities[i]);
}

System.out.println("Leaf node assignments: ");
for (int i=0; i < p.leafNodeAssignments.length; i++) {
  if (i > 0) {
    System.out.print(p.leafNodeAssignments[i]);
  }
}
System.out.println("");

System.out.println("Shapley contributions: ");
for (int i=0; i < p.contributions.length; i++) {
  if (i > 0) {
    System.out.print(", ");
  }
  System.out.print(model.getContributionNames()[i] + ": " + p.contributions[i]);
}
System.out.println("");

}
}

[wendycwong]

Next, compile the code as follows:

javac -cp /Users/wendycwong/h2o-3/h2o-web/src/main/resources/www/3/h2o-genmodel.jar -J-Xms2g main.java

then copy over the h2o-genmodel.jar into current directory (~/experiment)

cp /Users/wendycwong/h2o-3/h2o-web/src/main/resources/www/3/h2o-genmodel.jar .

then run the code to generate in this case both the leaf node assignment and the shapley values:

java -cp .:h2o-genmodel.jar main

the result looks like this:

[wendycwong]

Is this clear for you? @NidhiMehta

[NidhiMehta]

yes thanks Wendy. @sh1ng will reach out if need more info