F1-score to return 0.0 instead of NaN

src/Microsoft.ML.Data/Evaluators/BinaryClassifierEvaluator.cs

@@ -480,7 +480,16 @@ public Double LogLossReduction
                     }
                 }
 
-                public Double F1 { get { return 2 * PrecisionPos * RecallPos / (PrecisionPos + RecallPos); } }
+                public Double F1
+                {
+                    get
+                    {
+                        var precisionPlusRecall = PrecisionPos + RecallPos;
+                        if (precisionPlusRecall == 0)
+                            return 0;
+                        return 2 * PrecisionPos * RecallPos / precisionPlusRecall;
+                    }
+                }
 
                 public Counters(bool useRaw, Single threshold)
                 {

test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-out.txt

@@ -36,7 +36,7 @@ Negative precision: 0.655222 (0.0000)
 Negative recall:    1.000000 (0.0000)
 Log-loss:           1.000000 (0.0000)
 Log-loss reduction: -0.076058 (0.0000)
-F1 Score:               NaN (0.0000)
+F1 Score:           0.000000 (0.0000)
 AUPRC:              0.415719 (0.0000)
 
 ---------------------------------------

test/BaselineOutput/Common/FastTreeBinaryClassification/FastTreeHighMinDocs-TrainTest-breast-cancer-rp.txt

@@ -1,4 +1,4 @@
 FastTreeBinaryClassification
 AUC	Accuracy	Positive precision	Positive recall	Negative precision	Negative recall	Log-loss	Log-loss reduction	F1 Score	AUPRC	/mil	/iter	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.5	0.655222	0	0	0.655222	1	1	-0.076058	NaN	0.415719	10000	5	FastTreeBinaryClassification	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=FastTreeBinaryClassification{mil=10000 iter=5} cache=- dout=%Output% loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=%Data% out=%Output% seed=1	/mil:10000;/iter:5	
+0.5	0.655222	0	0	0.655222	1	1	-0.076058	0	0.415719	10000	5	FastTreeBinaryClassification	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=FastTreeBinaryClassification{mil=10000 iter=5} cache=- dout=%Output% loader=Text{sparse- col=Attr:TX:6 col=Label:0 col=Features:1-5,6,7-9} data=%Data% out=%Output% seed=1	/mil:10000;/iter:5	
 

test/BaselineOutput/SingleDebug/PriorPredictor/BinaryPrior-CV-breast-cancer-out.txt

@@ -42,7 +42,7 @@ Negative precision: 0.656163 (0.0263)
 Negative recall:    1.000000 (0.0000)
 Log-loss:           0.935104 (0.0247)
 Log-loss reduction: -0.009590 (0.0001)
-F1 Score:               NaN (NaN)
+F1 Score:           0.000000 (0.0000)
 AUPRC:              0.418968 (0.0212)
 
 ---------------------------------------

test/BaselineOutput/SingleDebug/PriorPredictor/BinaryPrior-CV-breast-cancer-rp.txt

@@ -1,4 +1,4 @@
 PriorPredictor
 AUC	Accuracy	Positive precision	Positive recall	Negative precision	Negative recall	Log-loss	Log-loss reduction	F1 Score	AUPRC	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.5	0.656163	0	0	0.656163	1	0.935104	-0.00959	NaN	0.418968	PriorPredictor	%Data%		%Output%	99	0	0	maml.exe CV tr=PriorPredictor threads=- dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% seed=1		
+0.5	0.656163	0	0	0.656163	1	0.935104	-0.00959	0	0.418968	PriorPredictor	%Data%		%Output%	99	0	0	maml.exe CV tr=PriorPredictor threads=- dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% seed=1		
 

test/BaselineOutput/SingleDebug/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-out.txt

@@ -26,7 +26,7 @@ Negative precision: 0.655222 (0.0000)
 Negative recall:    1.000000 (0.0000)
 Log-loss:           0.929318 (0.0000)
 Log-loss reduction: 0.000000 (0.0000)
-F1 Score:               NaN (0.0000)
+F1 Score:           0.000000 (0.0000)
 AUPRC:              0.415719 (0.0000)
 
 ---------------------------------------

test/BaselineOutput/SingleDebug/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-rp.txt

@@ -1,4 +1,4 @@
 PriorPredictor
 AUC	Accuracy	Positive precision	Positive recall	Negative precision	Negative recall	Log-loss	Log-loss reduction	F1 Score	AUPRC	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.5	0.655222	0	0	0.655222	1	0.929318	0	NaN	0.415719	PriorPredictor	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=PriorPredictor dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% out=%Output% seed=1		
+0.5	0.655222	0	0	0.655222	1	0.929318	0	0	0.415719	PriorPredictor	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=PriorPredictor dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% out=%Output% seed=1		
 

test/BaselineOutput/SingleRelease/PriorPredictor/BinaryPrior-CV-breast-cancer-out.txt

@@ -42,7 +42,7 @@ Negative precision: 0.656163 (0.0263)
 Negative recall:    1.000000 (0.0000)
 Log-loss:           0.935104 (0.0247)
 Log-loss reduction: -0.009590 (0.0001)
-F1 Score:               NaN (NaN)
+F1 Score:           0.000000 (0.0000)
 AUPRC:              0.418968 (0.0212)
 
 ---------------------------------------

test/BaselineOutput/SingleRelease/PriorPredictor/BinaryPrior-CV-breast-cancer-rp.txt

@@ -1,4 +1,4 @@
 PriorPredictor
 AUC	Accuracy	Positive precision	Positive recall	Negative precision	Negative recall	Log-loss	Log-loss reduction	F1 Score	AUPRC	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.5	0.656163	0	0	0.656163	1	0.935104	-0.00959	NaN	0.418968	PriorPredictor	%Data%		%Output%	99	0	0	maml.exe CV tr=PriorPredictor threads=- dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% seed=1		
+0.5	0.656163	0	0	0.656163	1	0.935104	-0.00959	0	0.418968	PriorPredictor	%Data%		%Output%	99	0	0	maml.exe CV tr=PriorPredictor threads=- dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% seed=1		
 

test/BaselineOutput/SingleRelease/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-out.txt

@@ -26,7 +26,7 @@ Negative precision: 0.655222 (0.0000)
 Negative recall:    1.000000 (0.0000)
 Log-loss:           0.929318 (0.0000)
 Log-loss reduction: 0.000000 (0.0000)
-F1 Score:               NaN (0.0000)
+F1 Score:           0.000000 (0.0000)
 AUPRC:              0.415719 (0.0000)
 
 ---------------------------------------

test/BaselineOutput/SingleRelease/PriorPredictor/BinaryPrior-TrainTest-breast-cancer-rp.txt

@@ -1,4 +1,4 @@
 PriorPredictor
 AUC	Accuracy	Positive precision	Positive recall	Negative precision	Negative recall	Log-loss	Log-loss reduction	F1 Score	AUPRC	Learner Name	Train Dataset	Test Dataset	Results File	Run Time	Physical Memory	Virtual Memory	Command Line	Settings	
-0.5	0.655222	0	0	0.655222	1	0.929318	0	NaN	0.415719	PriorPredictor	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=PriorPredictor dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% out=%Output% seed=1		
+0.5	0.655222	0	0	0.655222	1	0.929318	0	0	0.415719	PriorPredictor	%Data%	%Data%	%Output%	99	0	0	maml.exe TrainTest test=%Data% tr=PriorPredictor dout=%Output% loader=Text{col=Label:BL:0 col=Features:~} data=%Data% out=%Output% seed=1