diff --git a/src/methods/hoeffding_tree/hoeffding_tree.cpp b/src/methods/hoeffding_tree/hoeffding_tree.cpp
index cbe023a7ad80001679f2b5433b40a617bf6d14f8..d9ca00e01af2e794c72034b4781e40647176ecef 100644
--- a/src/methods/hoeffding_tree/hoeffding_tree.cpp
+++ b/src/methods/hoeffding_tree/hoeffding_tree.cpp
@@ -45,6 +45,12 @@ void initAndBuildModel(char const *treeType,
{
// convert the Prolog arrays to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+ // check if labels fit the data
+ if (data.n_cols != labelsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of labels!");
+ return;
+ }
// convert the Prolog arrays to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
@@ -144,6 +150,12 @@ void train(float *dataMatArr, SP_integer dataMatSize, SP_integer dataMatRowNum,
// convert the Prolog arrays to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+ // check if labels fit the data
+ if (data.n_cols != labelsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of labels!");
+ return;
+ }
// convert the Prolog arrays to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
diff --git a/src/methods/hoeffding_tree/hoeffding_tree_test.pl b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
index e03e532ae8fd2dd27f028e92df8bbeedebf81cd2..280b7cb233a184da4d8822f1dbe5c6d7014e2e99 100644
--- a/src/methods/hoeffding_tree/hoeffding_tree_test.pl
+++ b/src/methods/hoeffding_tree/hoeffding_tree_test.pl
@@ -47,18 +47,18 @@ test(hoeffding_Init_Negative_ObservationsBeforeBinning, fail) :-
hoeffding_tree_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_Wrong_Label_Dims1, [error(_,system_error('Labels Vector is too short or its values are incorrect: should fit into [0,numClasses)!'))]) :-
+test(hoeffding_Init_With_Wrong_Label_Dims1, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
hoeffding_tree_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) :-
+test(hoeffding_Init_With_Wrong_Label_Dims2, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
hoeffding_tree_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
+%% doesnt cause an error
test(hoeffding_Init_With_Wrong_Label_Value) :-
hoeffding_tree_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!'))]) :-
+%% doesnt cause an error
+test(hoeffding_Init_With_Too_Many_Label_Value) :-
hoeffding_tree_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).
@@ -105,10 +105,11 @@ test(hoeffding_Init_InfoBinary_CSV_Input) :-
:- begin_tests(hoeffding_tree_classify).
%% Failure Tests
-
-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)!'))]) :-
+
+%% seems to be able to classify diffrent Dimensions than trained
+test(hoeffding_Classify_Different_Dims_To_Train) :-
reset_Model,
- hoeffding_tree_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),
+ hoeffding_tree_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], 2, PredicList, ProbsList),
print('\nPredictions: '),
print(PredicList),
print('\nProbabilities: '),
@@ -167,23 +168,23 @@ test(hoeffding_Classify_InfoBinary) :-
%% Failure Tests
-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)!'))]) :-
+test(hoeffding_Train_With_Wrong_Label_Dims1, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model,
- hoeffding_tree_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).
+ hoeffding_tree_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).
-%% If the label vector is to long it seems to cause no problems
-test(hoeffding_Train_With_Wrong_Label_Dims2) :-
+test(hoeffding_Train_With_Wrong_Label_Dims2, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model,
hoeffding_tree_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
+
+%% all 3 test dont cause an error
test(hoeffding_Train_With_Wrong_Label_Value) :-
reset_Model,
- hoeffding_tree_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).
+ hoeffding_tree_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).
-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!'))]) :-
+test(hoeffding_Train_With_Too_Many_Label_Value) :-
reset_Model,
- hoeffding_tree_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).
+ hoeffding_tree_train([3, 2, 0, 5, 1, 4, 1, 0, 4, 3, 3, 5, 0, 5, 5, 2, 5, 5, 0, 2], 4, [1,1,0,2,3], 0).
test(hoeffding_Train_Bad_Data_Dims) :-
reset_Model,
@@ -192,7 +193,7 @@ test(hoeffding_Train_Bad_Data_Dims) :-
%% Successful Tests
-test(testDescription3) :-
+test(hoeffding_Train_Normal_Use) :-
reset_Model,
hoeffding_tree_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),
hoeffding_tree_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).
@@ -200,5 +201,5 @@ test(testDescription3) :-
:- end_tests(hoeffding_tree_train).
run_hoeffding_tree_tests :-
- run_tests(hoeffding_tree_train).
+ run_tests.