GH-6723 AdaBoost API

h2o-algos/src/main/java/hex/api/RegisterAlgos.java

@@ -38,7 +38,8 @@ public void registerEndPoints(RestApiContext context) {
             new hex.tree.uplift.UpliftDRF    (true),
             new hex.modelselection.ModelSelection (true),
             new hex.isotonic    .IsotonicRegression(true),
-            new hex.tree.dt      .DT         (true)
+            new hex.tree.dt      .DT         (true),
+            new hex.adaboost.     AdaBoost   (true)
     };
 
     // "Word2Vec", "Example", "Grep"

h2o-algos/src/main/java/hex/schemas/AdaBoostModelV3.java

@@ -0,0 +1,30 @@
+package hex.schemas;
+
+import hex.adaboost.AdaBoostModel;
+import water.api.schemas3.ModelOutputSchemaV3;
+import water.api.schemas3.ModelSchemaV3;
+
+public class AdaBoostModelV3 extends ModelSchemaV3<AdaBoostModel,
+        AdaBoostModelV3,
+        AdaBoostModel.AdaBoostParameters,
+        AdaBoostV3.AdaBoostParametersV3,
+        AdaBoostModel.AdaBoostOutput,
+        AdaBoostModelV3.AdaBoostModelOutputV3> {
+
+  public static final class AdaBoostModelOutputV3 extends ModelOutputSchemaV3<AdaBoostModel.AdaBoostOutput, AdaBoostModelOutputV3> {
+      // nothing
+  }
+
+  public AdaBoostV3.AdaBoostParametersV3 createParametersSchema() { return new AdaBoostV3.AdaBoostParametersV3(); }
+  public AdaBoostModelOutputV3 createOutputSchema() { return new AdaBoostModelOutputV3(); }
+
+  //==========================
+  // Custom adapters go here
+
+  // Version&Schema-specific filling into the impl
+  @Override public AdaBoostModel createImpl() {
+    AdaBoostV3.AdaBoostParametersV3 p = this.parameters;
+    AdaBoostModel.AdaBoostParameters parms = p.createImpl();
+    return new AdaBoostModel( model_id.key(), parms, new AdaBoostModel.AdaBoostOutput(null) );
+  }
+}

h2o-algos/src/main/java/hex/schemas/AdaBoostV3.java

@@ -0,0 +1,41 @@
+package hex.schemas;
+
+import hex.adaboost.AdaBoost;
+import hex.adaboost.AdaBoostModel;
+import water.api.API;
+import water.api.schemas3.ModelParametersSchemaV3;
+
+public class AdaBoostV3 extends ModelBuilderSchema<
+        AdaBoost,
+        AdaBoostV3, 
+        AdaBoostV3.AdaBoostParametersV3> {
+
+    public static final class AdaBoostParametersV3 extends ModelParametersSchemaV3<AdaBoostModel.AdaBoostParameters, AdaBoostParametersV3> {
+        static public String[] fields = new String[]{
+                "model_id",
+                "training_frame",
+                "ignored_columns",
+                "ignore_const_cols",
+                "categorical_encoding",
+                "weights_column",
+
+                // AdaBoost specific
+                "nlearners",
+                "weak_learner",
+                "learn_rate",
+                "seed",
+        };
+
+        @API(help = "Number of AdaBoost weak learners.", gridable = true)
+        public int nlearners;
+
+        @API(help = "Choose a weak learner type. Defaults to AUTO, which means DRF.", gridable = true, values = {"AUTO", "DRF", "GLM", "GBM"})
+        public AdaBoostModel.Algorithm weak_learner;
+
+        @API(help="Learning rate (from 0.0 to 1.0)", gridable = true)
+        public double learn_rate;
+
+        @API(help = "Seed for pseudo random number generator (if applicable)", gridable = true)
+        public long seed;
+    }
+}

h2o-algos/src/main/resources/META-INF/services/water.api.Schema

@@ -114,3 +114,7 @@ hex.schemas.UpliftDRFModelV3
 hex.schemas.UpliftDRFModelV3$UpliftDRFModelOutputV3
 hex.schemas.UpliftDRFV3
 hex.schemas.UpliftDRFV3$UpliftDRFParametersV3
+hex.schemas.AdaBoostModelV3
+hex.schemas.AdaBoostModelV3$AdaBoostModelOutputV3
+hex.schemas.AdaBoostV3
+hex.schemas.AdaBoostV3$AdaBoostParametersV3

h2o-bindings/bin/custom/R/gen_adaboost.py

@@ -0,0 +1,41 @@
+extensions = dict(
+    skip_default_set_params_for=['training_frame', 'ignored_columns', 'response_column', 
+                                 'max_confusion_matrix_size', 'distribution', 'offset_column'],
+    set_required_params="""
+parms$training_frame <- training_frame
+args <- .verify_dataxy(training_frame, x, y)
+parms$ignored_columns <- args$x_ignore
+parms$response_column <- args$y
+""",
+)
+
+
+doc = dict(
+    preamble="""
+Build an AdaBoost model
+
+Builds an AdaBoost model on an H2OFrame.
+""",
+    returns="""
+Creates a \linkS4class{H2OModel} object of the right type.
+""",
+    seealso="""
+\code{\link{predict.H2OModel}} for prediction
+""",
+    examples="""
+library(h2o)
+h2o.init()
+
+# Import the airlines dataset
+f <- "https://s3.amazonaws.com/h2o-public-test-data/smalldata/prostate/prostate.csv"
+data <- h2o.importFile(f)
+
+# Set predictors and response; set response as a factor
+data["CAPSULE"] <- as.factor(data["CAPSULE"])
+predictors <- c("AGE","RACE","DPROS","DCAPS","PSA","VOL","GLEASON")
+response <- "CAPSULE"
+
+# Train the AdaBoost model
+h2o_adaboost <- h2o.adaBoost(x = predictors, y = response, training_frame = data, seed = 1234)
+"""
+)

h2o-bindings/bin/custom/python/gen_adaboost.py

@@ -0,0 +1,8 @@
+options = dict(
+)
+
+doc = dict(
+    __class__="""
+Builds an AdaBoost model
+"""
+)

h2o-bindings/bin/gen_R.py

@@ -272,6 +272,7 @@ def algo_to_modelname(algo):
     if algo == "gam": return "Generalized Additive Model"
     if algo == "modelselection": return "Model Selection"
     if algo == "infogram": return "Infogram"
+    if algo == "adaboost": return "AdaBoost Model"
     return algo
 
 
@@ -347,6 +348,7 @@ def main():
         if name == "stackedensemble": module = "stackedEnsemble"
         if name == "pca": module = "prcomp"
         if name == "modelselection": module = "modelSelection"
+        if name == "adaboost": module = "adaBoost"
         bi.vprint("Generating model: " + name)
         bi.write_to_file("%s.R" % file_name, gen_module(mb, name, module))
 

h2o-bindings/bin/gen_python.py

@@ -351,6 +351,7 @@ def algo_to_classname(algo):
     if algo == "rulefit": return "H2ORuleFitEstimator"
     if algo == "modelselection": return "H2OModelSelectionEstimator"
     if algo == "isotonicregression": return "H2OIsotonicRegressionEstimator"
+    if algo == "adaboost": return "H2OAdaBoostEstimator"
     return "H2O" + algo.capitalize() + "Estimator"
 
 

h2o-py/docs/modeling.rst

@@ -8,6 +8,12 @@ Modeling In H2O
 Supervised
 ++++++++++
 
+:mod:`H2OAdaBoostEstimator`
+---------------------------
+.. autoclass:: h2o.estimators.adaboost.H2OAdaBoostEstimator
+    :show-inheritance:
+    :members:
+
 :mod:`H2OANOVAGLMEstimator`
 ---------------------------
 .. autoclass:: h2o.estimators.anovaglm.H2OANOVAGLMEstimator

h2o-py/h2o/estimators/__init__.py

@@ -7,6 +7,7 @@
 import inspect
 import sys
 
+from .adaboost import H2OAdaBoostEstimator
 from .aggregator import H2OAggregatorEstimator
 from .anovaglm import H2OANOVAGLMEstimator
 from .coxph import H2OCoxProportionalHazardsEstimator
@@ -60,12 +61,13 @@ def create_estimator(algo, **params):
 
 __all__ = (
     "create_estimator",
-    "H2OAggregatorEstimator", "H2OANOVAGLMEstimator", "H2OCoxProportionalHazardsEstimator", "H2ODecisionTreeEstimator",
-    "H2OAutoEncoderEstimator", "H2ODeepLearningEstimator", "H2OEstimator", "H2OExtendedIsolationForestEstimator",
-    "H2OGeneralizedAdditiveEstimator", "H2OGradientBoostingEstimator", "H2OGenericEstimator",
-    "H2OGeneralizedLinearEstimator", "H2OGeneralizedLowRankEstimator", "H2OInfogram", "H2OIsolationForestEstimator",
-    "H2OIsotonicRegressionEstimator", "H2OKMeansEstimator", "H2OModelSelectionEstimator", "H2ONaiveBayesEstimator",
-    "H2OPrincipalComponentAnalysisEstimator", "H2OSupportVectorMachineEstimator", "H2ORandomForestEstimator",
-    "H2ORuleFitEstimator", "H2OStackedEnsembleEstimator", "H2OSingularValueDecompositionEstimator",
-    "H2OTargetEncoderEstimator", "H2OUpliftRandomForestEstimator", "H2OWord2vecEstimator", "H2OXGBoostEstimator"
+    "H2OAdaBoostEstimator", "H2OAggregatorEstimator", "H2OANOVAGLMEstimator", "H2OCoxProportionalHazardsEstimator",
+    "H2ODecisionTreeEstimator", "H2OAutoEncoderEstimator", "H2ODeepLearningEstimator", "H2OEstimator",
+    "H2OExtendedIsolationForestEstimator", "H2OGeneralizedAdditiveEstimator", "H2OGradientBoostingEstimator",
+    "H2OGenericEstimator", "H2OGeneralizedLinearEstimator", "H2OGeneralizedLowRankEstimator", "H2OInfogram",
+    "H2OIsolationForestEstimator", "H2OIsotonicRegressionEstimator", "H2OKMeansEstimator", "H2OModelSelectionEstimator",
+    "H2ONaiveBayesEstimator", "H2OPrincipalComponentAnalysisEstimator", "H2OSupportVectorMachineEstimator",
+    "H2ORandomForestEstimator", "H2ORuleFitEstimator", "H2OStackedEnsembleEstimator",
+    "H2OSingularValueDecompositionEstimator", "H2OTargetEncoderEstimator", "H2OUpliftRandomForestEstimator",
+    "H2OWord2vecEstimator", "H2OXGBoostEstimator"
 )