Adding softmax_regression tests

src/methods/softmax_regression/softmax_regression.cpp

@@ -19,6 +19,7 @@ using namespace mlpack::regression;
 SoftmaxRegression softmaxRegression;
 
 
+
 // input:   const size_t 	inputSize = 0,
 //          const size_t 	numClasses = 0,
 //          const bool 	    fitIntercept = false//          
@@ -74,8 +75,7 @@ void initModelWithTrain(float *dataMatArr, SP_integer dataMatSize, SP_integer da
 SP_integer classifyPoint(float *pointArr, SP_integer pointArrSize)
 {
     // convert the Prolog arrays to arma::rowvec
-    rowvec pointVector = convertArrayToRowvec(pointArr, pointArrSize);
-    
+    vec pointVector = conv_to<vec>::from(convertArrayToRowvec(pointArr, pointArrSize));
 
     try
     {
@@ -118,6 +118,17 @@ void classifyMatrix(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMa
     }
     
     
+    // check for nan elements
+    if (labelsReturnVector.has_nan())
+    {
+        raisePrologSystemExeption("Labels return Vector contains nan!");
+        return;
+    }
+    if (probsReturnMat.has_nan())
+    {
+        raisePrologSystemExeption("Probabilities return Matrix contains nan!");
+        return;
+    }
     // return the Vector
     returnVectorInformation(labelsReturnVector, labelsArr, labelsArrSize);
     // return the Matrix
@@ -132,7 +143,8 @@ void classifyMatrix(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMa
 // description: 
 //          Computes accuracy of the learned model given the feature data and the labels associated with each data point.
 //
-double computeAccuracy(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize)
+double computeAccuracy(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, 
+                        float *labelsArr, SP_integer labelsArrSize)
 {
     // convert the Prolog array to arma::mat
     mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
@@ -144,6 +156,11 @@ double computeAccuracy(float *dataMatArr, SP_integer dataMatSize, SP_integer dat
     {
         return softmaxRegression.ComputeAccuracy(data, labelsVector);
     }
+    catch(const std::out_of_range& e)
+    {
+        raisePrologSystemExeption("The Labels Vector has the wrong Dimension!");
+        return 0.0;
+    }
     catch(const std::exception& e)
     {
         raisePrologSystemExeption(e.what());
@@ -188,7 +205,8 @@ void parameters(float **parametersMatArr, SP_integer *parametersMatColNum, SP_in
 // description: 
 //          Trains the softmax regression model with the given training data.
 //
-double train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, float *labelsArr, SP_integer labelsArrSize, SP_integer numClasses)
+double train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum, 
+                float *labelsArr, SP_integer labelsArrSize, SP_integer numClasses)
 {
     // convert the Prolog array to arma::mat
     mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);

src/methods/softmax_regression/softmax_regression.pl

@@ -25,7 +25,7 @@
 
 
 %% --Input--
-%%              int     inputSize       => 0,
+%%              int     inputSize       => 1,
 %%              int     numClasses      => 0,
 %%              bool    fitIntercept    => (1)true / (0)false => false
 %%
@@ -36,6 +36,8 @@
 %%              Be sure to use Train before calling Classif or ComputeAccuracy, otherwise the results may be meaningless.
 %%
 initModelNoTrain(InputSize, NumClasses, FitIntercept) :-
+        InputSize > 0,
+        NumClasses >= 0,
         initModelNoTrainI(InputSize, NumClasses, FitIntercept).
 
 foreign(initModelNoTrain, c, initModelNoTrainI( +integer, +integer, 
@@ -55,6 +57,8 @@ foreign(initModelNoTrain, c, initModelNoTrainI( +integer, +integer,
 %%              Initializes the softmax_regression model and trains it.
 %%
 initModelWithTrain(DataList, DataRows, LabelsList, NumClasses, Lambda, FitIntercept) :-
+        NumClasses >= 0,
+        Lambda >= 0,
         convert_list_to_float_array(DataList, DataRows, array(Xsize, Xrownum, X)),
         convert_list_to_float_array(LabelsList, array(Ysize, Y)),
         initModelWithTrainI(X, Xsize, Xrownum, Y, Ysize, NumClasses, Lambda, FitIntercept).
@@ -144,9 +148,9 @@ foreign(featureSize, c, featureSizeI([-integer])).
 %% --Description--
 %%              Get the model parameters.
 %%
-parameters(PraametersList, XCols) :-
+parameters(PrametersList, XCols) :-
         parametersI(X, XCols, XRows),
-        convert_float_array_to_2d_list(X, XCols, XRows, PraametersList).
+        convert_float_array_to_2d_list(X, XCols, XRows, PrametersList).
 
 foreign(parameters, c, parametersI(-pointer(float_array), -integer, -integer)).
 
@@ -163,6 +167,7 @@ foreign(parameters, c, parametersI(-pointer(float_array), -integer, -integer)).
 %%              Trains the softmax regression model with the given training data.
 %%
 train(DataList, DataRows, LabelsList, NumClasses, FinalValue) :-
+        NumClasses >= 0,
         convert_list_to_float_array(DataList, DataRows, array(Xsize, Xrownum, X)),
         convert_list_to_float_array(LabelsList, array(Ysize, Y)),
         trainI(X, Xsize, Xrownum, Y, Ysize, NumClasses, FinalValue).

src/methods/softmax_regression/softmax_regression_test.pl

@@ -6,38 +6,335 @@
 :- use_module(softmax_regression).
 :- use_module('../../helper_files/helper.pl').
 
-reset_Model :-
-        initModel(1,0,50,0.0001).
+reset_Model_NoTrain :-
+        initModelNoTrain(3, 2, 0).
+
+reset_Model_WithTrain :-
+        initModelWithTrain([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, 0.0001, 0).
+
+%%
+%% TESTING predicate initModelNoTrain/3
+%%
+:- begin_tests(initModelNoTrain).      
+
+%% Failure Tests
+                                            
+test(softmax_InitNoTrain_Negative_InputSize, fail) :-
+        initModelNoTrain(-1, 0, 0).
+
+test(softmax_InitNoTrain_Negative_InputSize, fail) :-
+        initModelNoTrain(3, -1, 0).
+        
+
+%% Successful Tests
+
+test(softmax_InitNoTrain_FitIntercept_False) :-
+        initModelNoTrain(3, 2, 0).
+
+test(softmax_InitNoTrain_FitIntercept_True) :-
+        initModelNoTrain(2, 3, 1).
+
+:- end_tests(initModelNoTrain).
+
+
+%%
+%% TESTING predicate initModelWithTrain/6
+%%
+:- begin_tests(initModelWithTrain).      
+
+%% Failure Tests
+                                            
+
+test(softmax_InitWithTrain_Negative_NumClass, fail) :-
+        initModelWithTrain([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], -1, 0.0001, 0).
+        
+test(softmax_InitWithTrain_Negative_Lambda, fail) :-
+        initModelWithTrain([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, -0.0001, 0).
+
+test(softmax_InitWithTrain_Wrong_Label_Dims1, [error(_,system_error('element-wise multiplication: incompatible matrix dimensions: 2x4 and 2x2'))]) :-
+        initModelWithTrain([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, 0.0001, 0).
+
+
+test(softmax_InitWithTrain_Wrong_Label_Dims2, [error(_,system_error('element-wise multiplication: incompatible matrix dimensions: 2x4 and 2x7'))]) :-
+        initModelWithTrain([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, 0.0001, 0).
+
+%% Doesnt cause exception
+test(softmax_InitWithTrain_Wrong_Label_Value) :-
+        initModelWithTrain([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, 0.0001, 0).
+
+%% Doesnt cause exception
+test(softmax_InitWithTrain_Too_Many_Label_Value) :-
+        initModelWithTrain([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, 0.0001, 0).
+        
+
+%% Successful Tests
+
+test(softmax_InitWithTrain_Direct_Input) :-
+        initModelWithTrain([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, 0.0001, 0).
+
+test(softmax_InitWithTrain_CSV_Input) :-
+        open('src/data_csv/iris2.csv', read, File),
+        take_csv_row(File, skipFirstRow,10, Data),
+        initModelWithTrain(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0.003, 1).
+
+:- end_tests(initModelWithTrain).
+
+
+%%
+%% TESTING predicate classifyPoint/2
+%%
+:- begin_tests(classifyPoint).      
+
+%% Failure Tests
+           
+%% Doesnt cause an exception                                 
+test(softmax_ClassifyPoint_On_Untrained_Model) :-
+        reset_Model_NoTrain,
+        classifyPoint([5.1,3.5,1.4], _).
+
+test(softmax_ClassifyPoint_With_Too_Big_Dims, [error(_,system_error('SoftmaxRegression::Classify(): dataset has 5 dimensions, but model has 3 dimensions!'))]) :-
+        reset_Model_WithTrain,
+        classifyPoint([5.1,3.5,1.4,5.2,3.2], _).
+
+test(softmax_ClassifyPoint_With_Too_Small_Dims, [error(_,system_error('SoftmaxRegression::Classify(): dataset has 2 dimensions, but model has 3 dimensions!'))]) :-
+        reset_Model_WithTrain,
+        classifyPoint([5.1,3.5], _).
+        
+
+%% Successful Tests
+
+test(softmax_ClassifyPoint) :-
+        reset_Model_WithTrain,
+        classifyPoint([4.1,2.5,1.4], Prediction),
+        print('\nPrediction: '),
+        print(Prediction).
+
+:- end_tests(classifyPoint).
+
+
+%%
+%% TESTING predicate classifyMatrix/5
+%%
+:- begin_tests(classifyMatrix).      
+
+%% Failure Tests
+                        
+%% Doesnt cause an exception                    
+test(softmax_ClassifyMatrix_On_Untrained_Model) :-
+        reset_Model_NoTrain,
+        classifyMatrix([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5], 3, _, _, _).
+
+test(softmax_ClassifyMatrix_With_Too_Big_Dims, [error(_,system_error('SoftmaxRegression::Classify(): dataset has 5 dimensions, but model has 3 dimensions!'))]) :-
+        reset_Model_WithTrain,
+        classifyMatrix([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5], 5, _, _, _).
+
+test(softmax_ClassifyMatrix_With_Too_Small_Dims, [error(_,system_error('SoftmaxRegression::Classify(): dataset has 2 dimensions, but model has 3 dimensions!'))]) :-
+        reset_Model_WithTrain,
+        classifyMatrix([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5], 2, _, _, _).
+        
+
+%% Successful Tests
+
+test(softmax_ClassifyMatrix_Direct_Input) :-
+        reset_Model_WithTrain,
+        classifyMatrix([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5], 3, PredicList, ProbsList, _),
+        print('\nPredicted Labels: '),
+        print(PredicList),
+        print('\nProbabilities: '),
+        print(ProbsList).
+
+test(softmax_ClassifyMatrix_CSV_Input) :-
+        open('src/data_csv/iris2.csv', read, File),
+        take_csv_row(File, skipFirstRow,10, Data),
+        initModelWithTrain(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0.003, 1),
+        classifyMatrix(Data, 4, PredicList, ProbsList, _),
+        print('\nPredicted Labels: '),
+        print(PredicList),
+        print('\nProbabilities: '),
+        print(ProbsList).
+
+:- end_tests(classifyMatrix).
+
+
+%%
+%% TESTING predicate computeAccuracy/4
+%%
+:- begin_tests(computeAccuracy).      
+
+%% Failure Tests
+
+%% Doesnt cause an exception
+test(softmax_ComputeAccuracy_On_Untrained_Model) :-
+        reset_Model_NoTrain,
+        computeAccuracy([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], _).
+
+test(softmax_ComputeAccuracy_Wrong_Label_Dims1, [error(_,system_error('The Labels Vector has the wrong Dimension!'))]) :-
+        reset_Model_WithTrain,
+        computeAccuracy([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], _).
+
+%% Doesnt cause exception
+test(softmax_ComputeAccuracy_Wrong_Label_Dims2) :-
+        reset_Model_WithTrain,
+        computeAccuracy([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], _).
+
+%% The same when the label values are out of range
+test(softmax_ComputeAccuracy_Wrong_Label_Value) :-
+        reset_Model_WithTrain,
+        computeAccuracy([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], _).
+
+%% Doesnt cause an exception
+test(softmax_ComputeAccuracy_Too_Many_Label_Value) :-
+        reset_Model_WithTrain,
+        computeAccuracy([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], _).
+
+test(softmax_ComputeAccuracy_Wrong_Data_Dims, [error(_,system_error('SoftmaxRegression::Classify(): dataset has 4 dimensions, but model has 3 dimensions!'))]) :-
+        reset_Model_WithTrain,
+        computeAccuracy([5.1,3.5,1.4,4.9,3.0,1.4,4.7,3.2,1.3,4.6,3.1,1.5], 4, [0,1,0], Accuracy),
+        print('\nAccuracy: '),
+        print(Accuracy).
+
+
+%% Successful Tests
+
+test(softmax_ComputeAccuracy_Direct_Input) :-
+        reset_Model_WithTrain,
+        computeAccuracy([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], Accuracy),
+        print('\nAccuracy: '),
+        print(Accuracy).
+
+test(softmax_ComputeAccuracy_CSV_Input) :-
+        open('src/data_csv/iris2.csv', read, File),
+        take_csv_row(File, skipFirstRow,10, Data),
+        initModelWithTrain(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0.003, 1),
+        computeAccuracy([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2], 4, [0,1,0,1], Accuracy),
+        print('\nAccuracy: '),
+        print(Accuracy).
+
+:- end_tests(computeAccuracy).
+
+
+%%
+%% TESTING predicate featureSize/1
+%%
+:- begin_tests(featureSize).      
+
+%% Failure Tests
+                                            
+
+        
+
+%% Successful Tests
+
+test(softmax_FeatureSize_No_Train) :-
+        reset_Model_NoTrain,
+        featureSize(FeatureSize),
+        print('\nFeatureSize: '),
+        print(FeatureSize).
+
+test(softmax_FeatureSize_Direct_Input) :-
+        reset_Model_WithTrain,
+        featureSize(FeatureSize),
+        print('\nFeatureSize: '),
+        print(FeatureSize).
+
+test(softmax_FeatureSize_CSV_Input) :-
+        open('src/data_csv/iris2.csv', read, File),
+        take_csv_row(File, skipFirstRow,10, Data),
+        initModelWithTrain(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0.003, 1),
+        featureSize(FeatureSize),
+        print('\nFeatureSize: '),
+        print(FeatureSize).
+
+:- end_tests(featureSize).
+
+
+%%
+%% TESTING predicate parameters/2
+%%
+:- begin_tests(parameters).      
+
+%% Failure Tests
+        
+
+%% Successful Tests
+
+test(softmax_Parameters_No_Train) :-
+        reset_Model_NoTrain,
+        parameters(PrametersList, _),
+        print('\nParameters: '),
+        print(PrametersList).
+
+test(softmax_Parameters_Direct_Input) :-
+        reset_Model_WithTrain,
+        parameters(PrametersList, _),
+        print('\nParameters: '),
+        print(PrametersList).
+
+test(softmax_Parameters_CSV_Input) :-
+        open('src/data_csv/iris2.csv', read, File),
+        take_csv_row(File, skipFirstRow,10, Data),
+        initModelWithTrain(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, 0.003, 1),
+        parameters(PrametersList, _),
+        print('\nParameters: '),
+        print(PrametersList).
+
+:- end_tests(parameters).
+
 
 %%
-%% TESTING predicate predicate/10
+%% TESTING predicate train/5
 %%
-:- begin_tests(predicate).      
+:- begin_tests(train).      
 
 %% 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(softmax_Train_Negative_NumClass, fail) :-
+        reset_Model_NoTrain,
+        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], -1, _).
+
+test(softmax_Train_Wrong_Label_Dims1, [error(_,system_error('element-wise multiplication: incompatible matrix dimensions: 2x4 and 2x2'))]) :-
+        reset_Model_NoTrain,
+        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], 2, _).
+
+%% If the label vector is to long it seems to cause no problems
+test(softmax_Train_Wrong_Label_Dims2, [error(_,system_error('element-wise multiplication: incompatible matrix dimensions: 2x4 and 2x7'))]) :-
+        reset_Model_NoTrain,
+        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, [0,1,0,1,0,0,1], 2, _).
 
-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, _).
+%% The same when the label values are out of range
+test(softmax_Train_Wrong_Label_Value) :-
+        reset_Model_NoTrain,
+        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, _).
+
+%% doesnt cause a exeption
+test(softmax_Train_Too_Many_Label_Value) :-
+        reset_Model_NoTrain,
+        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, [1,1,0,2], 2, _).
+
+%% doesnt cause a exeption
+test(softmax_Train_Wrong_Data_Dims) :-
+        reset_Model_NoTrain,
+        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], 4, [0,1,0], 2, _).
    
 
 %% 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(softmax_Train_Direct_Input) :-
+        reset_Model_NoTrain,
+        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, FinalValue),
+        print('\nFinalValue: '),
+        print(FinalValue).
 
-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),
+test(softmax_Train_CSV_Input) :-
+        initModelNoTrain(4, 2, 0),
+        open('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).
+        train(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, FinalValue),
+        print('\nFinalValue: '),
+        print(FinalValue).
+
+:- end_tests(train).
 
-:- end_tests(predicate).
 
 run_softmax_regression_tests :-
         run_tests.

test_all.pl

@@ -6,6 +6,9 @@
 
 %% The commented Methods either arent finished or still have some unfixed problems
 
+%% Make sure you run the tests in an sicstus Toplevel with prolog-mlpack-libary as its last path
+%% If not then the path to the iris2.csv will not be correct
+
 
 :- use_module('src/methods/adaboost/adaboost_test.pl').
 
@@ -63,7 +66,7 @@
 
 %%:- 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').
 
 %% better to run the sparse_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').