substituted winequality dataset with machine generated dataset (#937)

Author: artidoro

build.proj

@@ -75,11 +75,7 @@
              Targets="Pack" />
   </Target>
 
-  <ItemGroup>
-    <TestFile Include="$(MSBuildThisFileDirectory)/test/data/external/winequality-white.csv"
-      Url="https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv"
-      DestinationFile="$(MSBuildThisFileDirectory)test/data/external/winequality-white.csv" />
-    
+  <ItemGroup>  
     <TestFile Condition="'$(IncludeBenchmarkData)' == 'true'" Include="$(MSBuildThisFileDirectory)/test/data/external/WikiDetoxAnnotated160kRows.tsv"
       Url="https://aka.ms/tlc-resources/benchmarks/WikiDetoxAnnotated160kRows.tsv"
       DestinationFile="$(MSBuildThisFileDirectory)test/data/external/WikiDetoxAnnotated160kRows.tsv" />

test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-wine-out.txt renamed to test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-generatedRegressionDataset-out.txt

@@ -7,24 +7,24 @@ Not adding a normalizer.
 Auto-tuning parameters: UseCat = False
 LightGBM objective=regression
 Not training a calibrator because it is not needed.
-L1(avg):            0.524348
-L2(avg):            0.466735
-RMS(avg):           0.683180
-Loss-fn(avg):       0.466735
-R Squared:          0.400415
-L1(avg):            0.517508
-L2(avg):            0.458039
-RMS(avg):           0.676786
-Loss-fn(avg):       0.458039
-R Squared:          0.420159
+L1(avg):            27.477977
+L2(avg):            1,428.594095
+RMS(avg):           37.796747
+Loss-fn(avg):       1,428.594094
+R Squared:          0.920504
+L1(avg):            26.801569
+L2(avg):            1,413.398603
+RMS(avg):           37.595194
+Loss-fn(avg):       1,413.398596
+R Squared:          0.923322
 
 OVERALL RESULTS
 ---------------------------------------
-L1(avg):            0.520928 (0.0034)
-L2(avg):            0.462387 (0.0043)
-RMS(avg):           0.679983 (0.0032)
-Loss-fn(avg):       0.462387 (0.0043)
-R Squared:          0.410287 (0.0099)
+L1(avg):            27.139773 (0.3382)
+L2(avg):            1,420.996349 (7.5977)
+RMS(avg):           37.695971 (0.1008)
+Loss-fn(avg):       1,420.996345 (7.5977)
+R Squared:          0.921913 (0.0014)
 
 ---------------------------------------
 Physical memory usage(MB): %Number%
@@ -35,10 +35,10 @@ Virtual memory usage(MB): %Number%
 [1] 'Loading data for LightGBM' started.
 [1] 'Loading data for LightGBM' finished in %Time%.
 [2] 'Training with LightGBM' started.
-[2] (%Time%)	Iteration: 50	Training-l2: 0.189697165394939
+[2] (%Time%)	Iteration: 50	Training-l2: 37.107605006517
 [2] 'Training with LightGBM' finished in %Time%.
 [3] 'Loading data for LightGBM #2' started.
 [3] 'Loading data for LightGBM #2' finished in %Time%.
 [4] 'Training with LightGBM #2' started.
-[4] (%Time%)	Iteration: 50	Training-l2: 0.204982247876212
+[4] (%Time%)	Iteration: 50	Training-l2: 27.7037679135951
 [4] 'Training with LightGBM #2' finished in %Time%.

test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-wine-rp.txt renamed to test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-generatedRegressionDataset-rp.txt

@@ -1,4 +1,4 @@
 LightGBMR
 L1(avg)	L2(avg)	RMS(avg)	Loss-fn(avg)	R Squared	/iter	/lr	/nl	/mil	/booster	/v	/nt	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.520928	0.462387	0.679983	0.462387	0.410287	50	0.2	20	10	gbdt{l2=0.2 l1=0.2}	+	1	LightGBMR	%Data%		%Output%	99	0	0	maml.exe CV tr=LightGBMR{nt=1 iter=50 v=+ booster=gbdt{l1=0.2 l2=0.2} lr=0.2 mil=10 nl=20} threads=- dout=%Output% loader=Text{col=Label:R4:11 col=Features:R4:0-10 sep=; header+} data=%Data% seed=1	/iter:50;/lr:0.2;/nl:20;/mil:10;/booster:gbdt{l2=0.2 l1=0.2};/v:+;/nt:1	
+27.13977	1420.996	37.69597	1420.996	0.921913	50	0.2	20	10	gbdt{l2=0.2 l1=0.2}	+	1	LightGBMR	%Data%		%Output%	99	0	0	maml.exe CV tr=LightGBMR{nt=1 iter=50 v=+ booster=gbdt{l1=0.2 l2=0.2} lr=0.2 mil=10 nl=20} threads=- dout=%Output% loader=Text{col=Label:R4:11 col=Features:R4:0-10 sep=; header+} data=%Data% seed=1	/iter:50;/lr:0.2;/nl:20;/mil:10;/booster:gbdt{l2=0.2 l1=0.2};/v:+;/nt:1	
 

test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-generatedRegressionDataset.txt

@@ -3,19 +3,19 @@ Not adding a normalizer.
 Auto-tuning parameters: UseCat = False
 LightGBM objective=regression
 Not training a calibrator because it is not needed.
-L1(avg):            0.402080
-L2(avg):            0.272274
-RMS(avg):           0.521799
-Loss-fn(avg):       0.272274
-R Squared:          0.652798
+L1(avg):            3.472291
+L2(avg):            26.064428
+RMS(avg):           5.105333
+Loss-fn(avg):       26.064428
+R Squared:          0.998571
 
 OVERALL RESULTS
 ---------------------------------------
-L1(avg):            0.402080 (0.0000)
-L2(avg):            0.272274 (0.0000)
-RMS(avg):           0.521799 (0.0000)
-Loss-fn(avg):       0.272274 (0.0000)
-R Squared:          0.652798 (0.0000)
+L1(avg):            3.472291 (0.0000)
+L2(avg):            26.064428 (0.0000)
+RMS(avg):           5.105333 (0.0000)
+Loss-fn(avg):       26.064428 (0.0000)
+R Squared:          0.998571 (0.0000)
 
 ---------------------------------------
 Physical memory usage(MB): %Number%
@@ -26,7 +26,7 @@ Virtual memory usage(MB): %Number%
 [1] 'Loading data for LightGBM' started.
 [1] 'Loading data for LightGBM' finished in %Time%.
 [2] 'Training with LightGBM' started.
-[2] (%Time%)	Iteration: 50	Training-l2: 0.272273893168108
+[2] (%Time%)	Iteration: 50	Training-l2: 26.0644295080124
 [2] 'Training with LightGBM' finished in %Time%.
 [3] 'Saving model' started.
 [3] 'Saving model' finished in %Time%.

test/BaselineOutput/SingleDebug/LightGBMR/LightGBMReg-CV-wine.txt

@@ -0,0 +1,4 @@
+LightGBMR
+L1(avg)	L2(avg)	RMS(avg)	Loss-fn(avg)	R Squared	/iter	/lr	/nl	/mil	/booster	/v	/nt	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
+3.472291	26.06443	5.105333	26.06443	0.998571	50	0.2	20	10	gbdt{l2=0.2 l1=0.2}	+	1	LightGBMR	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=LightGBMR{nt=1 iter=50 v=+ booster=gbdt{l1=0.2 l2=0.2} lr=0.2 mil=10 nl=20} dout=%Output% loader=Text{col=Label:R4:11 col=Features:R4:0-10 sep=; header+} data=%Data% out=%Output% seed=1	/iter:50;/lr:0.2;/nl:20;/mil:10;/booster:gbdt{l2=0.2 l1=0.2};/v:+;/nt:1	
+