Adding Random_Forest

Makefile

@@ -13,6 +13,7 @@ all:
 	make -C src/methods/mean_shift splfr=$(SPLFR_PATH)
 	make -C src/methods/naive_bayes_classifier splfr=$(SPLFR_PATH)
 	make -C src/methods/perceptron splfr=$(SPLFR_PATH)
+	make -C src/methods/random_forest splfr=$(SPLFR_PATH)
 
 clean:
 	make -C src/methods/ada_boost clean
@@ -26,3 +27,4 @@ clean:
 	make -C src/methods/mean_shift clean
 	make -C src/methods/naive_bayes_classifier clean
 	make -C src/methods/perceptron clean
+	make -C src/methods/random_forest clean

src/methods/random_forest/Makefile

+splfr=/usr/local/sicstus4.7.1/bin/splfr
+
+METHOD_NAME=random_forest
+
+$(METHOD_NAME).so: $(METHOD_NAME).pl $(METHOD_NAME).cpp
+	$(splfr) -larmadillo -fopenmp -lmlpack -lstdc++ -cxx --struct $(METHOD_NAME).pl $(METHOD_NAME).cpp ../../helper_files/helper.cpp
+clean:
+	rm $(METHOD_NAME).so

src/methods/random_forest/random_forest.cpp

+#include <sicstus/sicstus.h>
+/* ex_glue.h is generated by splfr from the foreign/[2,3] facts.
+   Always include the glue header in your foreign resource code.
+*/
+#include "random_forest_glue.h"
+#include <mlpack/methods/random_forest/random_forest.hpp>
+#include <mlpack/core.hpp>
+
+// including helper functions for converting between arma structures and arrays
+#include "../../helper_files/helper.hpp"
+
+// some of the most used namespaces
+using namespace arma;
+using namespace mlpack;
+using namespace std;
+using namespace mlpack::tree;
+
+// Global Variable of the RandomForest object so it can be accessed from all functions
+RandomForest randomForest;
+
+// TODO: 
+// input: 
+// output: 
+// description: 
+void initModelNoTrain(SP_integer)
+{
+    randomForest = RandomForest();
+}
+
+// TODO: 
+// input:   const MatType & 	            dataset,
+//          const arma::Row< size_t > & 	labels,
+//          const size_t 	                numClasses,
+//          const size_t 	                numTrees = 20,
+//          const size_t 	                minimumLeafSize = 1,
+//          const double 	                minimumGainSplit = 1e-7,
+//          const size_t 	                maximumDepth = 0,
+//          DimensionSelectionType 	        dimensionSelector = DimensionSelectionType()
+// output: 
+// description: 
+void initModelWithTrainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize, 
+                                    SP_integer numClasses, SP_integer numTrees, SP_integer minimumLeafSize, double minimumGainSplit, SP_integer maximumDepth)
+{
+    // convert the Prolog arrays to arma::mat
+    mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+    // convert the Prolog arrays to arma::rowvec
+    Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
+    
+    randomForest = RandomForest(data, labelsVector, numClasses, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
+}
+
+// TODO: 
+// input:   onst MatType & 	                dataset,
+//          const arma::Row< size_t > & 	labels,
+//          const size_t 	                numClasses,
+//          const arma::rowvec & 	        weights,
+//          const size_t 	                numTrees = 20,
+//          const size_t 	                minimumLeafSize = 1,
+//          const double 	                minimumGainSplit = 1e-7,
+//          const size_t 	                maximumDepth = 0,
+//          DimensionSelectionType          dimensionSelector = DimensionSelectionType()
+// output: 
+// description: 
+void initModelWithTrainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize, SP_integer numClasses,
+									float *weightsArr, SP_integer weightsArrSize, SP_integer numTrees, SP_integer minimumLeafSize, double minimumGainSplit, SP_integer maximumDepth)
+{
+    // convert the Prolog arrays to arma::mat
+    mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+    // convert the Prolog arrays to arma::rowvec
+    Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
+
+    // convert the Prolog arrays to arma::rowvec
+    rowvec weightsVector = convertArrayToRowvec(weightsArr, weightsArrSize);
+    
+    
+    randomForest = RandomForest(data, labelsVector, numClasses, weightsVector, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
+}
+
+// TODO: 
+// input:   const VecType &     point,
+//          size_t & 	        prediction <-,
+//          arma::vec & 	    probabilities <-
+// output: 
+// description: 
+void classifyPoint(float *pointArr, SP_integer pointArrSize, SP_integer *prediction, float **probsArr, SP_integer *probsArrSize)
+{
+    // convert the Prolog arrays to arma::rowvec
+    rowvec pointVector = convertArrayToRowvec(pointArr, pointArrSize);
+
+    // create the ReturnVector
+    vec probsReturnVector;
+
+    size_t predicReturn;
+
+    randomForest.Classify(pointVector, predicReturn, probsReturnVector);
+
+    // return the predic value
+    *prediction = predicReturn;
+    
+    // return the Vector lenght
+    *probsArrSize = probsReturnVector.n_elem;
+    
+    // return the Vector as Array
+    *probsArr = convertToArray(probsReturnVector);
+    
+}
+
+// TODO: 
+// input:   const MatType & 	        data,
+//          arma::Row< size_t > & 	    predictions <-,
+//          arma::mat & 	            probabilities <-
+// output: 
+// description: 
+void classifyMatrix(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float **predicArr, SP_integer *predicArrSize, float **probsMatArr, SP_integer *probsMatColNum, SP_integer *probsMatRowNum)
+{
+    // convert the Prolog arrays to arma::mat
+    mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+    // create the ReturnVector
+    Row< size_t > predicReturnVector;
+
+    // create the ReturnMat
+    mat probsReturnMat;
+
+    randomForest.Classify(data, predicReturnVector, probsReturnMat);
+    
+    // return the Vector lenght
+    *predicArrSize = predicReturnVector.n_elem;
+    
+    // return the Vector as Array
+    *predicArr = convertToArray(predicReturnVector);
+    
+    // return the Matrix dimensions
+    *probsMatColNum = probsReturnMat.n_cols;
+    *probsMatRowNum = probsReturnMat.n_rows;
+    
+    // return the Matrix as one long Array
+    *probsMatArr = convertToArray(probsReturnMat);
+}
+
+// TODO: 
+// input: 
+// output:  const size_t   number of trees
+// description: 
+SP_integer numTrees()
+{
+    return randomForest.NumTrees();
+}
+
+// TODO:    doesnt accept warmStart parameter
+//
+// input:   const MatType & 	            data,
+//          const arma::Row< size_t > & 	labels,
+//          const size_t 	                numClasses,
+//          const size_t 	                numTrees = 20,
+//          const size_t 	                minimumLeafSize = 1,
+//          const double 	                minimumGainSplit = 1e-7,
+//          const size_t 	                maximumDepth = 0,
+//          const bool                      warmStart = false,
+//          DimensionSelectionType 	        dimensionSelector = DimensionSelectionType()
+//
+// output:  double                          average entropy of all trees trained
+// description: 
+double trainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize, 
+                        SP_integer numClasses, SP_integer numTrees, SP_integer minimumLeafSize, double minimumGainSplit, SP_integer maximumDepth)
+{
+    // convert the Prolog arrays to arma::mat
+    mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+    // convert the Prolog arrays to arma::rowvec
+    Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
+    
+    return randomForest.Train(data, labelsVector, numClasses, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
+}
+
+// TODO:    doesnt accept warmStart parameter
+//
+// input:   const MatType & 	            data,
+//          const arma::Row< size_t > & 	labels,
+//          const size_t 	                numClasses,
+//          const arma::rowvec & 	        weights,
+//          const size_t 	                numTrees = 20,
+//          const size_t 	                minimumLeafSize = 1,
+//          const double 	                minimumGainSplit = 1e-7,
+//          const size_t 	                maximumDepth = 0,
+//          const bool 	                    warmStart = false,
+//          DimensionSelectionType 	        dimensionSelector = DimensionSelectionType()
+//
+// output:  double                          average entropy of all trees trained
+// description: 
+double trainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize, SP_integer numClasses,
+							float *weightsArr, SP_integer weightsArrSize, SP_integer numTrees, SP_integer minimumLeafSize, double minimumGainSplit, SP_integer maximumDepth)
+{
+    // convert the Prolog arrays to arma::mat
+    mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+    // convert the Prolog arrays to arma::rowvec
+    Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
+
+    // convert the Prolog arrays to arma::rowvec
+    rowvec weightsVector = convertArrayToRowvec(weightsArr, weightsArrSize);
+    
+    
+    return randomForest.Train(data, labelsVector, numClasses, weightsVector, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
+}

src/methods/random_forest/random_forest.pl

+:- module(random_forest, [      initModelNoTrain/1,
+                                initModelWithTrainNoWeights/10,
+                                initModelWithTrainWithWeights/12,
+                                classifyPoint/5,
+                                classifyMatrix/8,
+                                numTrees/1,
+                                trainNoWeights/11,
+                                trainWithWeights/13]).
+
+%% requirements of library(struct)
+:- load_files(library(str_decl),
+                [when(compile_time), if(changed)]).
+
+%% needed for using the array type
+:- use_module(library(structs)).
+:- use_module('../../helper_files/helper.pl').
+
+%% type definitions for the float array
+:- foreign_type
+        float32          = float_32,
+        float_array      = array(float32).
+
+%% definitions for the connected function
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(initModelNoTrain, c, initModelNoTrain(+integer)).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(initModelWithTrainNoWeights, c, initModelWithTrainNoWeights(+pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer, +integer, +integer, +float32, +integer)).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(initModelWithTrainWithWeights, c, initModelWithTrainWithWeights(+pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer , +integer, +float32, +integer)).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(classifyPoint, c, classifyPoint(+pointer(float_array), +integer, -integer, -pointer(float_array), -integer)).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(classifyMatrix, c, classifyMatrix(+pointer(float_array), +integer, +integer, -pointer(float_array), -integer, -pointer(float_array), -integer, -integer)).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(numTrees, c, numTrees([-integer])).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(trainNoWeights, c, trainNoWeights(+pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer, +integer, +integer, +float32, +integer, [-float32])).
+
+%% TODO: 
+%% --Input--
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(trainWithWeights, c, trainWithWeights(+pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer, +pointer(float_array), +integer, +integer, +integer, +float32, +integer, [-float32])).
+
+
+%% Defines the functions that get connected from main.cpp
+foreign_resource(random_forest, [       initModelNoTrain,
+                                        initModelWithTrainNoWeights,
+                                        initModelWithTrainWithWeights,
+                                        classifyPoint,
+                                        classifyMatrix,
+                                        numTrees,
+                                        trainNoWeights,
+                                        trainWithWeights]).
+
+:- load_foreign_resource(random_forest).
\ No newline at end of file

src/methods/random_forest/random_forest_test.pl

+:- use_module(library(plunit)).
+
+:- use_module(random_forest).
+:- use_module('../../helper_files/helper.pl').
+
+reset_Model :-
+        initModel(1,0,50,0.0001).
+
+:- begin_tests(lists).
+
+%% alpha tests
+test(alpha_std_init) :-
+        reset_Model,
+        alpha(0).
+test(alpha_wrong_input, fail) :-
+        reset_Model,
+        alpha(1).
+test(alpha_after_train, A =:= 9223372036854775808) :-
+        reset_Model,
+        convert_list_to_float_array([5.1,3.5,1.4,4.9,3.0,1.4,4.7,3.2,1.3,4.6,3.1,1.5],3, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize),
+        alpha(A).
+
+%% train tests
+test(correct_train) :-
+        reset_Model,
+        convert_list_to_float_array([5.1,3.5,1.4,4.9,3.0,1.4,4.7,3.2,1.3,4.6,3.1,1.5],3, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+test(false_train, fail) :-
+        reset_Model,
+        convert_list_to_float_array([],3, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+test(false_train2, fail) :-
+        reset_Model,
+        convert_list_to_float_array([],0, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+test(false_train3, fail) :-
+        reset_Model,
+        convert_list_to_float_array([1,2],0, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+test(false_train3, fail) :-
+        reset_Model,
+        convert_list_to_float_array([1,2,44,3],3, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+test(false_train4) :-
+        reset_Model,
+        convert_list_to_float_array([1,2,44,3],2, array(Xsize, Xrownum, X)),
+        convert_list_to_float_array([0.2,0.2,0.2,0.2], array(Ysize, Y)),
+        train(X,Xsize, Xrownum,Y, Ysize).
+:- end_tests(lists).
\ No newline at end of file