feat: quantiles and average binning for RF histograms / maxBins=0 to …

…disable binning
uxlfoundation · May 15, 2023 · 377250c · 377250c
1 parent f1129b6
commit 377250c
Show file tree

Hide file tree

Showing 8 changed files with 222 additions and 85 deletions.
diff --git a/cpp/daal/include/algorithms/decision_forest/decision_forest_training_parameter.h b/cpp/daal/include/algorithms/decision_forest/decision_forest_training_parameter.h
@@ -94,6 +94,17 @@ enum splitterMode
 {
     best,  /* Calculates best split from aggregate best feature splits for every node. */
     random /* Calculates best split from aggregate random feature splits for every node. */
+}
+
+/**
+ * <a name = "DAAL-ENUM-ALGORITHMS__DECISION_FOREST__TRAINING__BINNINGSTRATEGY">
+ * </ a> * \brief Available strategies to compute data bins in 'hist' method * /
+*/
+enum BinningStrategy {
+    /* Frequency quantiles -> same number of data points per bin */
+    quantiles,
+    /* Same feature value range per bin */
+    averages
 };
 
 /**
@@ -145,6 +156,9 @@ class DAAL_EXPORT Parameter
     size_t minBinSize;                     /*!< Used with 'hist' split finding method only.
                                                  Minimal number of observations in a bin. Default is 5 */
     splitterMode splitter;                 /*!< Sets node splitting method. Default is best */
+    BinningStrategy binningStrategy;       /*!< Used with 'hist' split finding method only.
+                                                 Selects the strategy to group data points into bins.
+                                                 Allowed values are 'quantiles' (default), 'averages' */
 };
 /* [Parameter source code] */
 } // namespace interface2

diff --git a/cpp/daal/src/algorithms/dtrees/dtrees_feature_type_helper.h b/cpp/daal/src/algorithms/dtrees/dtrees_feature_type_helper.h
@@ -24,6 +24,7 @@
 #ifndef __DTREES_FEATURE_TYPE_HELPER_H__
 #define __DTREES_FEATURE_TYPE_HELPER_H__
 
+#include "include/algorithms/decision_forest/decision_forest_training_parameter.h"
 #include "src/externals/service_memory.h"
 #include "src/data_management/service_numeric_table.h"
 
@@ -69,12 +70,20 @@ class FeatureTypes
     int _lastUnordered     = -1;
 };
 
+using daal::algorithms::decision_forest::training::BinningStrategy;
+
 struct BinParams
 {
-    BinParams(size_t _maxBins, size_t _minBinSize) : maxBins(_maxBins), minBinSize(_minBinSize) {}
-    BinParams(const BinParams & o) : maxBins(o.maxBins), minBinSize(o.minBinSize) {}
-
-    size_t maxBins    = 256;
+    BinParams(size_t _maxBins, size_t _minBinSize, BinningStrategy _binningStrategy = BinningStrategy::quantiles)
+        : maxBins(_maxBins), minBinSize(_minBinSize), binningStrategy(_binningStrategy)
+    {}
+    BinParams(const BinParams & o) : maxBins(o.maxBins), minBinSize(o.minBinSize), binningStrategy(o.binningStrategy) {}
+
+    /* Strategy to create bins for feature values. Default: quantiles */
+    BinningStrategy binningStrategy = BinningStrategy::quantiles;
+    /* Maximum number of bins for indexed data. Default: 256 */
+    size_t maxBins = 256;
+    /* Minimum bin width (number of data points per bin). Default: 5*/
     size_t minBinSize = 5;
 };
 
@@ -103,6 +112,7 @@ class IndexedFeatures
     IndexedFeatures() : _data(nullptr), _entries(nullptr), _sizeOfIndex(sizeof(IndexType)), _nCols(0), _nRows(0), _capacity(0), _maxNumIndices(0) {}
     ~IndexedFeatures();
 
+    //initialize the feature indices, i.e. bins
     template <typename algorithmFPType, CpuType cpu>
     services::Status init(const NumericTable & nt, const FeatureTypes * featureTypes = nullptr, const BinParams * pBimPrm = nullptr);