public void TestCrossValidationMacroWithNonDefaultNames()
{
string dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
using (var env = new TlcEnvironment(42))
{
var subGraph = env.CreateExperiment();
var textToKey = new Legacy.Transforms.TextToKeyConverter();
textToKey.Column = new[] { new Legacy.Transforms.TermTransformColumn()
{
Name = "Label1", Source = "Label"
} };
var textToKeyOutput = subGraph.Add(textToKey);
var hash = new Legacy.Transforms.HashConverter();
hash.Column = new[] { new Legacy.Transforms.HashJoinTransformColumn()
{
Name = "GroupId1", Source = "Workclass"
} };
hash.Data = textToKeyOutput.OutputData;
var hashOutput = subGraph.Add(hash);
var learnerInput = new Legacy.Trainers.FastTreeRanker
{
TrainingData = hashOutput.OutputData,
NumThreads = 1,
LabelColumn = "Label1",
GroupIdColumn = "GroupId1"
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(textToKeyOutput.Model, hashOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
importInput.Arguments.HasHeader = true;
importInput.Arguments.Column = new TextLoaderColumn[]
{
new TextLoaderColumn {
Name = "Label", Source = new[] { new TextLoaderRange(0) }
},
new TextLoaderColumn {
Name = "Workclass", Source = new[] { new TextLoaderRange(1) }, Type = Legacy.Data.DataKind.Text
},
new TextLoaderColumn {
Name = "Features", Source = new[] { new TextLoaderRange(9, 14) }
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
TransformModel = null,
LabelColumn = "Label1",
GroupColumn = "GroupId1",
NameColumn = "Workclass",
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureRankerTrainer
};
crossValidate.Inputs.Data = textToKey.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("NDCG", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <VBuffer <double> >(metricCol);
var foldGetter = cursor.GetGetter <DvText>(foldCol);
DvText fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
var avg = default(VBuffer <double>);
getter(ref avg);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Average"));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
var stdev = default(VBuffer <double>);
getter(ref stdev);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Standard Deviation"));
Assert.Equal(2.462, stdev.Values[0], 3);
Assert.Equal(2.763, stdev.Values[1], 3);
Assert.Equal(3.273, stdev.Values[2], 3);
var sumBldr = new BufferBuilder <double>(R8Adder.Instance);
sumBldr.Reset(avg.Length, true);
var val = default(VBuffer <double>);
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sumBldr.AddFeatures(0, ref val);
Assert.True(fold.EqualsStr("Fold " + f));
}
var sum = default(VBuffer <double>);
sumBldr.GetResult(ref sum);
for (int i = 0; i < avg.Length; i++)
{
Assert.Equal(avg.Values[i], sum.Values[i] / 2);
}
b = cursor.MoveNext();
Assert.False(b);
}
data = experiment.GetOutput(crossValidateOutput.PerInstanceMetrics);
Assert.True(data.Schema.TryGetColumnIndex("Instance", out int nameCol));
using (var cursor = data.GetRowCursor(col => col == nameCol))
{
var getter = cursor.GetGetter <DvText>(nameCol);
while (cursor.MoveNext())
{
DvText name = default;
getter(ref name);
Assert.Subset(new HashSet <DvText>()
{
new DvText("Private"), new DvText("?"), new DvText("Federal-gov")
}, new HashSet <DvText>()
{
name
});
if (cursor.Position > 4)
{
break;
}
}
}
}
}
public void TestCrossValidationMacroWithStratification()
{
var dataPath = GetDataPath(@"breast-cancer.txt");
using (var env = new TlcEnvironment(42))
{
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new Legacy.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
importInput.Arguments.Column = new Legacy.Data.TextLoaderColumn[]
{
new Legacy.Data.TextLoaderColumn {
Name = "Label", Source = new[] { new Legacy.Data.TextLoaderRange(0) }
},
new Legacy.Data.TextLoaderColumn {
Name = "Strat", Source = new[] { new Legacy.Data.TextLoaderRange(1) }
},
new Legacy.Data.TextLoaderColumn {
Name = "Features", Source = new[] { new Legacy.Data.TextLoaderRange(2, 9) }
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
TransformModel = null,
StratificationColumn = "Strat"
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <DvText>(foldCol);
DvText fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
double avg = 0;
getter(ref avg);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Average"));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Standard Deviation"));
Assert.Equal(0.00485, stdev, 5);
double sum = 0;
double val = 0;
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sum += val;
Assert.True(fold.EqualsStr("Fold " + f));
}
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
public void TestCrossValidationMacroWithMultiClass()
{
var dataPath = GetDataPath(@"Train-Tiny-28x28.txt");
using (var env = new TlcEnvironment(42))
{
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new Legacy.Trainers.StochasticDualCoordinateAscentClassifier
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureMultiClassClassifierTrainer,
TransformModel = null
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("Accuracy(micro-avg)", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <DvText>(foldCol);
DvText fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
double avg = 0;
getter(ref avg);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Average"));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Standard Deviation"));
Assert.Equal(0.025, stdev, 3);
double sum = 0;
double val = 0;
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sum += val;
Assert.True(fold.EqualsStr("Fold " + f));
}
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
var confusion = experiment.GetOutput(crossValidateOutput.ConfusionMatrix);
schema = confusion.Schema;
b = schema.TryGetColumnIndex("Count", out int countCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out foldCol);
Assert.True(b);
var type = schema.GetMetadataTypeOrNull(MetadataUtils.Kinds.SlotNames, countCol);
Assert.True(type != null && type.ItemType.IsText && type.VectorSize == 10);
var slotNames = default(VBuffer <DvText>);
schema.GetMetadata(MetadataUtils.Kinds.SlotNames, countCol, ref slotNames);
Assert.True(slotNames.Values.Select((s, i) => s.EqualsStr(i.ToString())).All(x => x));
using (var curs = confusion.GetRowCursor(col => true))
{
var countGetter = curs.GetGetter <VBuffer <double> >(countCol);
var foldGetter = curs.GetGetter <DvText>(foldCol);
var confCount = default(VBuffer <double>);
var foldIndex = default(DvText);
int rowCount = 0;
var foldCur = "Fold 0";
while (curs.MoveNext())
{
countGetter(ref confCount);
foldGetter(ref foldIndex);
rowCount++;
Assert.True(foldIndex.EqualsStr(foldCur));
if (rowCount == 10)
{
rowCount = 0;
foldCur = "Fold 1";
}
}
Assert.Equal(0, rowCount);
}
var warnings = experiment.GetOutput(crossValidateOutput.Warnings);
using (var cursor = warnings.GetRowCursor(col => true))
Assert.False(cursor.MoveNext());
}
}
public void TestCrossValidationMacro()
{
var dataPath = GetDataPath(TestDatasets.winequalitymacro.trainFilename);
using (var env = new TlcEnvironment(42))
{
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var generate = new Legacy.Transforms.RandomNumberGenerator();
generate.Column = new[] { new Legacy.Transforms.GenerateNumberTransformColumn()
{
Name = "Weight1"
} };
generate.Data = nopOutput.OutputData;
var generateOutput = subGraph.Add(generate);
var learnerInput = new Legacy.Trainers.PoissonRegressor
{
TrainingData = generateOutput.OutputData,
NumThreads = 1,
WeightColumn = "Weight1"
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model, generateOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath)
{
Arguments = new Legacy.Data.TextLoaderArguments
{
Separator = new[] { ';' },
HasHeader = true,
Column = new[]
{
new TextLoaderColumn()
{
Name = "Label",
Source = new [] { new TextLoaderRange(11) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Features",
Source = new [] { new TextLoaderRange(0, 10) },
Type = Legacy.Data.DataKind.Num
}
}
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureRegressorTrainer,
TransformModel = null,
WeightColumn = "Weight1"
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("L1(avg)", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
b = schema.TryGetColumnIndex("IsWeighted", out int isWeightedCol);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol || col == isWeightedCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <DvText>(foldCol);
var isWeightedGetter = cursor.GetGetter <DvBool>(isWeightedCol);
DvText fold = default;
DvBool isWeighted = default;
double avg = 0;
double weightedAvg = 0;
for (int w = 0; w < 2; w++)
{
// Get the average.
b = cursor.MoveNext();
Assert.True(b);
if (w == 1)
{
getter(ref weightedAvg);
}
else
{
getter(ref avg);
}
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Average"));
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted.IsTrue == (w == 1));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Standard Deviation"));
if (w == 1)
{
Assert.Equal(0.004557, stdev, 6);
}
else
{
Assert.Equal(0.000393, stdev, 6);
}
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted.IsTrue == (w == 1));
}
double sum = 0;
double weightedSum = 0;
for (int f = 0; f < 2; f++)
{
for (int w = 0; w < 2; w++)
{
b = cursor.MoveNext();
Assert.True(b);
double val = 0;
getter(ref val);
foldGetter(ref fold);
if (w == 1)
{
weightedSum += val;
}
else
{
sum += val;
}
Assert.True(fold.EqualsStr("Fold " + f));
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted.IsTrue == (w == 1));
}
}
Assert.Equal(weightedAvg, weightedSum / 2);
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
public void TestCrossValidationMacro()
{
var dataPath = GetDataPath(TestDatasets.winequality.trainFilename);
using (var env = new TlcEnvironment(42))
{
var subGraph = env.CreateExperiment();
var nop = new ML.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new ML.Trainers.StochasticDualCoordinateAscentRegressor
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new ML.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath)
{
Arguments = new TextLoaderArguments
{
Separator = new[] { ';' },
HasHeader = true,
Column = new[]
{
new TextLoaderColumn()
{
Name = "Label",
Source = new [] { new TextLoaderRange(11) },
Type = DataKind.Num
},
new TextLoaderColumn()
{
Name = "Features",
Source = new [] { new TextLoaderRange(0, 10) },
Type = DataKind.Num
}
}
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new ML.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = ML.Models.MacroUtilsTrainerKinds.SignatureRegressorTrainer,
TransformModel = null
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("L1(avg)", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <DvText>(foldCol);
DvText fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
double avg = 0;
getter(ref avg);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Average"));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(fold.EqualsStr("Standard Deviation"));
Assert.Equal(0.0013, stdev, 4);
double sum = 0;
double val = 0;
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sum += val;
Assert.True(fold.EqualsStr("Fold " + f));
}
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
public static CommonOutputs.TransformOutput RenameBinaryPredictionScoreColumns(IHostEnvironment env,
RenameBinaryPredictionScoreColumnsInput input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("ScoreModel");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
if (input.PredictorModel.Predictor.PredictionKind == PredictionKind.BinaryClassification)
{
ColumnType labelType;
var labelNames = input.PredictorModel.GetLabelInfo(host, out labelType);
if (labelNames != null && labelNames.Length == 2)
{
var positiveClass = labelNames[1];
// Rename all the score columns.
int colMax;
var maxScoreId = input.Data.Schema.GetMaxMetadataKind(out colMax, MetadataUtils.Kinds.ScoreColumnSetId);
var copyCols = new List <CopyColumnsTransform.Column>();
for (int i = 0; i < input.Data.Schema.ColumnCount; i++)
{
if (input.Data.Schema.IsHidden(i))
{
continue;
}
if (!ShouldAddColumn(input.Data.Schema, i, null, maxScoreId))
{
continue;
}
// Do not rename the PredictedLabel column.
DvText tmp = default(DvText);
if (input.Data.Schema.TryGetMetadata(TextType.Instance, MetadataUtils.Kinds.ScoreValueKind, i,
ref tmp) &&
tmp.EqualsStr(MetadataUtils.Const.ScoreValueKind.PredictedLabel))
{
continue;
}
var source = input.Data.Schema.GetColumnName(i);
var name = source + "." + positiveClass;
copyCols.Add(new CopyColumnsTransform.Column()
{
Name = name, Source = source
});
}
var copyColumn = new CopyColumnsTransform(env, new CopyColumnsTransform.Arguments()
{
Column = copyCols.ToArray()
}, input.Data);
var dropColumn = new DropColumnsTransform(env, new DropColumnsTransform.Arguments()
{
Column = copyCols.Select(c => c.Source).ToArray()
}, copyColumn);
return(new CommonOutputs.TransformOutput {
Model = new TransformModel(env, dropColumn, input.Data), OutputData = dropColumn
});
}
}
var newView = NopTransform.CreateIfNeeded(env, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModel(env, newView, input.Data), OutputData = newView
});
}