Fix ResultProcessor bug, LogisticRegression bug and missing value conversion bug

src/Microsoft.ML.Data/Data/Conversion.cs

@@ -1170,7 +1170,7 @@ private bool IsStdMissing(ref ReadOnlySpan<char> span)
         public bool TryParseKey(ref TX src, U8 min, U8 max, out U8 dst)
         {
             var span = src.Span;
-            Contracts.Check(!IsStdMissing(ref span), "Missing text value cannot be converted to unsigned integer type.");
+            Contracts.Check(span.IsEmpty || !IsStdMissing(ref span), "Missing text value cannot be converted to unsigned integer type.");
             Contracts.Assert(min <= max);
 
             // This simply ensures we don't have min == 0 and max == U8.MaxValue. This is illegal since
@@ -1530,7 +1530,7 @@ public bool TryParse(ref TX src, out BL dst)
         {
             var span = src.Span;
 
-            Contracts.Check(!IsStdMissing(ref span), "Missing text values cannot be converted to bool value.");
+            Contracts.Check(span.IsEmpty || !IsStdMissing(ref span), "Missing text value cannot be converted to bool type.");
 
             char ch;
             switch (src.Length)

src/Microsoft.ML.Data/Transforms/ConcatTransform.cs

@@ -384,7 +384,7 @@ public static IDataTransform Create(IHostEnvironment env, TaggedArguments args,
                 env.CheckUserArg(Utils.Size(args.Column[i].Source) > 0, nameof(args.Column));
 
             var cols = args.Column
-                .Select(c => new ColumnInfo(c.Name, c.Source.Select(kvp => (kvp.Value, kvp.Key))))
+                .Select(c => new ColumnInfo(c.Name, c.Source.Select(kvp => (kvp.Value, kvp.Key != "" ? kvp.Key : null))))
                 .ToArray();
             var transformer = new ConcatTransform(env, cols);
             return transformer.MakeDataTransform(input);

src/Microsoft.ML.Data/Transforms/TermEstimator.cs

@@ -21,6 +21,9 @@ public static class Defaults
 
         private readonly IHost _host;
         private readonly TermTransform.ColumnInfo[] _columns;
+        private readonly string _file;
+        private readonly string _termsColumn;
+        private readonly IComponentFactory<IMultiStreamSource, IDataLoader> _loaderFactory;
 
         /// <summary>
         /// Convenience constructor for public facing API.
@@ -32,18 +35,23 @@ public static class Defaults
         /// <param name="sort">How items should be ordered when vectorized. By default, they will be in the order encountered.
         /// If by value items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
         public TermEstimator(IHostEnvironment env, string inputColumn, string outputColumn = null, int maxNumTerms = Defaults.MaxNumTerms, TermTransform.SortOrder sort = Defaults.Sort) :
-           this(env, new TermTransform.ColumnInfo(inputColumn, outputColumn ?? inputColumn, maxNumTerms, sort))
+           this(env, new[] { new TermTransform.ColumnInfo(inputColumn, outputColumn ?? inputColumn, maxNumTerms, sort) })
         {
         }
 
-        public TermEstimator(IHostEnvironment env, params TermTransform.ColumnInfo[] columns)
+        public TermEstimator(IHostEnvironment env, TermTransform.ColumnInfo[] columns,
+            string file = null, string termsColumn = null,
+            IComponentFactory<IMultiStreamSource, IDataLoader> loaderFactory = null)
         {
             Contracts.CheckValue(env, nameof(env));
             _host = env.Register(nameof(TermEstimator));
             _columns = columns;
+            _file = file;
+            _termsColumn = termsColumn;
+            _loaderFactory = loaderFactory;
         }
 
-        public TermTransform Fit(IDataView input) => new TermTransform(_host, input, _columns);
+        public TermTransform Fit(IDataView input) => new TermTransform(_host, input, _columns, _file, _termsColumn, _loaderFactory);
 
         public SchemaShape GetOutputSchema(SchemaShape inputSchema)
         {

src/Microsoft.ML.Data/Transforms/TermTransform.cs

@@ -268,7 +268,7 @@ public TermTransform(IHostEnvironment env, IDataView input,
             this(env, input, columns, null, null, null)
         { }
 
-        private TermTransform(IHostEnvironment env, IDataView input,
+        internal TermTransform(IHostEnvironment env, IDataView input,
             ColumnInfo[] columns,
             string file = null, string termsColumn = null,
             IComponentFactory<IMultiStreamSource, IDataLoader> loaderFactory = null)
@@ -314,13 +314,13 @@ public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataV
                     if (!Enum.IsDefined(typeof(SortOrder), sortOrder))
                         throw env.ExceptUserArg(nameof(args.Sort), "Undefined sorting criteria '{0}' detected for column '{1}'", sortOrder, item.Name);
 
-                    cols[i] = new ColumnInfo(item.Source,
+                    cols[i] = new ColumnInfo(item.Source ?? item.Name,
                         item.Name,
                         item.MaxNumTerms ?? args.MaxNumTerms,
                         sortOrder,
                         item.Term,
                         item.TextKeyValues ?? args.TextKeyValues);
-                    cols[i].Terms = item.Terms;
+                    cols[i].Terms = item.Terms ?? args.Terms;
                 };
             }
             return new TermTransform(env, input, cols, args.DataFile, args.TermsColumn, args.Loader).MakeDataTransform(input);

src/Microsoft.ML.ResultProcessor/ResultProcessor.cs

@@ -1063,10 +1063,10 @@ private static Experiment CreateVisualizationExperiment(ExperimentItemResult res
             var experiment = new ML.Runtime.ExperimentVisualization.Experiment
             {
                 Key = index.ToString(),
-                CompareGroup = string.IsNullOrEmpty(result.CustomizedTag) ? result.Trainer.Kind : result.CustomizedTag,
+                CompareGroup = string.IsNullOrEmpty(result.CustomizedTag) ? result.TrainerKind : result.CustomizedTag,
                 Trainer = new ML.Runtime.ExperimentVisualization.Trainer
                 {
-                    Name = result.Trainer.Kind,
+                    Name = result.TrainerKind,
                     ParameterSets = new List<ML.Runtime.ExperimentVisualization.Item>()
                 },
                 DataSet = new ML.Runtime.ExperimentVisualization.DataSet { File = result.Datafile },
@@ -1152,7 +1152,10 @@ private static object Load(Stream stream)
 
         public static int Main(string[] args)
         {
-            return Main(new ConsoleEnvironment(42), args);
+            string currentDirectory = Path.GetDirectoryName(typeof(ResultProcessor).Module.FullyQualifiedName);
+            using (var env = new ConsoleEnvironment(42))
+            using (AssemblyLoadingUtils.CreateAssemblyRegistrar(env, currentDirectory))
+                return Main(env, args);
         }
 
         public static int Main(IHostEnvironment env, string[] args)

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -373,7 +373,7 @@ protected override ParameterMixingCalibratedPredictor CreatePredictor()
             CurrentWeights.GetItemOrDefault(0, ref bias);
             CurrentWeights.CopyTo(ref weights, 1, CurrentWeights.Length - 1);
             return new ParameterMixingCalibratedPredictor(Host,
-                new LinearBinaryPredictor(Host, ref weights, bias),
+                new LinearBinaryPredictor(Host, ref weights, bias, _stats),
                 new PlattCalibrator(Host, -1, 0));
         }
 

src/Microsoft.ML.Sweeper/Algorithms/NelderMead.cs

@@ -26,7 +26,7 @@ public sealed class Arguments
             public IComponentFactory<IValueGenerator>[] SweptParameters;
 
             [Argument(ArgumentType.LastOccurenceWins, HelpText = "The sweeper used to get the initial results.", ShortName = "init", SignatureType = typeof(SignatureSweeperFromParameterList))]
-            public IComponentFactory<IValueGenerator[], ISweeper> FirstBatchSweeper;
+            public IComponentFactory<IValueGenerator[], ISweeper> FirstBatchSweeper = ComponentFactoryUtils.CreateFromFunction<IValueGenerator[], ISweeper>((host, array) => new UniformRandomSweeper(host, new SweeperBase.ArgumentsBase(), array));
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Seed for the random number generator for the first batch sweeper", ShortName = "seed")]
             public int RandomSeed;

src/Microsoft.ML.Sweeper/ConfigRunner.cs

@@ -107,7 +107,10 @@ public virtual void Finish()
             if (Exe == null || Exe.EndsWith("maml", StringComparison.OrdinalIgnoreCase) ||
                 Exe.EndsWith("maml.exe", StringComparison.OrdinalIgnoreCase))
             {
+                string currentDirectory = Path.GetDirectoryName(typeof(ExeConfigRunnerBase).Module.FullyQualifiedName);
+
                 using (var ch = Host.Start("Finish"))
+                using (AssemblyLoadingUtils.CreateAssemblyRegistrar(Host, currentDirectory))
                 {
                     var runs = RunNums.ToArray();
                     var args = Utils.BuildArray(RunNums.Count + 2,
@@ -120,7 +123,7 @@ public virtual void Finish()
                             return string.Format("{{{0}}}", GetFilePath(runs[i], "out"));
                         });
 
-                    ResultProcessorInternal.ResultProcessor.Main (args);
+                    ResultProcessorInternal.ResultProcessor.Main(args);
 
                     ch.Info(@"The summary of the run results has been saved to the file {0}\{1}.summary.txt", OutputFolder, Prefix);
                 }

src/Microsoft.ML.Sweeper/Microsoft.ML.Sweeper.csproj

@@ -16,4 +16,8 @@
 
   </ItemGroup>
 
+  <ItemGroup>
+    <Compile Include="..\Common\AssemblyLoadingUtils.cs" Link="Common\AssemblyLoadingUtils.cs" />
+  </ItemGroup>
+
 </Project>

src/Microsoft.ML.Transforms/CategoricalTransform.cs

@@ -135,18 +135,20 @@ public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataV
                     column.MaxNumTerms ?? args.MaxNumTerms,
                     column.Sort ?? args.Sort,
                     column.Term ?? args.Term);
-                col.SetTerms(column.Terms);
+                col.SetTerms(column.Terms ?? args.Terms);
                 columns.Add(col);
             }
-            return new CategoricalEstimator(env, columns.ToArray()).Fit(input).Transform(input) as IDataTransform;
+            return new CategoricalEstimator(env, columns.ToArray(), args.DataFile, args.TermsColumn, args.Loader).Fit(input).Transform(input) as IDataTransform;
         }
 
         private readonly TransformerChain<ITransformer> _transformer;
 
         public CategoricalTransform(TermEstimator term, IEstimator<ITransformer> toVector, IDataView input)
         {
-            var chain = term.Append(toVector);
-            _transformer = chain.Fit(input);
+            if (toVector != null)
+                _transformer = term.Append(toVector).Fit(input);
+            else
+                _transformer = new TransformerChain<ITransformer>(term.Fit(input));
         }
 
         public Schema GetOutputSchema(Schema inputSchema) => _transformer.GetOutputSchema(inputSchema);
@@ -198,15 +200,17 @@ internal void SetTerms(string terms)
         /// <param name="outputKind">The type of output expected.</param>
         public CategoricalEstimator(IHostEnvironment env, string input,
             string output = null, CategoricalTransform.OutputKind outputKind = Defaults.OutKind)
-            : this(env, new ColumnInfo(input, output ?? input, outputKind))
+            : this(env, new[] { new ColumnInfo(input, output ?? input, outputKind) })
         {
         }
 
-        public CategoricalEstimator(IHostEnvironment env, params ColumnInfo[] columns)
+        public CategoricalEstimator(IHostEnvironment env, ColumnInfo[] columns,
+            string file = null, string termsColumn = null,
+            IComponentFactory<IMultiStreamSource, IDataLoader> loaderFactory = null)
         {
             Contracts.CheckValue(env, nameof(env));
             _host = env.Register(nameof(TermEstimator));
-            _term = new TermEstimator(_host, columns);
+            _term = new TermEstimator(_host, columns, file, termsColumn, loaderFactory);
             var binaryCols = new List<(string input, string output)>();
             var cols = new List<(string input, string output, bool bag)>();
             for (int i = 0; i < columns.Length; i++)

test/BaselineOutput/Common/Command/CommandTrainMlrWithStats-1-out.txt

@@ -0,0 +1 @@
+Saving predictor summary

test/BaselineOutput/Common/Command/CommandTrainMlrWithStats-out.txt

@@ -0,0 +1,15 @@
+maml.exe Train tr=MultiClassLogisticRegression{maxiter=100 t=- stat=+} loader=TextLoader{col=Label:TX:4 col=Features:R4:0-3 sep=,} data=%Data% out=%Output% seed=1 xf=Term{col=Label}
+Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.
+Beginning optimization
+num vars: 15
+improvement criterion: Mean Improvement
+L1 regularization selected 11 of 15 weights.
+Model trained with 150 training examples.
+Residual Deviance: 	132.0122
+Null Deviance:    	329.5837
+AIC:              	154.0122
+Not training a calibrator because it is not needed.
+Physical memory usage(MB): %Number%
+Virtual memory usage(MB): %Number%
+%DateTime%	 Time elapsed(s): %Number%
+

test/BaselineOutput/Common/Command/CommandTrainMlrWithStats-summary.txt

@@ -0,0 +1,18 @@
+MulticlassLogisticRegression bias and non-zero weights
+	Iris-setosa+(Bias)	2.265129
+	Iris-versicolor+(Bias)	0.7695086
+	Iris-virginica+(Bias)	-3.034663
+	Iris-setosa+f3	-3.180634
+	Iris-setosa+f2	-2.88663
+	Iris-setosa+f1	0.5392878
+	Iris-setosa+f0	-0.03958065
+	Iris-versicolor+f1	-0.7073272
+	Iris-virginica+f3	3.158146
+	Iris-virginica+f2	1.907791
+	Iris-virginica+f0	0.01793481
+
+*** MODEL STATISTICS SUMMARY ***   
+Count of training examples:	150
+Residual Deviance:         	132.0122
+Null Deviance:             	329.5837
+AIC:                       	154.0122

test/BaselineOutput/Common/Command/CommandTrainingLrWithStats-1-out.txt

@@ -0,0 +1 @@
+Saving predictor summary

test/BaselineOutput/Common/Command/CommandTrainingLrWithStats-out.txt

@@ -0,0 +1,15 @@
+maml.exe Train feat=Num lab=Lab tr=lr{t=- stat=+} loader=text{header+ sep=comma col=Lab:14 col=Num:0,2,4,10-12} data=%Data% out=%Output%
+Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.
+Beginning optimization
+num vars: 7
+improvement criterion: Mean Improvement
+L1 regularization selected 7 of 7 weights.
+Model trained with 32561 training examples.
+Residual Deviance: 	26705.74 (on 32554 degrees of freedom)
+Null Deviance:     	35948.08 (on 32560 degrees of freedom)
+AIC:               	26719.74
+Not training a calibrator because it is not needed.
+Physical memory usage(MB): %Number%
+Virtual memory usage(MB): %Number%
+%DateTime%	 Time elapsed(s): %Number%
+

test/BaselineOutput/Common/Command/CommandTrainingLrWithStats-summary.txt

@@ -0,0 +1,15 @@
+Linear Binary Classification Predictor non-zero weights
+
+(Bias)	-8.228298
+capital-gain	18.58347
+education-num	5.066041
+hours-per-week	3.946534
+age	3.86064
+capital-loss	2.81616
+fnlwgt	0.7489593
+
+*** MODEL STATISTICS SUMMARY ***   
+Count of training examples:	32561
+Residual Deviance:         	26705.74
+Null Deviance:             	35948.08
+AIC:                       	26719.74

test/BaselineOutput/Common/EntryPoints/ensemble-model0-stats.txt

@@ -0,0 +1,10 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col={name={Count of training examples} type=I8 src=0}
+#@   col={name={Residual Deviance} type=R4 src=1}
+#@   col={name={Null Deviance} type=R4 src=2}
+#@   col=AIC:R4:3
+#@ }
+Count of training examples	Residual Deviance	Null Deviance	AIC
+521	98.29433	669.0935	118.294327

test/BaselineOutput/Common/EntryPoints/ensemble-model0-summary.txt

@@ -0,0 +1,8 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col=Bias:R4:0
+#@   col=Weights:R4:1-17
+#@ }
+Bias	Features.thickness	Features.uniform_size	Features.uniform_shape	Features.adhesion	Features.epit_size	Features.bare_nuclei	Features.bland_chromatin	Features.normal_nucleoli	Cat.1	Cat.5	Cat.4	Cat.3	Cat.2	Cat.7	Cat.10	Cat.8	Cat.6
+-5.120674	2.353567	1.78653753	1.9442488	1.38072	1.0831089	2.43588924	1.61141682	1.34575915	-0.7715381	0	0	0	0	0	0	0	0

test/BaselineOutput/Common/EntryPoints/ensemble-model1-summary.txt

@@ -0,0 +1,7 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col=Gains:R4:0-16
+#@ }
+Cat.1	Cat.4	Cat.2	Cat.5	Cat.10	Cat.3	Cat.7	Cat.8	Cat.6	Features.thickness	Features.uniform_size	Features.uniform_shape	Features.adhesion	Features.epit_size	Features.bare_nuclei	Features.bland_chromatin	Features.normal_nucleoli
+0.0607880056	0	0.0249023773	0	0	4.10026857E-09	0	0	0	0.190965369	1	0.7112387	0.14315024	0.222178861	0.413435966	0.254190356	0.2604484

test/BaselineOutput/Common/EntryPoints/ensemble-model2-stats.txt

@@ -0,0 +1,10 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col={name={Count of training examples} type=I8 src=0}
+#@   col={name={Residual Deviance} type=R4 src=1}
+#@   col={name={Null Deviance} type=R4 src=2}
+#@   col=AIC:R4:3
+#@ }
+Count of training examples	Residual Deviance	Null Deviance	AIC
+520	94.1969452	673.3445	114.196945

test/BaselineOutput/Common/EntryPoints/ensemble-model2-summary.txt

@@ -0,0 +1,8 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col=Bias:R4:0
+#@   col=Weights:R4:1-17
+#@ }
+Bias	Features.thickness	Features.uniform_size	Features.uniform_shape	Features.adhesion	Features.epit_size	Features.bare_nuclei	Features.bland_chromatin	Features.normal_nucleoli	Cat.1	Cat.5	Cat.4	Cat.2	Cat.3	Cat.7	Cat.10	Cat.8	Cat.6
+-4.860323	2.143086	1.49418533	1.71121442	1.38318741	0.883200347	3.16845965	1.38684654	1.51904845	-0.8226236	0	0	0	0	0	0	0	0

test/BaselineOutput/Common/EntryPoints/ensemble-model3-summary.txt

@@ -0,0 +1,7 @@
+#@ TextLoader{
+#@   header+
+#@   sep=tab
+#@   col=Gains:R4:0-16
+#@ }
+Cat.1	Cat.5	Cat.2	Cat.4	Cat.3	Cat.7	Cat.10	Cat.8	Cat.6	Features.thickness	Features.uniform_size	Features.uniform_shape	Features.adhesion	Features.epit_size	Features.bare_nuclei	Features.bland_chromatin	Features.normal_nucleoli
+0.009761757	0	0.0203766879	0	0.000928933	0	0	0	0	0.308038682	1	0.5590685	0.125412315	0.118880585	0.488731444	0.308761537	0.132577017

test/BaselineOutput/Common/EntryPoints/ensemble-summary-key-value-pairs.txt

@@ -0,0 +1,58 @@
+Partition model 0 summary:
+Linear Binary Classification Predictor non-zero weights
+(Bias): -5.120674
+Features.bare_nuclei: 2.435889
+Features.thickness: 2.353567
+Features.uniform_shape: 1.944249
+Features.uniform_size: 1.786538
+Features.bland_chromatin: 1.611417
+Features.adhesion: 1.38072
+Features.normal_nucleoli: 1.345759
+Features.epit_size: 1.083109
+Cat.1: -0.7715381
+Count of training examples: 521
+Residual Deviance: 98.29433
+Null Deviance: 669.0935
+AIC: 118.2943
+Partition model 1 summary:
+Per-feature gain summary for the boosted tree ensemble:
+Features.uniform_size: 1
+Features.uniform_shape: 0.711238682354263
+Features.bare_nuclei: 0.413435971399054
+Features.normal_nucleoli: 0.260448393604327
+Features.bland_chromatin: 0.254190368593018
+Features.epit_size: 0.222178863469679
+Features.thickness: 0.190965373645692
+Features.adhesion: 0.143150245168852
+Cat.1: 0.0607880054395048
+Cat.2: 0.0249023775790133
+Cat.3: 4.10026871732935E-09
+Partition model 2 summary:
+Linear Binary Classification Predictor non-zero weights
+(Bias): -4.860323
+Features.bare_nuclei: 3.16846
+Features.thickness: 2.143086
+Features.uniform_shape: 1.711214
+Features.normal_nucleoli: 1.519048
+Features.uniform_size: 1.494185
+Features.bland_chromatin: 1.386847
+Features.adhesion: 1.383187
+Features.epit_size: 0.8832003
+Cat.1: -0.8226236
+Count of training examples: 520
+Residual Deviance: 94.19695
+Null Deviance: 673.3445
+AIC: 114.1969
+Partition model 3 summary:
+Per-feature gain summary for the boosted tree ensemble:
+Features.uniform_size: 1
+Features.uniform_shape: 0.559068504082849
+Features.bare_nuclei: 0.488731457203164
+Features.bland_chromatin: 0.308761540884501
+Features.thickness: 0.308038677882308
+Features.normal_nucleoli: 0.132577017456797
+Features.adhesion: 0.125412316945858
+Features.epit_size: 0.118880587537871
+Cat.2: 0.0203766881332348
+Cat.1: 0.00976175711400017
+Cat.3: 0.000928932959407758