diff --git a/src/helper_files/helper.hpp b/src/helper_files/helper.hpp
index 15dee9381356ed95961cd303c656f2e7db6c061e..63bb0256a5b52c5fb3774231fbc7e3763d4d288c 100644
--- a/src/helper_files/helper.hpp
+++ b/src/helper_files/helper.hpp
@@ -7,6 +7,9 @@ using namespace arma;
using namespace mlpack;
using namespace std;
+
+// conversion from arma datatypes to arrays usable by prolog
+
float *convertToArray(colvec vec);
float *convertToArray(rowvec vec);
@@ -24,12 +27,17 @@ float *convertToArray(Row<size_t> vec);
float *convertToArray(vector<vec> vec);
+// conversion from arrays to arma datatypes
+
rowvec convertArrayToRowvec(float *arr, int vecSize);
Row<size_t> convertArrayToVec(float *arr, int vecSize);
mat convertArrayToMat(float *arr, int vecSize, int rowCount);
+
+// insert the Vector and Matrix informations into the prolog Variables
+
void returnMatrixInformation(mat matrix, float **mat, SP_integer *matColNum, SP_integer *matRowNum);
void returnMatrixInformation(Mat< size_t > matrix, float **mat, SP_integer *matColNum, SP_integer *matRowNum);
diff --git a/src/methods/adaboost/adaboost_test.pl b/src/methods/adaboost/adaboost_test.pl
index c00808081034ac579f83551f812ee1180117425c..a930b619e1509d05d05498da33abdf1ce9f23873 100644
--- a/src/methods/adaboost/adaboost_test.pl
+++ b/src/methods/adaboost/adaboost_test.pl
@@ -269,12 +269,12 @@ test(train_With_Bad_Labels_Too_Many_Classes, [error(_,system_error('The values o
reset_Model_No_Train(perceptron),
train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
-test(train_With_Bad_Labels_Negative, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
+test(train_With_Bad_Labels_Negative_Perceptron, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
reset_Model_No_Train(perceptron),
train([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, [0,-1,0,-1], 2, perceptron, 50, 0.0001, _).
%% should cause an exeption but doesnt TODO:
-test(train_With_Bad_Labels_Negative) :-
+test(train_With_Bad_Labels_Negative_Decision_Stump) :-
reset_Model_No_Train(decision_stump),
train([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, [0,-1,0,-1], 2, decision_stump, 50, 0.0001, _).
diff --git a/src/methods/approx_kfn/approx_kfn.cpp b/src/methods/approx_kfn/approx_kfn.cpp
index fa198355b4e438b862c1f633b645fbeeeef39651..cc77858ef26f3bfb761776048e3f953a2d7de0c4 100644
--- a/src/methods/approx_kfn/approx_kfn.cpp
+++ b/src/methods/approx_kfn/approx_kfn.cpp
@@ -17,10 +17,10 @@ using namespace std;
using namespace mlpack::neighbor;
// Global Variable of the DrusillaSelect object so it can be accessed from all functions
-DrusillaSelect<mat> drusillaSelect = DrusillaSelect(0,0);
+DrusillaSelect<mat> drusillaSelect = DrusillaSelect(1,1);
// Global Variable of the QDAFN object so it can be accessed from all functions
-QDAFN<mat> qdafn = QDAFN(0,0);
+QDAFN<mat> qdafn = QDAFN(1,1);
// TODO:
// input: const size_t l,
@@ -62,7 +62,7 @@ void searchDrusilla(float *querySetMatArr, SP_integer querySetMatSize, SP_intege
mat querySet = convertArrayToMat(querySetMatArr, querySetMatSize, querySetMatRowNum);
// create the ReturnMat
- Mat< size_t> neighborsReturnMat;
+ Mat< size_t > neighborsReturnMat;
// create the ReturnMat
mat distancesReturnMat;
diff --git a/src/methods/approx_kfn/approx_kfn_test.pl b/src/methods/approx_kfn/approx_kfn_test.pl
index e58694a63e55248763286a01431b1c595e3306e1..6e5d6df774d516d384c313dbf95ac8ff5b374fe8 100644
--- a/src/methods/approx_kfn/approx_kfn_test.pl
+++ b/src/methods/approx_kfn/approx_kfn_test.pl
@@ -1,3 +1,6 @@
+
+:- module(approx_kfn_tests, [run_approx_kfn_tests/0]).
+
:- use_module(library(plunit)).
:- use_module(approx_kfn).
@@ -6,51 +9,36 @@
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
+%%
+%% TESTING predicate predicate/10
+%%
+:- begin_tests(predicate).
+
+%% Failure Tests
+
+test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
+
+test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+
+
+%% Successful Tests
+
+test(testDescription3, [true(Error =:= 1)]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+
+test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
+ reset_Model_No_Train(perceptron),
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+
+:- end_tests(predicate).
+
+run_approx_kfn_tests :-
+ run_tests.
+
diff --git a/src/methods/bayesian_linear_regression/bayesian_linear_regression.cpp b/src/methods/bayesian_linear_regression/bayesian_linear_regression.cpp
index 67751451be589f0547459a38a561a9ea3d92b95e..0dd644f52f06c304205c345d0f42f75b35af6f65 100644
--- a/src/methods/bayesian_linear_regression/bayesian_linear_regression.cpp
+++ b/src/methods/bayesian_linear_regression/bayesian_linear_regression.cpp
@@ -77,7 +77,8 @@ void omega(float **omegaArr, SP_integer *omegaArrSize)
// input: const arma::mat &points,
// arma::rowvec &predictions
// output:
-void predict(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMatRowNum, float **predictionsArr, SP_integer *predictionsArrSize)
+void predict(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMatRowNum,
+ float **predictionsArr, SP_integer *predictionsArrSize)
{
// convert the Prolog array to arma::mat
mat points = convertArrayToMat(pointsMatArr, pointsMatSize, pointsMatRowNum);
@@ -86,8 +87,16 @@ void predict(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMat
rowvec predictionsReturnVector;
- // run the prediction and save the result in arma::rowvec
- regressor.Predict(points, predictionsReturnVector);
+ try
+ {
+ // run the prediction and save the result in arma::rowvec
+ regressor.Predict(points, predictionsReturnVector);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return;
+ }
// return the Vector
@@ -98,7 +107,9 @@ void predict(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMat
// arma::rowvec &predictions,
// arma::rowvec &std
// output:
-void predictWithStd(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMatRowNum, float **predictionsArr, SP_integer *predictionsArrSize, float **stdArr, SP_integer *stdArrSize)
+void predictWithStd(float *pointsMatArr, SP_integer pointsMatSize, SP_integer pointsMatRowNum,
+ float **predictionsArr, SP_integer *predictionsArrSize,
+ float **stdArr, SP_integer *stdArrSize)
{
// convert the Prolog array to arma::mat
mat points = convertArrayToMat(pointsMatArr, pointsMatSize, pointsMatRowNum);
@@ -108,8 +119,16 @@ void predictWithStd(float *pointsMatArr, SP_integer pointsMatSize, SP_integer po
rowvec stdReturnVector;
- // run the prediction and save the result in arma::rowvec
- regressor.Predict(points, predictionsReturnVector, stdReturnVector);
+ try
+ {
+ // run the prediction and save the result in arma::rowvec
+ regressor.Predict(points, predictionsReturnVector, stdReturnVector);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return;
+ }
// return the Vectors
@@ -128,7 +147,8 @@ double responsesOffset()
// input: const arma::mat & data,
// const arma::rowvec & responses
// output: double
-double rmse(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *responsesArr, SP_integer responsesArrSize)
+double rmse(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
+ float *responsesArr, SP_integer responsesArrSize)
{
// convert the Prolog array to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -137,14 +157,23 @@ double rmse(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
rowvec responsesVector = convertArrayToRowvec(responsesArr, responsesArrSize);
- // run the model function and return the error
- return regressor.RMSE(data, responsesVector);
+ try
+ {
+ // run the model function and return the error
+ return regressor.RMSE(data, responsesVector);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return 0.0;
+ }
}
// input: const arma::mat & data,
// const arma::rowvec & responses
// output:
-void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *responsesArr, SP_integer responsesArrSize)
+void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
+ float *responsesArr, SP_integer responsesArrSize)
{
if(dataMatSize / dataMatRowNum != responsesArrSize)
{
@@ -158,8 +187,16 @@ void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
rowvec responsesVector = convertArrayToRowvec(responsesArr, responsesArrSize);
- // run the model function
- regressor.Train(data, responsesVector);
+ try
+ {
+ // run the model function
+ regressor.Train(data, responsesVector);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return;
+ }
}
// input:
diff --git a/src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl b/src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl
index b672360363a0148e11533598ab1472f3188b996c..86bb61e38bd6b9b5ae90d2c4c3cfef3e80fe320a 100644
--- a/src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl
+++ b/src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl
@@ -1,3 +1,6 @@
+
+:- module(bayesian_linear_regression_tests, [run_bayesian_linear_regression_tests/0]).
+
:- use_module(library(plunit)).
%%:- compile(bayesian_linear_regression).
@@ -57,3 +60,37 @@ test(false_train4) :-
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).
+
+%%
+%% TESTING predicate predicate/10
+%%
+:- begin_tests(predicate).
+
+%% Failure Tests
+
+test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
+
+test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+
+
+%% Successful Tests
+
+test(testDescription3, [true(Error =:= 1)]) :-
+ reset_Model_No_Train(perceptron),
+ train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+
+test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
+ reset_Model_No_Train(perceptron),
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+
+:- end_tests(predicate).
+
+run_bayesian_linear_regression_tests :-
+ run_tests.
+
diff --git a/src/methods/hoeffding_tree/hoeffding_tree.cpp b/src/methods/hoeffding_tree/hoeffding_tree.cpp
index 9e3326279b563ce1edef26054841e03850431264..cbe023a7ad80001679f2b5433b40a617bf6d14f8 100644
--- a/src/methods/hoeffding_tree/hoeffding_tree.cpp
+++ b/src/methods/hoeffding_tree/hoeffding_tree.cpp
@@ -17,6 +17,7 @@ using namespace mlpack::tree;
// Global Variable of the HoeffdingTreeModel object so it can be accessed from all functions
HoeffdingTreeModel hoeffdingTreeObj;
+bool isModelInitialized = false;
// input: const TreeType & type = GINI_HOEFFDING,
@@ -48,18 +49,33 @@ void initAndBuildModel(char const *treeType,
// convert the Prolog arrays to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
- if (strcmp(treeType, "gini-hoeffding") == 0)
+ if (strcmp(treeType, "gini_hoeffding") == 0)
hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::GINI_HOEFFDING);
- else if (strcmp(treeType, "gini-binary") == 0)
+ else if (strcmp(treeType, "gini_binary") == 0)
hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::GINI_BINARY);
- else if (strcmp(treeType, "info-hoeffding") == 0)
+ else if (strcmp(treeType, "info_hoeffding") == 0)
hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::INFO_HOEFFDING);
- else if (strcmp(treeType, "info-binary") == 0)
+ else if (strcmp(treeType, "info_binary") == 0)
hoeffdingTreeObj = HoeffdingTreeModel(HoeffdingTreeModel::INFO_BINARY);
else
- cout << "wrong treeType input" << endl;
+ {
+ raisePrologDomainExeption(treeType, 1, "The given TreeType is unkown!", "initAndBuildModel");
+ return;
+ }
- hoeffdingTreeObj.BuildModel(data, data::DatasetInfo(data.n_rows), labelsVector, numClasses, (batchTraining == 1), successProbability, maxSamples, checkInterval, minSamples, bins, observationsBeforeBinning);
+
+ try
+ {
+ hoeffdingTreeObj.BuildModel(data, data::DatasetInfo(data.n_rows), labelsVector, numClasses, (batchTraining == 1), successProbability, maxSamples, checkInterval, minSamples, bins, observationsBeforeBinning);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ isModelInitialized = false;
+ return;
+ }
+
+ isModelInitialized = true;
}
@@ -74,6 +90,12 @@ void classify(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNu
float **predictArr, SP_integer *predictArrSize,
float **probsArr, SP_integer *probsArrSize)
{
+ if (!isModelInitialized)
+ {
+ raisePrologSystemExeption("The model is not initialized!");
+ return;
+ }
+
// convert the Prolog arrays to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -84,7 +106,15 @@ void classify(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNu
rowvec probsReturnVector;
- hoeffdingTreeObj.Classify(data, predictReturnVector, probsReturnVector);
+ try
+ {
+ hoeffdingTreeObj.Classify(data, predictReturnVector, probsReturnVector);
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return;
+ }
// return the Vector
@@ -106,11 +136,26 @@ void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
float *labelsArr, SP_integer labelsArrSize,
SP_integer batchTraining)
{
+ if (!isModelInitialized)
+ {
+ raisePrologSystemExeption("The model is not initialized!");
+ return;
+ }
+
// 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));
+
+ try
+ {
+ hoeffdingTreeObj.Train(data, labelsVector, (batchTraining == 1));
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption("nice");
+ return;
+ }
}
diff --git a/src/methods/hoeffding_tree/hoeffding_tree.pl b/src/methods/hoeffding_tree/hoeffding_tree.pl
index 478e73107e48e31d6709dbd5ad32f5c032d5ea55..9996abf949b859e17cd512c35815ad195b001dab 100644
--- a/src/methods/hoeffding_tree/hoeffding_tree.pl
+++ b/src/methods/hoeffding_tree/hoeffding_tree.pl
@@ -20,7 +20,7 @@
%% --Input--
-%% string treeType => "gini-hoeffding", "gini-binary", "info-hoeffding", "info-binary",
+%% string treeType => "gini_hoeffding", "gini_binary", "info_hoeffding", "info_binary",
%% mat dataset,
%% vec labels,
%% int numClasses,
@@ -43,6 +43,10 @@ initAndBuildModel(TreeType, DataList, DataRows, LabelsList, NumClasses, BatchTra
SuccessProbability >= 0,
SuccessProbability =< 1,
MaxSamples >= 0,
+ CheckInterval > 0,
+ MinSamples >= 0,
+ Bins >= 0,
+ ObservationsBeforeBinning >= 0,
convert_list_to_float_array(DataList, DataRows, array(Xsize, Xrownum, X)),
convert_list_to_float_array(LabelsList, array(Ysize, Y)),
initAndBuildModelI(TreeType, X, Xsize, Xrownum, Y, Ysize, NumClasses, BatchTraining, SuccessProbability, MaxSamples, CheckInterval, MinSamples, Bins, ObservationsBeforeBinning).
diff --git a/src/methods/hoeffding_tree/hoeffding_tree_test.pl b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
index 20434461ef2cb7366126dc396eafdaa8ece3b5ed..a1dbaabe9963baa4481d4cae8982f2a3bb58faff 100644
--- a/src/methods/hoeffding_tree/hoeffding_tree_test.pl
+++ b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
@@ -7,7 +7,9 @@
:- use_module('../../helper_files/helper.pl').
reset_Model :-
- initAndBuildModel(1,0,50,0.0001).
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(gini_binary, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100).
%%
%% TESTING predicate initAndBuildModel/12
@@ -15,27 +17,84 @@ reset_Model :-
:- begin_tests(initAndBuildModel).
%% Failure Tests
+
+test(hoeffding_Init_Classify_Befor_Init, [error(_,system_error('The model is not initialized!'))]) :-
+ classify([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, _, _).
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
+test(hoeffding_Init_Wrong_TreeType, [error(domain_error('The given TreeType is unkown!' , wrongType), _)]) :-
+ initAndBuildModel(wrongType, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_Negative_NumClass, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], -2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_Bad_SuccessProbability, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, -1.0, 5000, 100, 100, 10, 100),
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 2.0, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_Negative_MaxSamples, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, -5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_Negative_CheckInterval, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, -100, 100, 10, 100).
+
+test(hoeffding_Init_Negative_MinSamples, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, -100, 10, 100).
+
+test(hoeffding_Init_Negative_Bins, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, -10, 100).
+
+test(hoeffding_Init_Negative_ObservationsBeforeBinning, fail) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, -100).
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+
+test(hoeffding_Init_With_Wrong_Label_Dims1, [error(_,system_error('Labels Vector is too short or its values are incorrect: should fit into [0,numClasses)!'))]) :-
+ initAndBuildModel(gini_binary, [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, [0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+%% If the label vector is to long it seems to cause no problems
+test(hoeffding_Init_With_Wrong_Label_Dims2) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1,0,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+%% The same when the label values are out of range
+test(hoeffding_Init_With_Wrong_Label_Value) :-
+ initAndBuildModel(gini_binary, [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, [0,-1,0,-1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_With_Too_Many_Label_Value, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
+ initAndBuildModel(gini_binary, [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, [1,1,0,2], 2, 0, 0.95, 5000, 100, 100, 10, 100).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+test(hoeffding_Init_GiniHoeffding_Direkt_Input) :-
+ initAndBuildModel(gini_hoeffding, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_GiniHoeffding_CSV_Input) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(gini_hoeffding, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_GiniBinary_Direkt_Input) :-
+ initAndBuildModel(gini_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
+test(hoeffding_Init_GiniBinary_CSV_Input) :-
open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+ initAndBuildModel(gini_binary, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_InfoHoeffding_Direkt_Input) :-
+ initAndBuildModel(info_hoeffding, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_InfoHoeffding_CSV_Input) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(info_hoeffding, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_InfoBinary_Direkt_Input) :-
+ initAndBuildModel(info_binary, [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, [0,1,0,1], 2, 0, 0.95, 5000, 100, 100, 10, 100).
+
+test(hoeffding_Init_InfoBinary_CSV_Input) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(info_binary, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100).
:- end_tests(initAndBuildModel).
@@ -47,26 +106,56 @@ test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
%% Failure Tests
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+test(hoeffding_Classify_Different_Dims_To_Train, [error(_,system_error('Labels Vector is too short or its values are incorrect: should fit into [0,numClasses)!'))]) :-
+ reset_Model,
+ classify([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, PredicList, ProbsList),
+ print('\nPredictions: '),
+ print(PredicList),
+ print('\nProbabilities: '),
+ print(ProbsList).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
-
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
+test(hoeffding_Classify_GiniHoeffding) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(gini_hoeffding, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100),
+ classify([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, PredicList, ProbsList),
+ print('\nPredictions: '),
+ print(PredicList),
+ print('\nProbabilities: '),
+ print(ProbsList).
+
+test(hoeffding_Classify_GiniBinary) :-
open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+ initAndBuildModel(gini_binary, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100),
+ classify([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, PredicList, ProbsList),
+ print('\nPredictions: '),
+ print(PredicList),
+ print('\nProbabilities: '),
+ print(ProbsList).
+
+test(hoeffding_Classify_InfoHoeffding) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(info_hoeffding, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100),
+ classify([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, PredicList, ProbsList),
+ print('\nPredictions: '),
+ print(PredicList),
+ print('\nProbabilities: '),
+ print(ProbsList).
+
+test(hoeffding_Classify_InfoBinary) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ initAndBuildModel(info_binary, Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0, 0.95, 5000, 100, 100, 10, 100),
+ classify([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, PredicList, ProbsList),
+ print('\nPredictions: '),
+ print(PredicList),
+ print('\nProbabilities: '),
+ print(ProbsList).
:- end_tests(classify).
@@ -78,29 +167,38 @@ test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
%% Failure Tests
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+test(hoeffding_Train_With_Wrong_Label_Dims1, [error(_,system_error('Labels Vector is too short or its values are incorrect: should fit into [0,numClasses)!'))]) :-
+ reset_Model,
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [0,1,0,0,0], 0).
+
+%% If the label vector is to long it seems to cause no problems
+test(hoeffding_Train_With_Wrong_Label_Dims2) :-
+ reset_Model,
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [0,1,0,1,0,0,1], 0).
+
+%% The same when the label values are out of range
+test(hoeffding_Train_With_Wrong_Label_Value) :-
+ reset_Model,
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [0,-1,0,-1], 0).
+
+test(hoeffding_Train_With_Too_Many_Label_Value, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
+ reset_Model,
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [1,1,0,2], 0).
+test(hoeffding_Train_Bad_Data_Dims) :-
+ reset_Model,
+ train([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, [0,1,0,1], 0).
-%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+%% Successful Tests
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
- open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
- take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+test(testDescription3) :-
+ reset_Model,
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [0,0,1,1,0], 1),
+ train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [0,0,1,1,0], 0).
:- end_tests(train).
run_hoeffding_tree_tests :-
- run_tests.
+ run_tests(train).
diff --git a/src/methods/kde/kde.cpp b/src/methods/kde/kde.cpp
index 6609138288d30f55d1049222e6103e5fc66689fb..9e10401e91f4dc11e938d00fce844554d72d1b03 100644
--- a/src/methods/kde/kde.cpp
+++ b/src/methods/kde/kde.cpp
@@ -67,21 +67,22 @@ void initAndBuildModel(double bandwidth, double relError, double absError,
}
else
{
- raisePrologSystemExeption("The given KernelType is unknown!");
+ raisePrologDomainExeption(kernelType, 4, "The given KernelType is unknown!", "initAndBuildModel");
+ return;
}
// select the treeType
mlpack::kde::KDEModel::TreeTypes treeT;
- if (strcmp(treeType, "kd-tree") == 0)
+ if (strcmp(treeType, "kd_tree") == 0)
{
treeT = KDEModel::KD_TREE;
}
- else if (strcmp(treeType, "ball-tree") == 0)
+ else if (strcmp(treeType, "ball_tree") == 0)
{
treeT = KDEModel::BALL_TREE;
}
- else if (strcmp(treeType, "cover-tree") == 0)
+ else if (strcmp(treeType, "cover_tree") == 0)
{
treeT = KDEModel::COVER_TREE;
}
@@ -89,42 +90,43 @@ void initAndBuildModel(double bandwidth, double relError, double absError,
{
treeT = KDEModel::OCTREE;
}
- else if (strcmp(treeType, "r-tree") == 0)
+ else if (strcmp(treeType, "r_tree") == 0)
{
treeT = KDEModel::R_TREE;
}
else
{
- raisePrologSystemExeption("The given TreeType is unknown!");
+ raisePrologDomainExeption(treeType, 5, "The given TreeType is unknown!", "initAndBuildModel");
+ return;
}
-
- kdeModel = KDEModel(bandwidth, relError, absError, kernelT, treeT, (monteCarlo == 1), mcProb, initialSampleSize, mcEntryCoef, mcBreakCoef);
+
+ try
+ {
+ kdeModel = KDEModel(bandwidth, relError, absError, kernelT, treeT, (monteCarlo == 1), mcProb, initialSampleSize, mcEntryCoef, mcBreakCoef);
+ kdeModel.BuildModel(move(reference));
+ }
+ catch(const std::exception& e)
+ {
+ raisePrologSystemExeption(e.what());
+ return;
+ }
- if (strcmp(algorithm, "dual-tree") == 0)
+ if (strcmp(algorithm, "dual_tree") == 0)
{
KDEMode& mode = kdeModel.Mode();
mode = KDEMode::DUAL_TREE_MODE;
}
- else if (strcmp(algorithm, "single-tree") == 0)
+ else if (strcmp(algorithm, "single_tree") == 0)
{
KDEMode& mode = kdeModel.Mode();
mode = KDEMode::SINGLE_TREE_MODE;
}
else
{
- raisePrologSystemExeption("The given Algorithm is unknown!");
- }
-
-
- try
- {
- kdeModel.BuildModel(move(reference));
- }
- catch(const std::exception& e)
- {
- raisePrologSystemExeption(e.what());
+ raisePrologDomainExeption(algorithm, 6, "The given Algorithm is unknown!", "initAndBuildModel");
+ return;
}
}
@@ -151,6 +153,7 @@ void evaluateWithQuery(float *querySetMatArr, SP_integer querySetMatSize, SP_int
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
+ return;
}
@@ -178,6 +181,7 @@ void evaluateNoQuery(float **estimationsArr, SP_integer *estimationsArrSize)
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
+ return;
}
diff --git a/src/methods/kde/kde_test.pl b/src/methods/kde/kde_test.pl
index 991662cb5826b0f56210923192bb681d2c5260ff..ba0891761a995b3d8061aed24c7af077217e577b 100644
--- a/src/methods/kde/kde_test.pl
+++ b/src/methods/kde/kde_test.pl
@@ -7,98 +7,295 @@
:- use_module('../../helper_files/helper.pl').
reset_Model :-
- initModel(1,0,50,0.0001).
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
%%
-%% TESTING predicate initAndBuildModel/10
+%% TESTING predicate initAndBuildModel/13
%%
:- begin_tests(initAndBuildModel).
%% Failure Tests
-
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+
+%% only raises an exeption if the model hasnt been initilized once, so only after fully reseting the tests.
+test(kde_EvaluateWithQuery_Befor_Init, [error(_, system_error('no KDE model initialized'))]) :-
+ evaluateWithQuery([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, _).
+
+%% only raises an exeption if the model hasnt been initilized once, so only after fully reseting the tests.
+test(kde_EvaluateNoQuery_Befor_Init, [error(_, system_error('no KDE model initialized'))]) :-
+ evaluateNoQuery(_).
+
+test(kde_Init_Negative_Bandwidth, fail) :-
+ initAndBuildModel(-1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Bad_RelError, fail) :-
+ initAndBuildModel(1.0, -0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 1.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Negative_AbsError, fail) :-
+ initAndBuildModel(1.0, 0.05, -1.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Wrong_KernelType, [error(domain_error('The given KernelType is unknown!' , wrongType), _)]) :-
+ initAndBuildModel(1.0, 0.05, 0.0, wrongType, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Wrong_TreeType, [error(domain_error('The given TreeType is unknown!' , wrongType), _)]) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, wrongType, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Wrong_Algorithm, [error(domain_error('The given Algorithm is unknown!' , wrongType), _)]) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, wrongType, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Bad_McProb, fail) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, -0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 1.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Negative_InitialSampleSize, fail) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, -100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Negative_MCEntryCoef, fail) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 0.0, 0.4,
+ [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).
+
+test(kde_Init_Bad_MCBreakCoef, fail) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, -0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 1.4,
+ [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).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+%% Gaussian Kernel
+test(kde_Init_Gaussian_KDTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, kd_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Gaussian_BALLTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, ball_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, ball_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Gaussian_COVERTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, cover_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, cover_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Gaussian_OCTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, octree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, octree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Gaussian_RTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, r_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, gaussian, r_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+
+
+%% Epanechnikov Kernel
+test(kde_Init_Epanechnikov_KDTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, kd_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Epanechnikov_BALLTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, ball_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, ball_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Epanechnikov_COVERTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, cover_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, cover_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Epanechnikov_OCTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, octree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, octree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Epanechnikov_RTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, r_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, epanechnikov, r_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
+
+%% Laplacian Kernel
+test(kde_Init_Laplacian_KDTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, kd_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Laplacian_BALLTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, ball_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, ball_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Laplacian_COVERTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, cover_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, cover_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Laplacian_OCTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, octree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, octree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Laplacian_RTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, r_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, laplacian, r_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+
+
+%% Spherical Kernel
+test(kde_Init_Spherical_KDTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, kd_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Spherical_BALLTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, ball_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, ball_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Spherical_COVERTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, cover_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, cover_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Spherical_OCTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, octree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, octree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Spherical_RTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, r_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, spherical, r_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+
+%% Triangular Kernel
+test(kde_Init_Triangular_KDTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, kd_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, kd_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Triangular_BALLTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, ball_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, ball_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Triangular_COVERTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, cover_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, cover_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Triangular_OCTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, octree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, octree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+test(kde_Init_Triangular_RTREE) :-
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, r_tree, dual_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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),
+ initAndBuildModel(1.0, 0.05, 0.0, triangular, r_tree, single_tree, 0, 0.95, 100, 3.0, 0.4,
+ [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).
+
+
+
+test(kde_Init_CSV_Input) :-
open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+ initAndBuildModel(2.2, 0.25, 0.5, gaussian, kd_tree, dual_tree, 1, 0.75, 50, 2.0, 0.2,
+ Data, 4).
:- end_tests(initAndBuildModel).
%%
-%% TESTING predicate evaluateWithQuery/10
+%% TESTING predicate evaluateWithQuery/3
%%
:- begin_tests(evaluateWithQuery).
%% Failure Tests
-
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+test(kde_EvalWithQuery_Wrong_Query_Dims, [error(_, system_error('cannot evaluate KDE model: querySet and referenceSet dimensions don\'t match'))]) :-
+ reset_Model,
+ evaluateWithQuery([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, Estimation),
+ print('\nEstimation: '),
+ print(Estimation).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+test(kde_EvalWithQuery) :-
+ reset_Model,
+ evaluateWithQuery([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5], 3, Estimation),
+ print('\nEstimation: '),
+ print(Estimation).
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
+test(kde_EvalWithQuery_CSV_Input) :-
open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+ initAndBuildModel(2.2, 0.25, 0.5, gaussian, kd_tree, dual_tree, 1, 0.75, 50, 2.0, 0.2,
+ Data, 4),
+ evaluateWithQuery([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, Estimation),
+ print('\nEstimation: '),
+ print(Estimation).
:- end_tests(evaluateWithQuery).
%%
-%% TESTING predicate evaluateNoQuery/10
+%% TESTING predicate evaluateNoQuery/1
%%
:- begin_tests(evaluateNoQuery).
%% Failure Tests
-
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
-
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
- open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
- take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+test(kde_EvalNoQuery) :-
+ reset_Model,
+ evaluateNoQuery(Estimation),
+ print('\nEstimation: '),
+ print(Estimation).
:- end_tests(evaluateNoQuery).
diff --git a/src/methods/kernel_pca/kernel_pca.cpp b/src/methods/kernel_pca/kernel_pca.cpp
index 374ce418380e5698692dee6600a3f7d374f21bd3..65af3b53bb827fdf900fcd594c21e62b1067d09a 100644
--- a/src/methods/kernel_pca/kernel_pca.cpp
+++ b/src/methods/kernel_pca/kernel_pca.cpp
@@ -23,7 +23,7 @@ using namespace mlpack::kernel;
template<typename KernelType>
-void useNystroemKernelPCA(char const *nystroemMethod, KernelType kernel, bool centerTranformedData, mat data, mat transformedDataReturnMat, vec eigvalReturnVector, mat eigvecReturnMat, size_t returnDim)
+bool useNystroemKernelPCA(char const *nystroemMethod, KernelType kernel, bool centerTranformedData, mat data, mat transformedDataReturnMat, vec eigvalReturnVector, mat eigvecReturnMat, size_t returnDim)
{
if (strcmp(nystroemMethod, "kmeans") == 0)
{
@@ -42,8 +42,10 @@ void useNystroemKernelPCA(char const *nystroemMethod, KernelType kernel, bool ce
}
else
{
- raisePrologDomainExeption(nystroemMethod, 4, "The given NystoemMethod is unkown!", "kernel_pca");
+ raisePrologDomainExeption(nystroemMethod, 4, "The given NystroemMethod is unknown!", "kernel_pca");
+ return false;
}
+ return true;
}
// TODO:
@@ -62,7 +64,7 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
float **transformedDataMatArr, SP_integer *transformedDataMatColNum, SP_integer *transformedDataMatRowNum,
float **eigvalArr, SP_integer *eigvalArrSize,
float **eigvecMatArr, SP_integer *eigvecMatColNum, SP_integer *eigvecMatRowNum,
- SP_integer *newDimension)
+ SP_integer newDimension)
{
// convert the Prolog array to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -75,20 +77,19 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
// create the ReturnMat
mat eigvecReturnMat;
- size_t returnDim = 0;
-
if (strcmp(kernel, "linear") == 0)
{
LinearKernel lk;
if(useNystroem == 1)
{
- useNystroemKernelPCA<LinearKernel>(nystroemMethod, lk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<LinearKernel>(nystroemMethod, lk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<LinearKernel, NaiveKernelRule<LinearKernel>>(lk, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<LinearKernel>(lk, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "polynomial") == 0)
@@ -96,12 +97,13 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
PolynomialKernel pk(degree, offset);
if(useNystroem == 1)
{
- useNystroemKernelPCA<PolynomialKernel>(nystroemMethod, pk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<PolynomialKernel>(nystroemMethod, pk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<PolynomialKernel, NaiveKernelRule<PolynomialKernel>>(pk, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<PolynomialKernel>(pk, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "cosine") == 0)
@@ -109,12 +111,13 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
CosineDistance cd;
if(useNystroem == 1)
{
- useNystroemKernelPCA<CosineDistance>(nystroemMethod, cd, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<CosineDistance>(nystroemMethod, cd, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<CosineDistance, NaiveKernelRule<CosineDistance>>(cd, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<CosineDistance>(cd, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "gaussian") == 0)
@@ -122,12 +125,13 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
GaussianKernel gk(bandwidth);
if(useNystroem == 1)
{
- useNystroemKernelPCA<GaussianKernel>(nystroemMethod, gk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<GaussianKernel>(nystroemMethod, gk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<GaussianKernel, NaiveKernelRule<GaussianKernel>>(gk, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<GaussianKernel>(gk, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "epanechnikov") == 0)
@@ -135,12 +139,13 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
EpanechnikovKernel ek(bandwidth);
if(useNystroem == 1)
{
- useNystroemKernelPCA<EpanechnikovKernel>(nystroemMethod, ek, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<EpanechnikovKernel>(nystroemMethod, ek, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<EpanechnikovKernel, NaiveKernelRule<EpanechnikovKernel>>(ek, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<EpanechnikovKernel>(ek, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "laplacian") == 0)
@@ -148,12 +153,13 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
LaplacianKernel tk(bandwidth);
if(useNystroem == 1)
{
- useNystroemKernelPCA<LaplacianKernel>(nystroemMethod, tk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<LaplacianKernel>(nystroemMethod, tk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<LaplacianKernel, NaiveKernelRule<LaplacianKernel>>(tk, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<LaplacianKernel>(tk, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else if (strcmp(kernel, "hyptan") == 0)
@@ -161,19 +167,35 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
HyperbolicTangentKernel htk(scale, offset);
if(useNystroem == 1)
{
- useNystroemKernelPCA<HyperbolicTangentKernel>(nystroemMethod, htk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ if(!useNystroemKernelPCA<HyperbolicTangentKernel>(nystroemMethod, htk, (centerTranformedData == 1), data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension))
+ return;
}
else
{
- KernelPCA<HyperbolicTangentKernel, NaiveKernelRule<HyperbolicTangentKernel>>(htk, (centerTranformedData == 1))
- .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, returnDim);
+ KernelPCA<HyperbolicTangentKernel>(htk, (centerTranformedData == 1))
+ .Apply(data, transformedDataReturnMat, eigvalReturnVector, eigvecReturnMat, newDimension);
}
}
else
{
raisePrologDomainExeption(kernel, 1, "The given Kernel is unkown!", "kernel_pca");
+ return;
+ }
+
+ if (newDimension < eigvecReturnMat.n_rows && newDimension > 0 && !useNystroem)
+ transformedDataReturnMat.shed_rows(newDimension, transformedDataReturnMat.n_rows - 1);
+ else
+ {
+ transformedDataReturnMat.shed_rows(data.n_rows, transformedDataReturnMat.n_rows - 1);
}
+ if(isnan(transformedDataReturnMat[0]))
+ {
+ raisePrologSystemExeption("Matrix contains nan!");
+ return;
+ }
+
+
// return the transformedData Matrix
returnMatrixInformation(transformedDataReturnMat, transformedDataMatArr, transformedDataMatColNum, transformedDataMatRowNum);
@@ -182,6 +204,4 @@ void kernel_pca(char const *kernel, SP_integer centerTranformedData, SP_integer
// return the eigvec Matrix
returnMatrixInformation(eigvecReturnMat, eigvecMatArr, eigvecMatColNum, eigvecMatRowNum);
-
- *newDimension = returnDim;
-}
\ No newline at end of file
+}
diff --git a/src/methods/kernel_pca/kernel_pca.pl b/src/methods/kernel_pca/kernel_pca.pl
index 62772b73c2ea978dfe1c36d47a5d2b4e41985678..01a1c62f7af1e806edf43c94a85b11b25728bb32 100644
--- a/src/methods/kernel_pca/kernel_pca.pl
+++ b/src/methods/kernel_pca/kernel_pca.pl
@@ -43,6 +43,8 @@ kernel_pca(Kernel, CenterTransformedData, UseNystroem, NystroemMethod, Degree, O
EigVecList, EigVecCols,
NewDimension) :-
Bandwidth > 0.0,
+ NewDimension >= 0,
+ Bandwidth =< DataRows,
convert_list_to_float_array(DataList, DataRows, array(Xsize, Xrownum, X)),
kernel_pcaI(Kernel, CenterTransformedData, UseNystroem, NystroemMethod, Degree, Offset, Bandwidth, Scale,
X, Xsize, Xrownum,
@@ -60,7 +62,7 @@ foreign(kernel_pca, c, kernel_pcaI( +string, +integer, +integer, +string,
-pointer(float_array), -integer, -integer,
-pointer(float_array), -integer,
-pointer(float_array), -integer, -integer,
- -integer)).
+ +integer)).
%% Defines the functions that get connected from main.cpp
diff --git a/src/methods/kernel_pca/kernel_pca_test.pl b/src/methods/kernel_pca/kernel_pca_test.pl
index 92735f99beb513796c6a0afef6e12b411e217689..f0c7864a9ff9c746e4749ead75fca94843bfe94e 100644
--- a/src/methods/kernel_pca/kernel_pca_test.pl
+++ b/src/methods/kernel_pca/kernel_pca_test.pl
@@ -6,8 +6,6 @@
:- use_module(kernel_pca).
:- use_module('../../helper_files/helper.pl').
-reset_Model :-
- initModel(1,0,50,0.0001).
%%
%% TESTING predicate kernel_pca/16
@@ -15,27 +13,167 @@ reset_Model :-
:- begin_tests(kernel_pca).
%% Failure Tests
-
-test(testDescription, [error(domain_error('expectation' , culprit), _)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, culprit, 50, 0.0001, _).
-
-test(testDescription2, [error(_,system_error('The values of the Label have to start at 0 and be >= 0 and < the given numClass!'))]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,1,0,2], 2, perceptron, 50, 0.0001, _).
+
+
+test(kernel_pca_Init_Wrong_Kernel, [error(domain_error('The given Kernel is unkown!' , wrongType), _)]) :-
+ kernel_pca(wrongType, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0, [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, _, _, _, _, _, 0).
+
+test(kernel_pca_Init_Wrong_NystroemMethod, [error(domain_error('The given NystroemMethod is unknown!' , wrongType), _)]) :-
+ kernel_pca(linear, 0, 1, wrongType, 1.0, 0.0, 1.0, 1.0, [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, _, _, _, _, _, 0).
+
+test(kernel_pca_Zero_Bandwidth, fail) :-
+ kernel_pca(linear, 0, 0, kmeans, 1.0, 0.0, 0.0, 1.0, [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, _, _, _, _, _, 0).
%% Successful Tests
-test(testDescription3, [true(Error =:= 1)]) :-
- reset_Model_No_Train(perceptron),
- train([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, [0,0,0,0], 2, perceptron, 50, 0.0001, Error).
+test(kernel_pca_Linear_Random) :-
+ kernel_pca(linear, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Linear_Ordered) :-
+ kernel_pca(linear, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Linear_Kmeans) :-
+ kernel_pca(linear, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Gaussian) :-
+ kernel_pca(gaussian, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(gaussian, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(gaussian, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Polynomial) :-
+ kernel_pca(polynomial, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(polynomial, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(polynomial, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Hyptan, [error(_, system_error('Matrix contains nan!'))]) :-
+ kernel_pca(hyptan, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(hyptan, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(hyptan, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Laplacian) :-
+ kernel_pca(laplacian, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(laplacian, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(laplacian, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Epanechnikov) :-
+ kernel_pca(epanechnikov, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(epanechnikov, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(epanechnikov, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_Cosine) :-
+ kernel_pca(cosine, 0, 0, random, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(cosine, 0, 0, ordered, 1.0, 0.0, 1.0, 1.0,
+ [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, _, _, _, _, _, 0),
+ kernel_pca(cosine, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0,
+ [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, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+
+test(kernel_pca_CSV_Input) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ kernel_pca(linear, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0, Data, 4, TransformedList, _, EigValList, EigVecList, _, 0),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
+
+test(kernel_pca_CSV_Input_Same_NewDims) :-
+ open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
+ take_csv_row(File, skipFirstRow,10, Data),
+ kernel_pca(linear, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0, Data, 4, TransformedList, _, EigValList, EigVecList, _, 4),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
-test(testDescription4, [true(Error =:= 0.9797958971132711)]) :-
- reset_Model_No_Train(perceptron),
+test(kernel_pca_CSV_Input_Smaller_NewDims) :-
open('/home/afkjakhes/eclipse-workspace/prolog-mlpack-libary/src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, perceptron, 50, 0.0001, Error).
+ kernel_pca(linear, 0, 0, kmeans, 1.0, 0.0, 1.0, 1.0, Data, 4, TransformedList, _, EigValList, EigVecList, _, 2),
+ print('\nTransformedData: '),
+ print(TransformedList),
+ print('\nEigenValues: '),
+ print(EigValList),
+ print('\nEigenVectors: '),
+ print(EigVecList).
:- end_tests(kernel_pca).
diff --git a/src/methods/lars/lars.cpp b/src/methods/lars/lars.cpp
index 1528da25bcf07dc0f7d0fc8021375aad37fefc15..ee00d5030328aa99c5226fa7de65c3e59f9ae9d6 100644
--- a/src/methods/lars/lars.cpp
+++ b/src/methods/lars/lars.cpp
@@ -153,7 +153,7 @@ double computeError(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMa
if(dataMatSize / dataMatRowNum != responsesArrSize)
{
cout << "Target dim doesnt fit to the Data dim" << endl;
- return;
+ return 0.0;
}
// convert the Prolog array to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -221,7 +221,7 @@ double train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum
if(dataMatSize / dataMatRowNum != responsesArrSize)
{
cout << "Target dim doesnt fit to the Data dim" << endl;
- return;
+ return 0.0;
}
// convert the Prolog array to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -239,4 +239,4 @@ double train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum
// return the Vector
returnVectorInformation(betaReturnVector, betaArr, betaArrSize);
return error;
-}
\ No newline at end of file
+}
diff --git a/test_all.pl b/test_all.pl
index 2b45b697f29b8b36e5a08d19df96a9c9e7595ecb..57c8267d4ae62cda7872619ae5814985a9d7a1cd 100644
--- a/test_all.pl
+++ b/test_all.pl
@@ -1,9 +1,15 @@
+:- use_module(library(plunit)).
+
+
+%% Just compile this file and call run_tests. to run every tests
+
+
:- use_module('src/methods/adaboost/adaboost_test.pl').
-:- use_module('src/methods/approx_kfn/approx_kfn_test.pl').
+%%:- use_module('src/methods/approx_kfn/approx_kfn_test.pl').
-:- use_module('src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl').
+%%:- use_module('src/methods/bayesian_linear_regression/bayesian_linear_regression_test.pl').
:- use_module('src/methods/dbscan/dbscan_test.pl').
@@ -13,83 +19,53 @@
:- use_module('src/methods/fastmks/fastmks_test.pl').
-:- use_module('src/methods/hoeffding_tree/hoeffding_tree_test.pl').
+%%:- use_module('src/methods/hoeffding_tree/hoeffding_tree_test.pl').
:- use_module('src/methods/kde/kde_test.pl').
:- use_module('src/methods/kernel_pca/kernel_pca_test.pl').
-:- use_module('src/methods/kfn/kfn_test.pl').
+%%:- use_module('src/methods/kfn/kfn_test.pl').
-:- use_module('src/methods/kmeans/kmeans_test.pl').
+%%:- use_module('src/methods/kmeans/kmeans_test.pl').
-:- use_module('src/methods/knn/knn_test.pl').
+%%:- use_module('src/methods/knn/knn_test.pl').
-:- use_module('src/methods/lars/lars_test.pl').
+%%:- use_module('src/methods/lars/lars_test.pl').
-:- use_module('src/methods/linear_regression/linear_regression_test.pl').
+%%:- use_module('src/methods/linear_regression/linear_regression_test.pl').
-:- use_module('src/methods/linear_SVM/linear_SVM_test.pl').
+%%:- use_module('src/methods/linear_SVM/linear_SVM_test.pl').
-:- use_module('src/methods/lmnn/lmnn_test.pl').
+%%:- use_module('src/methods/lmnn/lmnn_test.pl').
-:- use_module('src/methods/local_coordinate_coding/local_coordinate_coding_test.pl').
+%%:- use_module('src/methods/local_coordinate_coding/local_coordinate_coding_test.pl').
-:- use_module('src/methods/logistic_regression/logistic_regression_test.pl').
+%%:- use_module('src/methods/logistic_regression/logistic_regression_test.pl').
-:- use_module('src/methods/lsh/lsh_test.pl').
+%%:- use_module('src/methods/lsh/lsh_test.pl').
-:- use_module('src/methods/mean_shift/mean_shift_test.pl').
+%%:- use_module('src/methods/mean_shift/mean_shift_test.pl').
-:- use_module('src/methods/naive_bayes_classifier/naive_bayes_classifier_test.pl').
+%%:- use_module('src/methods/naive_bayes_classifier/naive_bayes_classifier_test.pl').
-:- use_module('src/methods/nca/nca_test.pl').
+%%:- use_module('src/methods/nca/nca_test.pl').
-:- use_module('src/methods/nmf/nmf_test.pl').
+%%:- use_module('src/methods/nmf/nmf_test.pl').
-:- use_module('src/methods/pca/pca_test.pl').
+%%:- use_module('src/methods/pca/pca_test.pl').
-:- use_module('src/methods/perceptron/perceptron_test.pl').
+%%:- use_module('src/methods/perceptron/perceptron_test.pl').
-:- use_module('src/methods/radical/radical_test.pl').
+%%:- use_module('src/methods/radical/radical_test.pl').
-:- use_module('src/methods/random_forest/random_forest_test.pl').
+%%:- use_module('src/methods/random_forest/random_forest_test.pl').
-:- use_module('src/methods/softmax_regression/softmax_regression_test.pl').
+%%:- use_module('src/methods/softmax_regression/softmax_regression_test.pl').
-:- use_module('src/methods/sparse_coding/sparse_coding_test.pl').
+%% better to run the parse_coding tests alone because the c++ Method writes out alot of Debug messages that make the tests hard to read.
+%%:- use_module('src/methods/sparse_coding/sparse_coding_test.pl').
:- use_module('src/helper_files/helper_tests.pl').
-run :-
- run_adaboost_tests,
- run_approx_kfn_tests,
- run_bayesian_linear_regression_tests,
- run_dbscan_tests,
- run_decision_tree_tests,
- run_emst_tests,
- run_fastmks_tests,
- run_hoeffding_tree_tests,
- run_kde_tests,
- run_kernel_pca_tests,
- run_kfn_tests,
- run_kmeans_tests,
- run_knn_tests,
- run_lars_tests,
- run_linear_regression_tests,
- run_linear_SVM_tests,
- run_lmnn_tests,
- run_local_coordinate_coding_tests,
- run_logistic_regression_tests,
- run_lsh_tests,
- run_mean_shift_tests,
- run_naive_bayes_classifier_tests,
- run_nca_tests,
- run_nmf_tests,
- run_pca_tests,
- run_perceptron_tests,
- run_radical_tests,
- run_random_forest_tests,
- run_softmax_regression_tests,
- run_sparse_coding_tests,
- run_helper_tests.
\ No newline at end of file
+