From bb4a353e34e3a3b1470180c4256f26e6715406b8 Mon Sep 17 00:00:00 2001
From: Jakhes <dean.schmitz@schmitzbauer.de>
Date: Mon, 7 Nov 2022 23:50:36 +0100
Subject: [PATCH] Finishing random_forest tests
---
src/methods/random_forest/random_forest.cpp | 56 ++++++++-
.../random_forest/random_forest_test.pl | 109 +++++++++---------
2 files changed, 111 insertions(+), 54 deletions(-)
diff --git a/src/methods/random_forest/random_forest.cpp b/src/methods/random_forest/random_forest.cpp
index f831a2a..913d54a 100644
--- a/src/methods/random_forest/random_forest.cpp
+++ b/src/methods/random_forest/random_forest.cpp
@@ -48,7 +48,12 @@ void initModelWithTrainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_i
{
// convert the Prolog array 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 array to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
@@ -57,6 +62,11 @@ void initModelWithTrainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_i
{
randomForest = RandomForest(data, labelsVector, numClasses, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
}
+ catch(const std::out_of_range& e)
+ {
+ raisePrologSystemExeption("The given Labels dont fit the format [0,Numclasses-1]!");
+ return;
+ }
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
@@ -86,6 +96,18 @@ void initModelWithTrainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP
{
// convert the Prolog array to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+ // check if labels and weights fit the data
+ if (data.n_cols != labelsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of labels!");
+ return;
+ }
+ if (data.n_cols != weightsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of weights!");
+ return;
+ }
+
// convert the Prolog array to arma::Row< size_t >
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
// convert the Prolog array to arma::rowvec
@@ -96,6 +118,11 @@ void initModelWithTrainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP
{
randomForest = RandomForest(data, labelsVector, numClasses, weightsVector, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
}
+ catch(const std::out_of_range& e)
+ {
+ raisePrologSystemExeption("The given Labels dont fit the format [0,Numclasses-1]!");
+ return;
+ }
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
@@ -214,6 +241,12 @@ double trainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer data
{
// convert the Prolog array 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 0.0;
+ }
// convert the Prolog array to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
@@ -222,6 +255,11 @@ double trainNoWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer data
{
return randomForest.Train(data, labelsVector, numClasses, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
}
+ catch(const std::out_of_range& e)
+ {
+ raisePrologSystemExeption("The given Labels dont fit the format [0,Numclasses-1]!");
+ return 0.0;
+ }
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
@@ -252,6 +290,17 @@ double trainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer da
{
// convert the Prolog arrays to arma::mat
mat data = convertArrayToMat(dataMatArr, dataMatSize, dataMatRowNum);
+ // check if labels and weights fit the data
+ if (data.n_cols != labelsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of labels!");
+ return 0.0;
+ }
+ if (data.n_cols != weightsArrSize)
+ {
+ raisePrologSystemExeption("The number of data points does not match the number of weights!");
+ return 0.0;
+ }
// convert the Prolog arrays to arma::rowvec
Row< size_t > labelsVector = convertArrayToVec(labelsArr, labelsArrSize);
// convert the Prolog arrays to arma::rowvec
@@ -262,6 +311,11 @@ double trainWithWeights(float *dataMatArr, SP_integer dataMatSize, SP_integer da
{
return randomForest.Train(data, labelsVector, numClasses, weightsVector, numTrees, minimumLeafSize, minimumGainSplit, maximumDepth);
}
+ catch(const std::out_of_range& e)
+ {
+ raisePrologSystemExeption("The given Labels dont fit the format [0,Numclasses-1]!");
+ return 0.0;
+ }
catch(const std::exception& e)
{
raisePrologSystemExeption(e.what());
diff --git a/src/methods/random_forest/random_forest_test.pl b/src/methods/random_forest/random_forest_test.pl
index 2ee6329..ac6b4e1 100644
--- a/src/methods/random_forest/random_forest_test.pl
+++ b/src/methods/random_forest/random_forest_test.pl
@@ -38,8 +38,6 @@ test(random_forest_InitModelNoTrain) :-
test(random_forest_InitModelWithTrainNoWeights_Negative_NumClasses, fail) :-
initModelWithTrainNoWeights([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, 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainNoWeights_Too_Many_NumClasses, fail) :-
- initModelWithTrainNoWeights([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], 15, 20, 1, 0.0000001, 0).
test(random_forest_InitModelWithTrainNoWeights_Negative_NumTrees, fail) :-
initModelWithTrainNoWeights([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, -20, 1, 0.0000001, 0).
@@ -54,13 +52,13 @@ test(random_forest_InitModelWithTrainNoWeights_Negative_MaxDepth, fail) :-
initModelWithTrainNoWeights([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, 20, 1, 0.0000001, -1).
-test(random_forest_InitModelWithTrainNoWeights_Too_Short_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainNoWeights_Too_Short_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
initModelWithTrainNoWeights([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, 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainNoWeights_Too_Long_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainNoWeights_Too_Long_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
initModelWithTrainNoWeights([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, [0,1,0,1,0,1], 2, 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainNoWeights_Too_Many_Label_Classes, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainNoWeights_Too_Many_Label_Classes, [error(_,system_error('The given Labels dont fit the format [0,Numclasses-1]!'))]) :-
initModelWithTrainNoWeights([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, [0,1,2,3], 2, 20, 1, 0.0000001, 0).
@@ -88,9 +86,6 @@ test(random_forest_InitModelWithTrainNoWeights_CSV_Input) :-
test(random_forest_InitModelWithTrainWithWeights_Negative_NumClasses, fail) :-
initModelWithTrainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainWithWeights_Too_Many_NumClasses, fail) :-
- initModelWithTrainWithWeights([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], 15, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
-
test(random_forest_InitModelWithTrainWithWeights_Negative_NumTrees, fail) :-
initModelWithTrainWithWeights([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, [0.5,0.1,0.7,1.2], -20, 1, 0.0000001, 0).
@@ -104,24 +99,21 @@ test(random_forest_InitModelWithTrainWithWeights_Negative_MaxDepth, fail) :-
initModelWithTrainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, -1).
-test(random_forest_InitModelWithTrainWithWeights_Too_Short_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainWithWeights_Too_Short_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
initModelWithTrainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainWithWeights_Too_Long_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainWithWeights_Too_Long_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
initModelWithTrainWithWeights([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, [0,1,0,1,0,1], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainWithWeights_Too_Many_Label_Classes, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainWithWeights_Too_Many_Label_Classes, [error(_,system_error('The given Labels dont fit the format [0,Numclasses-1]!'))]) :-
initModelWithTrainWithWeights([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, [0,1,2,3], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainWithWeights_Too_Short_Weights, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainWithWeights_Too_Short_Weights, [error(_,system_error('The number of data points does not match the number of weights!'))]) :-
initModelWithTrainWithWeights([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, [0.5,0.1], 20, 1, 0.0000001, 0).
-test(random_forest_InitModelWithTrainWithWeights_Too_Long_Weights, [error(_,system_error('Error'))]) :-
+test(random_forest_InitModelWithTrainWithWeights_Too_Long_Weights, [error(_,system_error('The number of data points does not match the number of weights!'))]) :-
initModelWithTrainWithWeights([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, [0.5,0.1,0.7,1.2,0.43,2.0], 20, 1, 0.0000001, 0).
-
-test(random_forest_InitModelWithTrainWithWeights_Too_Many_Weights_Classes, [error(_,system_error('Error'))]) :-
- initModelWithTrainWithWeights([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, [-0.5,0.1,-0.7,1.2], 20, 1, 0.0000001, 0).
%% Successful Tests
@@ -132,7 +124,7 @@ test(random_forest_InitModelWithTrainWithWeights_Normal_Use) :-
test(random_forest_InitModelWithTrainWithWeights_CSV_Input) :-
open('src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- initModelWithTrainWithWeights(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0).
+ initModelWithTrainWithWeights(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, [0.5,0.1,0.7,1.2,0.5,3.4,0.9,0.5,0.5,1.2], 20, 1, 0.0000001, 0).
:- end_tests(initModelWithTrainWithWeights).
@@ -145,17 +137,27 @@ test(random_forest_InitModelWithTrainWithWeights_CSV_Input) :-
%% Failure Tests
-test(random_forest_ClassifyPoint_Before_Train, [error(_,system_error('Error'))]) :-
+test(random_forest_ClassifyPoint_Before_Train, [error(_,system_error('RandomForest::Classify(): no random forest trained!'))]) :-
reset_Model_NoTrain,
classifyPoint([5.1,3.5,1.4], _, _).
-test(random_forest_ClassifyPoint_Smaller_Dim_To_Train, [error(_,system_error('Error'))]) :-
+%% Point dim seems to not matter
+test(random_forest_ClassifyPoint_Smaller_Dim_To_Train) :-
reset_Model_WithTrain,
- classifyPoint([5.1,3.5], _, _).
+ classifyPoint([5.1,3.5], Prediction, ProbabilitiesList),
+ print('\nPrediction: '),
+ print(Prediction),
+ print('\nProbabilities: '),
+ print(ProbabilitiesList).
-test(random_forest_ClassifyPoint_Larger_Dim_To_Train, [error(_,system_error('Error'))]) :-
+%% Point dim seems to not matter
+test(random_forest_ClassifyPoint_Larger_Dim_To_Train) :-
reset_Model_WithTrain,
- classifyPoint([5.1,3.5,1.4,4.3,0.4], _, _).
+ classifyPoint([5.1,3.5,1.4,4.3,0.4], Prediction, ProbabilitiesList),
+ print('\nPrediction: '),
+ print(Prediction),
+ print('\nProbabilities: '),
+ print(ProbabilitiesList).
%% Successful Tests
@@ -179,17 +181,27 @@ test(random_forest_ClassifyPoint_Normal_Use) :-
%% Failure Tests
-test(random_forest_ClassifyMatrix_Before_Train, [error(_,system_error('Error'))]) :-
+test(random_forest_ClassifyMatrix_Before_Train, [error(_,system_error('RandomForest::Classify(): no random forest trained!'))]) :-
reset_Model_NoTrain,
classifyMatrix([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(random_forest_ClassifyMatrix_Smaller_Dim_To_Train, [error(_,system_error('Error'))]) :-
+%% Classify dim seems to not matter
+test(random_forest_ClassifyMatrix_Smaller_Dim_To_Train) :-
reset_Model_WithTrain,
- classifyMatrix([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, _, _, _).
+ classifyMatrix([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, Prediction, ProbabilitiesList, _),
+ print('\nPrediction: '),
+ print(Prediction),
+ print('\nProbabilities: '),
+ print(ProbabilitiesList).
-test(random_forest_ClassifyMatrix_Larger_Dim_To_Train, [error(_,system_error('Error'))]) :-
+%% Classify dim seems to not matter
+test(random_forest_ClassifyMatrix_Larger_Dim_To_Train) :-
reset_Model_WithTrain,
- classifyMatrix([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, _, _, _).
+ classifyMatrix([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, Prediction, ProbabilitiesList, _),
+ print('\nPrediction: '),
+ print(Prediction),
+ print('\nProbabilities: '),
+ print(ProbabilitiesList).
%% Successful Tests
@@ -207,15 +219,18 @@ test(random_forest_ClassifyMatrix_Normal_Use) :-
%%
-%% TESTING predicate numTrees/10
+%% TESTING predicate numTrees/1
%%
:- begin_tests(numTrees).
%% Failure Tests
-
-test(random_forest_NumTrees_Before_Train, [error(_,system_error('Error'))]) :-
+
+%% doesnt cause an error
+test(random_forest_NumTrees_Before_Train) :-
reset_Model_NoTrain,
- numTrees(_).
+ numTrees(NumTrees),
+ print('\nNumber of Trees: '),
+ print(NumTrees).
%% Successful Tests
@@ -231,7 +246,7 @@ test(random_forest_NumTrees_Normal_Use) :-
%%
-%% TESTING predicate trainNoWeights/10
+%% TESTING predicate trainNoWeights/9
%%
:- begin_tests(trainNoWeights).
@@ -241,10 +256,6 @@ test(random_forest_TrainNoWeights_Negative_NumClasses, fail) :-
reset_Model_NoTrain,
trainNoWeights([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, 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainNoWeights_Too_Many_NumClasses, fail) :-
- reset_Model_NoTrain,
- trainNoWeights([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], 15, 20, 1, 0.0000001, 0, _).
-
test(random_forest_TrainNoWeights_Negative_NumTrees, fail) :-
reset_Model_NoTrain,
trainNoWeights([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, -20, 1, 0.0000001, 0, _).
@@ -262,15 +273,15 @@ test(random_forest_TrainNoWeights_Negative_MaxDepth, fail) :-
trainNoWeights([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, 20, 1, 0.0000001, -1, _).
-test(random_forest_TrainNoWeights_Too_Short_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainNoWeights_Too_Short_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model_NoTrain,
trainNoWeights([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, 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainNoWeights_Too_Long_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainNoWeights_Too_Long_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model_NoTrain,
trainNoWeights([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, [0,1,0,1,0,1], 2, 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainNoWeights_Too_Many_Label_Classes, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainNoWeights_Too_Many_Label_Classes, [error(_,system_error('The given Labels dont fit the format [0,Numclasses-1]!'))]) :-
reset_Model_NoTrain,
trainNoWeights([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, [0,1,2,3], 2, 20, 1, 0.0000001, 0, _).
@@ -306,10 +317,6 @@ test(random_forest_TrainWithWeights_Negative_NumClasses, fail) :-
reset_Model_NoTrain,
trainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainWithWeights_Too_Many_NumClasses, fail) :-
- reset_Model_NoTrain,
- trainWithWeights([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], 15, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, _).
-
test(random_forest_TrainWithWeights_Negative_NumTrees, fail) :-
reset_Model_NoTrain,
trainWithWeights([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, [0.5,0.1,0.7,1.2], -20, 1, 0.0000001, 0, _).
@@ -327,30 +334,26 @@ test(random_forest_TrainWithWeights_Negative_MaxDepth, fail) :-
trainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, -1, _).
-test(random_forest_TrainWithWeights_Too_Short_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainWithWeights_Too_Short_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model_NoTrain,
trainWithWeights([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, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainWithWeights_Too_Long_Label, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainWithWeights_Too_Long_Label, [error(_,system_error('The number of data points does not match the number of labels!'))]) :-
reset_Model_NoTrain,
trainWithWeights([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, [0,1,0,1,0,1], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainWithWeights_Too_Many_Label_Classes, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainWithWeights_Too_Many_Label_Classes, [error(_,system_error('The given Labels dont fit the format [0,Numclasses-1]!'))]) :-
reset_Model_NoTrain,
trainWithWeights([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, [0,1,2,3], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainWithWeights_Too_Short_Weights, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainWithWeights_Too_Short_Weights, [error(_,system_error('The number of data points does not match the number of weights!'))]) :-
reset_Model_NoTrain,
trainWithWeights([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, [0.5,0.1], 20, 1, 0.0000001, 0, _).
-test(random_forest_TrainWithWeights_Too_Long_Weights, [error(_,system_error('Error'))]) :-
+test(random_forest_TrainWithWeights_Too_Long_Weights, [error(_,system_error('The number of data points does not match the number of weights!'))]) :-
reset_Model_NoTrain,
trainWithWeights([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, [0.5,0.1,0.7,1.2,0.43,2.0], 20, 1, 0.0000001, 0, _).
-
-test(random_forest_TrainWithWeights_Too_Many_Weights_Classes, [error(_,system_error('Error'))]) :-
- reset_Model_NoTrain,
- trainWithWeights([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, [-0.5,0.1,-0.7,1.2], 20, 1, 0.0000001, 0, _).
%% Successful Tests
@@ -365,7 +368,7 @@ test(random_forest_TrainWithWeights_CSV_Input) :-
reset_Model_NoTrain,
open('src/data_csv/iris2.csv', read, File),
take_csv_row(File, skipFirstRow,10, Data),
- trainWithWeights(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, [0.5,0.1,0.7,1.2], 20, 1, 0.0000001, 0, Entropy),
+ trainWithWeights(Data, 4, [0,1,0,1,1,0,1,1,1,0], 2, [0.5,0.1,0.7,1.2,0.5,3.4,0.9,0.5,0.5,1.2], 20, 1, 0.0000001, 0, Entropy),
print('\nEntropy: '),
print(Entropy).
--
GitLab