Enable EnsembleClassifier and EnsembleRegressor

src/DotNetBridge/Bridge.cs

@@ -314,7 +314,7 @@ private static unsafe int GenericExec(EnvironmentBlock* penv, sbyte* psz, int cd
             env.ComponentCatalog.RegisterAssembly(typeof(CategoricalCatalog).Assembly); // ML.Transforms
             env.ComponentCatalog.RegisterAssembly(typeof(FastTreeRegressionTrainer).Assembly); // ML.FastTree
 
-            //env.ComponentCatalog.RegisterAssembly(typeof(EnsembleModelParameters).Assembly); // ML.Ensemble
+            env.ComponentCatalog.RegisterAssembly(typeof(EnsembleModelParameters).Assembly); // ML.Ensemble
             env.ComponentCatalog.RegisterAssembly(typeof(KMeansModelParameters).Assembly); // ML.KMeansClustering
             env.ComponentCatalog.RegisterAssembly(typeof(PcaModelParameters).Assembly); // ML.PCA
             env.ComponentCatalog.RegisterAssembly(typeof(CVSplit).Assembly); // ML.EntryPoints

src/python/nimbusml.pyproj

@@ -46,6 +46,15 @@
     <Compile Include="nimbusml\ensemble\booster\gbdt.py" />
     <Compile Include="nimbusml\ensemble\booster\goss.py" />
     <Compile Include="nimbusml\ensemble\booster\__init__.py" />
+    <Compile Include="nimbusml\ensemble\feature_selector\allfeatureselector.py" />
+    <Compile Include="nimbusml\ensemble\feature_selector\randomfeatureselector.py" />
+    <Compile Include="nimbusml\ensemble\feature_selector\__init__.py" />
+    <Compile Include="nimbusml\ensemble\subset_selector\allinstanceselector.py" />
+    <Compile Include="nimbusml\ensemble\subset_selector\bootstrapselector.py" />
+    <Compile Include="nimbusml\ensemble\subset_selector\randompartitionselector.py" />
+    <Compile Include="nimbusml\ensemble\subset_selector\__init__.py" />
+    <Compile Include="nimbusml\ensemble\ensembleclassifier.py" />
+    <Compile Include="nimbusml\ensemble\ensembleregressor.py" />
     <Compile Include="nimbusml\ensemble\fastforestbinaryclassifier.py" />
     <Compile Include="nimbusml\ensemble\fastforestregressor.py" />
     <Compile Include="nimbusml\ensemble\fasttreesbinaryclassifier.py" />
@@ -68,13 +77,16 @@
     <Compile Include="nimbusml\examples\ColumnSelector.py" />
     <Compile Include="nimbusml\examples\CountSelector.py" />
     <Compile Include="nimbusml\examples\CV.py" />
+    <Compile Include="nimbusml\examples\EnsembleClassifier.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\AveragedPerceptronBinaryClassifier_infert_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\Binner_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\BootStrapSample_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\CharTokenizer_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\ColumnConcatenator_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\ColumnDuplicator_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\Concat_Drop_Select_Columns_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\EnsembleClassifier_iris_df.py" />
+    <Compile Include="nimbusml\examples\examples_from_dataframe\EnsembleRegressor_airquality_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\FactorizationMachineBinaryClassifier_infert_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\FastForestBinaryClassifier_infert_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\FastForestRegressor_airquality_df.py" />
@@ -126,6 +138,7 @@
     <Compile Include="nimbusml\examples\examples_from_dataframe\WordEmbedding_df.py" />
     <Compile Include="nimbusml\examples\examples_from_dataframe\__init__.py" />
     <Compile Include="nimbusml\examples\Exp.py" />
+    <Compile Include="nimbusml\examples\EnsembleRegressor.py" />
     <Compile Include="nimbusml\examples\FactorizationMachineBinaryClassifier.py" />
     <Compile Include="nimbusml\examples\FastForestBinaryClassifier.py" />
     <Compile Include="nimbusml\examples\FastForestRegressor.py" />
@@ -212,6 +225,15 @@
     <Compile Include="nimbusml\internal\core\ensemble\booster\gbdt.py" />
     <Compile Include="nimbusml\internal\core\ensemble\booster\goss.py" />
     <Compile Include="nimbusml\internal\core\ensemble\booster\__init__.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\feature_selector\allfeatureselector.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\feature_selector\randomfeatureselector.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\feature_selector\__init__.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\subset_selector\allinstanceselector.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\subset_selector\bootstrapselector.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\subset_selector\randompartitionselector.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\subset_selector\__init__.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\ensembleclassifier.py" />
+    <Compile Include="nimbusml\internal\core\ensemble\ensembleregressor.py" />
     <Compile Include="nimbusml\internal\core\ensemble\gambinaryclassifier.py" />
     <Compile Include="nimbusml\internal\core\ensemble\gamregressor.py" />
     <Compile Include="nimbusml\internal\core\ensemble\lightgbmranker.py" />
@@ -287,6 +309,8 @@
     <Compile Include="nimbusml\internal\entrypoints\timeseriesprocessingentrypoints_ssaforecasting.py" />
     <Compile Include="nimbusml\internal\entrypoints\timeseriesprocessingentrypoints_ssaspikedetector.py" />
     <Compile Include="nimbusml\internal\entrypoints\trainers_averagedperceptronbinaryclassifier.py" />
+    <Compile Include="nimbusml\internal\entrypoints\trainers_ensembleclassification.py" />
+    <Compile Include="nimbusml\internal\entrypoints\trainers_ensembleregression.py" />
     <Compile Include="nimbusml\internal\entrypoints\trainers_fastforestbinaryclassifier.py" />
     <Compile Include="nimbusml\internal\entrypoints\trainers_fastforestregressor.py" />
     <Compile Include="nimbusml\internal\entrypoints\trainers_fasttreebinaryclassifier.py" />
@@ -411,13 +435,18 @@
     <Compile Include="nimbusml\internal\entrypoints\_ensemblemulticlassoutputcombiner_multivoting.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensemblemulticlassoutputcombiner_multiweightedaverage.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensemblemulticlasssubmodelselector_allselectormulticlass.py" />
+    <Compile Include="nimbusml\internal\entrypoints\_ensemblemulticlasssubmodelselector_bestdiverseselectormulticlass.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensemblemulticlasssubmodelselector_bestperformanceselectormulticlass.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressiondiversitymeasure_regressiondisagreementdiversitymeasure.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionoutputcombiner_average.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionoutputcombiner_median.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionoutputcombiner_regressionstacking.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionsubmodelselector_allselector.py" />
+    <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionsubmodelselector_bestdiverseselectorregression.py" />
     <Compile Include="nimbusml\internal\entrypoints\_ensembleregressionsubmodelselector_bestperformanceregressionselector.py" />
+    <Compile Include="nimbusml\internal\entrypoints\_ensemblesubsetselector_allinstanceselector.py" />
+    <Compile Include="nimbusml\internal\entrypoints\_ensemblesubsetselector_bootstrapselector.py" />
+    <Compile Include="nimbusml\internal\entrypoints\_ensemblesubsetselector_randompartitionselector.py" />
     <Compile Include="nimbusml\internal\entrypoints\_fasttreetrainer_fasttreebinaryclassification.py" />
     <Compile Include="nimbusml\internal\entrypoints\_fasttreetrainer_fasttreeranking.py" />
     <Compile Include="nimbusml\internal\entrypoints\_fasttreetrainer_fasttreeregression.py" />
@@ -561,9 +590,7 @@
     <Compile Include="nimbusml\preprocessing\normalization\minmaxscaler.py" />
     <Compile Include="nimbusml\preprocessing\normalization\__init__.py" />
     <Compile Include="nimbusml\preprocessing\schema\columnconcatenator.py" />
-    <Compile Include="nimbusml\preprocessing\schema\columndropper.py">
-      <SubType>Code</SubType>
-    </Compile>
+    <Compile Include="nimbusml\preprocessing\schema\columndropper.py" />
     <Compile Include="nimbusml\preprocessing\schema\columnduplicator.py" />
     <Compile Include="nimbusml\preprocessing\schema\columnselector.py" />
     <Compile Include="nimbusml\preprocessing\schema\typeconverter.py" />
@@ -751,6 +778,8 @@
     <Folder Include="nimbusml\decomposition\" />
     <Folder Include="nimbusml\ensemble\" />
     <Folder Include="nimbusml\ensemble\booster\" />
+    <Folder Include="nimbusml\ensemble\feature_selector\" />
+    <Folder Include="nimbusml\ensemble\subset_selector\" />
     <Folder Include="nimbusml\examples\" />
     <Folder Include="nimbusml\examples\examples_from_dataframe\" />
     <Folder Include="nimbusml\feature_extraction\" />
@@ -766,6 +795,8 @@
     <Folder Include="nimbusml\internal\core\decomposition\" />
     <Folder Include="nimbusml\internal\core\ensemble\" />
     <Folder Include="nimbusml\internal\core\ensemble\booster\" />
+    <Folder Include="nimbusml\internal\core\ensemble\feature_selector\" />
+    <Folder Include="nimbusml\internal\core\ensemble\subset_selector\" />
     <Folder Include="nimbusml\internal\core\feature_extraction\" />
     <Folder Include="nimbusml\internal\core\feature_extraction\categorical\" />
     <Folder Include="nimbusml\internal\core\feature_extraction\image\" />

src/python/nimbusml/ensemble/__init__.py

@@ -1,3 +1,5 @@
+from .ensembleclassifier import EnsembleClassifier
+from .ensembleregressor import EnsembleRegressor
 from .fastforestbinaryclassifier import FastForestBinaryClassifier
 from .fastforestregressor import FastForestRegressor
 from .fasttreesbinaryclassifier import FastTreesBinaryClassifier
@@ -11,6 +13,8 @@
 from .lightgbmregressor import LightGbmRegressor
 
 __all__ = [
+    'EnsembleClassifier',
+    'EnsembleRegressor',
     'FastForestBinaryClassifier',
     'FastForestRegressor',
     'FastTreesBinaryClassifier',

src/python/nimbusml/ensemble/ensembleclassifier.py

@@ -0,0 +1,127 @@
+# --------------------------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------------------------------------
+# - Generated by tools/entrypoint_compiler.py: do not edit by hand
+"""
+EnsembleClassifier
+"""
+
+__all__ = ["EnsembleClassifier"]
+
+
+from sklearn.base import ClassifierMixin
+
+from ..base_predictor import BasePredictor
+from ..internal.core.ensemble.ensembleclassifier import \
+    EnsembleClassifier as core
+from ..internal.utils.utils import trace
+from .feature_selector import AllFeatureSelector
+from .subset_selector import BootstrapSelector
+
+
+class EnsembleClassifier(core, BasePredictor, ClassifierMixin):
+    """
+    **Description**
+        Train multiclass ensemble.
+
+    :param feature: see `Columns </nimbusml/concepts/columns>`_.
+
+    :param label: see `Columns </nimbusml/concepts/columns>`_.
+
+    :param sampling_type: Sampling Type.
+
+    :param num_models: Number of models per batch. If not specified, will
+        default to 50 if there is only one base predictor, or the number of
+        base predictors otherwise.
+
+    :param sub_model_selector_type: Algorithm to prune the base learners for
+        selective Ensemble.
+
+    :param output_combiner: Output combiner.
+
+    :param normalize: If ``Auto``, the choice to normalize depends on the
+        preference declared by the algorithm. This is the default choice. If
+        ``No``, no normalization is performed. If ``Yes``, normalization always
+        performed. If ``Warn``, if normalization is needed by the algorithm, a
+        warning message is displayed but normalization is not performed. If
+        normalization is performed, a ``MaxMin`` normalizer is used. This
+        normalizer preserves sparsity by mapping zero to zero.
+
+    :param caching: Whether trainer should cache input training data.
+
+    :param train_parallel: All the base learners will run asynchronously if the
+        value is true.
+
+    :param batch_size: Batch size.
+
+    :param show_metrics: True, if metrics for each model need to be evaluated
+        and shown in comparison table. This is done by using validation set if
+        available or the training set.
+
+    :param params: Additional arguments sent to compute engine.
+
+    """
+
+    @trace
+    def __init__(
+            self,
+            sampling_type=BootstrapSelector(
+                feature_selector=AllFeatureSelector()),
+            num_models=None,
+            sub_model_selector_type=None,
+            output_combiner=None,
+            normalize='Auto',
+            caching='Auto',
+            train_parallel=False,
+            batch_size=-1,
+            show_metrics=False,
+            feature=None,
+            label=None,
+            **params):
+
+        if 'feature_column_name' in params:
+            raise NameError(
+                "'feature_column_name' must be renamed to 'feature'")
+        if feature:
+            params['feature_column_name'] = feature
+        if 'label_column_name' in params:
+            raise NameError(
+                "'label_column_name' must be renamed to 'label'")
+        if label:
+            params['label_column_name'] = label
+        BasePredictor.__init__(self, type='classifier', **params)
+        core.__init__(
+            self,
+            sampling_type=sampling_type,
+            num_models=num_models,
+            sub_model_selector_type=sub_model_selector_type,
+            output_combiner=output_combiner,
+            normalize=normalize,
+            caching=caching,
+            train_parallel=train_parallel,
+            batch_size=batch_size,
+            show_metrics=show_metrics,
+            **params)
+        self.feature = feature
+        self.label = label
+
+    @trace
+    def predict_proba(self, X, **params):
+        '''
+        Returns probabilities
+        '''
+        return self._predict_proba(X, **params)
+
+    @trace
+    def decision_function(self, X, **params):
+        '''
+        Returns score values
+        '''
+        return self._decision_function(X, **params)
+
+    def get_params(self, deep=False):
+        """
+        Get the parameters for this operator.
+        """
+        return core.get_params(self)

src/python/nimbusml/ensemble/ensembleregressor.py

@@ -0,0 +1,113 @@
+# --------------------------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------------------------------------
+# - Generated by tools/entrypoint_compiler.py: do not edit by hand
+"""
+EnsembleRegressor
+"""
+
+__all__ = ["EnsembleRegressor"]
+
+
+from sklearn.base import RegressorMixin
+
+from ..base_predictor import BasePredictor
+from ..internal.core.ensemble.ensembleregressor import \
+    EnsembleRegressor as core
+from ..internal.utils.utils import trace
+from .feature_selector import AllFeatureSelector
+from .subset_selector import BootstrapSelector
+
+
+class EnsembleRegressor(core, BasePredictor, RegressorMixin):
+    """
+    **Description**
+        Train regression ensemble.
+
+    :param feature: see `Columns </nimbusml/concepts/columns>`_.
+
+    :param label: see `Columns </nimbusml/concepts/columns>`_.
+
+    :param sampling_type: Sampling Type.
+
+    :param num_models: Number of models per batch. If not specified, will
+        default to 50 if there is only one base predictor, or the number of
+        base predictors otherwise.
+
+    :param sub_model_selector_type: Algorithm to prune the base learners for
+        selective Ensemble.
+
+    :param output_combiner: Output combiner.
+
+    :param normalize: If ``Auto``, the choice to normalize depends on the
+        preference declared by the algorithm. This is the default choice. If
+        ``No``, no normalization is performed. If ``Yes``, normalization always
+        performed. If ``Warn``, if normalization is needed by the algorithm, a
+        warning message is displayed but normalization is not performed. If
+        normalization is performed, a ``MaxMin`` normalizer is used. This
+        normalizer preserves sparsity by mapping zero to zero.
+
+    :param caching: Whether trainer should cache input training data.
+
+    :param train_parallel: All the base learners will run asynchronously if the
+        value is true.
+
+    :param batch_size: Batch size.
+
+    :param show_metrics: True, if metrics for each model need to be evaluated
+        and shown in comparison table. This is done by using validation set if
+        available or the training set.
+
+    :param params: Additional arguments sent to compute engine.
+
+    """
+
+    @trace
+    def __init__(
+            self,
+            sampling_type=BootstrapSelector(
+                feature_selector=AllFeatureSelector()),
+            num_models=None,
+            sub_model_selector_type=None,
+            output_combiner=None,
+            normalize='Auto',
+            caching='Auto',
+            train_parallel=False,
+            batch_size=-1,
+            show_metrics=False,
+            feature=None,
+            label=None,
+            **params):
+
+        if 'feature_column_name' in params:
+            raise NameError(
+                "'feature_column_name' must be renamed to 'feature'")
+        if feature:
+            params['feature_column_name'] = feature
+        if 'label_column_name' in params:
+            raise NameError(
+                "'label_column_name' must be renamed to 'label'")
+        if label:
+            params['label_column_name'] = label
+        BasePredictor.__init__(self, type='regressor', **params)
+        core.__init__(
+            self,
+            sampling_type=sampling_type,
+            num_models=num_models,
+            sub_model_selector_type=sub_model_selector_type,
+            output_combiner=output_combiner,
+            normalize=normalize,
+            caching=caching,
+            train_parallel=train_parallel,
+            batch_size=batch_size,
+            show_metrics=show_metrics,
+            **params)
+        self.feature = feature
+        self.label = label
+
+    def get_params(self, deep=False):
+        """
+        Get the parameters for this operator.
+        """
+        return core.get_params(self)

src/python/nimbusml/ensemble/feature_selector/__init__.py

@@ -0,0 +1,7 @@
+from .allfeatureselector import AllFeatureSelector
+from .randomfeatureselector import RandomFeatureSelector
+
+__all__ = [
+    'AllFeatureSelector',
+    'RandomFeatureSelector'
+]