From ff2511eba623c74d11ea2b989026fd3151560aa0 Mon Sep 17 00:00:00 2001
From: Jakhes <dean.schmitz@schmitzbauer.de>
Date: Fri, 23 Sep 2022 17:54:07 +0200
Subject: [PATCH] Adding hoeffding_tree
---
Makefile | 2 +
src/methods/hoeffding_tree/Makefile | 8 ++
src/methods/hoeffding_tree/hoeffding_tree.cpp | 108 ++++++++++++++++++
src/methods/hoeffding_tree/hoeffding_tree.pl | 74 ++++++++++++
.../hoeffding_tree/hoeffding_tree_test.pl | 56 +++++++++
5 files changed, 248 insertions(+)
create mode 100644 src/methods/hoeffding_tree/Makefile
create mode 100644 src/methods/hoeffding_tree/hoeffding_tree.cpp
create mode 100644 src/methods/hoeffding_tree/hoeffding_tree.pl
create mode 100644 src/methods/hoeffding_tree/hoeffding_tree_test.pl
diff --git a/Makefile b/Makefile
index ecbabb6..bbe1ff6 100644
--- a/Makefile
+++ b/Makefile
@@ -10,6 +10,7 @@ all:
make -C src/methods/dbscan splfr=$(SPLFR_PATH)
make -C src/methods/emst splfr=$(SPLFR_PATH)
make -C src/methods/fastmks splfr=$(SPLFR_PATH)
+ make -C src/methods/hoeffding_tree splfr=$(SPLFR_PATH)
make -C src/methods/kde splfr=$(SPLFR_PATH)
make -C src/methods/kernel_pca splfr=$(SPLFR_PATH)
make -C src/methods/kmeans splfr=$(SPLFR_PATH)
@@ -39,6 +40,7 @@ clean:
make -C src/methods/dbscan clean
make -C src/methods/emst clean
make -C src/methods/fastmks clean
+ make -C src/methods/hoeffding_tree clean
make -C src/methods/kde clean
make -C src/methods/kernel_pca clean
make -C src/methods/kmeans clean
diff --git a/src/methods/hoeffding_tree/Makefile b/src/methods/hoeffding_tree/Makefile
new file mode 100644
index 0000000..d37037f
--- /dev/null
+++ b/src/methods/hoeffding_tree/Makefile
@@ -0,0 +1,8 @@
+splfr=/usr/local/sicstus4.7.1/bin/splfr
+
+METHOD_NAME=hoeffding_tree
+
+$(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
diff --git a/src/methods/hoeffding_tree/hoeffding_tree.cpp b/src/methods/hoeffding_tree/hoeffding_tree.cpp
new file mode 100644
index 0000000..1d1cfc4
--- /dev/null
+++ b/src/methods/hoeffding_tree/hoeffding_tree.cpp
@@ -0,0 +1,108 @@
+#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 "hoeffding_tree_glue.h"
+#include <mlpack/methods/hoeffding_trees/hoeffding_tree_model.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 HoeffdingTreeModel object so it can be accessed from all functions
+HoeffdingTreeModel hoeffdingTreeObj;
+
+// TODO:
+// input: const TreeType & type = GINI_HOEFFDING,
+// const arma::mat & dataset,
+// const data::DatasetInfo & datasetInfo,
+// const arma::Row< size_t > & labels,
+// const size_t numClasses,
+// const bool batchTraining,
+// const double successProbability,
+// const size_t maxSamples,
+// const size_t checkInterval,
+// const size_t minSamples,
+// const size_t bins,
+// const size_t observationsBeforeBinning
+// output:
+// description:
+void initAndBuildModel(char const *treeType,
+ float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
+ float *labelsArr, SP_integer labelsArrSize,
+ SP_integer numClasses, SP_integer batchTraining, double successProbability, SP_integer maxSamples, SP_integer checkInterval, SP_integer minSamples, SP_integer bins, SP_integer observationsBeforeBinning)
+{
+ // 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);
+
+ if (strcmp(treeType, "gini-hoeffding") == 0)
+ hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::GINI_HOEFFDING);
+ else if (strcmp(treeType, "gini-binary") == 0)
+ hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::GINI_BINARY);
+ else if (strcmp(treeType, "info-hoeffding") == 0)
+ hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::INFO_HOEFFDING);
+ else if (strcmp(treeType, "info-binary") == 0)
+ hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::INFO_BINARY);
+ else
+ cout << "wrong treeType input" << endl;
+
+ hoeffdingTreeObj.BuildModel(data, data::DatasetInfo(data.n_rows), labelsVector, numClasses, (batchTraining == 1), successProbability, maxSamples, checkInterval, minSamples, bins, observationsBeforeBinning);
+}
+
+// TODO:
+// input: const arma::mat & dataset,
+// arma::Row< size_t > & predictions <-,
+// arma::rowvec & probabilities <-
+// output:
+// description:
+void classify(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
+ float **predictArr, SP_integer *predictArrSize,
+ float **probsArr, SP_integer *probsArrSize)
+{
+ // convert the Prolog arrays to arma::mat
+ mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+
+ // create the ReturnVector
+ Row< size_t > predictReturnVector;
+
+ // create the ReturnVector
+ rowvec probsReturnVector;
+
+
+ hoeffdingTreeObj.Classify(data, predictReturnVector, probsReturnVector);
+
+
+ // return the Vector
+ returnVectorInformation(predictReturnVector, predictArr, predictArrSize);
+
+ // return the Vector
+ returnVectorInformation(probsReturnVector, probsArr, probsArrSize);
+}
+
+// TODO:
+// input: const arma::mat & dataset,
+// const arma::Row< size_t > & labels,
+// const bool batchTraining
+// output:
+// description:
+void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
+ float *labelsArr, SP_integer labelsArrSize,
+ SP_integer batchTraining)
+{
+ // 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);
+
+ hoeffdingTreeObj.Train(data, labelsVector, (batchTraining == 1));
+}
\ No newline at end of file
diff --git a/src/methods/hoeffding_tree/hoeffding_tree.pl b/src/methods/hoeffding_tree/hoeffding_tree.pl
new file mode 100644
index 0000000..3836ad6
--- /dev/null
+++ b/src/methods/hoeffding_tree/hoeffding_tree.pl
@@ -0,0 +1,74 @@
+:- module(hoeffding_tree, [ initAndBuildModel/14,
+ classify/7,
+ train/6]).
+
+%% 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--
+%% string treeType => "gini-hoeffding", "gini-binary", "info-hoeffding", "info-binary",
+%% mat dataset,
+%% vec labels,
+%% int numClasses,
+%% bool batchTrainig => (1)true / (0)false,
+%% float32 successProbability,
+%% int maxSamples,
+%% int checkInterval,
+%% int minSamples,
+%% int bins,
+%% int observationsBeforeBinning
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(initAndBuildModel, c, initAndBuildModel(+string,
+ +pointer(float_array), +integer, +integer,
+ +pointer(float_array), +integer,
+ +integer, +integer, +float32, +integer, +integer, +integer, +integer, +integer)).
+
+%% TODO:
+%% --Input--
+%% mat data
+%%
+%% --Output--
+%% vec predictions,
+%% vec probabilities
+%%
+%% --Description--
+foreign(classify, c, classify( +pointer(float_array), +integer, +integer,
+ -pointer(float_array), -integer,
+ -pointer(float_array), -integer)).
+
+%% TODO:
+%% --Input--
+%% mat data,
+%% vec labels,
+%% bool batchTrainig => (1)true / (0)false
+%%
+%% --Output--
+%%
+%% --Description--
+foreign(train, c, train(+pointer(float_array), +integer, +integer,
+ +pointer(float_array), +integer,
+ +integer)).
+
+
+%% Defines the functions that get connected from main.cpp
+foreign_resource(hoeffding_tree, [ initAndBuildModel,
+ classify,
+ train]).
+
+:- load_foreign_resource(hoeffding_tree).
\ No newline at end of file
diff --git a/src/methods/hoeffding_tree/hoeffding_tree_test.pl b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
new file mode 100644
index 0000000..cf01d51
--- /dev/null
+++ b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
@@ -0,0 +1,56 @@
+:- use_module(library(plunit)).
+
+:- use_module(hoeffding_tree).
+:- 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
--
GitLab