public static CommonOutputs.MacroOutput <Output> CrossValidate(
IHostEnvironment env,
Arguments input,
EntryPointNode node)
{
env.CheckValue(input, nameof(input));
// This will be the final resulting list of nodes that is returned from the macro.
var subGraphNodes = new List <EntryPointNode>();
//the input transform model
VariableBinding transformModelVarName = null;
if (input.TransformModel != null)
{
transformModelVarName = node.GetInputVariable(nameof(input.TransformModel));
}
// Split the input data into folds.
var exp = new Experiment(env);
var cvSplit = new Models.CrossValidatorDatasetSplitter();
cvSplit.Data.VarName = node.GetInputVariable("Data").ToJson();
cvSplit.NumFolds = input.NumFolds;
cvSplit.StratificationColumn = input.StratificationColumn;
var cvSplitOutput = exp.Add(cvSplit);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
var predModelVars = new Var <IPredictorModel> [input.NumFolds];
var transformModelVars = new Var <ITransformModel> [input.NumFolds];
var inputTransformModelVars = new Var <IPredictorModel> [input.NumFolds];
var warningsVars = new Var <IDataView> [input.NumFolds];
var overallMetricsVars = new Var <IDataView> [input.NumFolds];
var instanceMetricsVars = new Var <IDataView> [input.NumFolds];
var confusionMatrixVars = new Var <IDataView> [input.NumFolds];
// Instantiate the subgraph for each fold.
for (int k = 0; k < input.NumFolds; k++)
{
// Parse the nodes in input.Nodes into a temporary run context.
var context = new RunContext(env);
var graph = EntryPointNode.ValidateNodes(env, context, input.Nodes, node.Catalog);
// Rename all the variables such that they don't conflict with the ones in the outer run context.
var mapping = new Dictionary <string, string>();
foreach (var entryPointNode in graph)
{
entryPointNode.RenameAllVariables(mapping);
}
// Instantiate a TrainTest entry point for this fold.
var args = new TrainTestMacro.Arguments
{
Nodes = new JArray(graph.Select(n => n.ToJson()).ToArray()),
TransformModel = null,
LabelColumn = input.LabelColumn,
GroupColumn = input.GroupColumn,
WeightColumn = input.WeightColumn,
NameColumn = input.NameColumn
};
if (transformModelVarName != null)
{
args.TransformModel = new Var <ITransformModel> {
VarName = transformModelVarName.VariableName
}
}
;
args.Inputs.Data = new Var <IDataView>
{
VarName = mapping[input.Inputs.Data.VarName]
};
if (input.Outputs.PredictorModel != null && mapping.ContainsKey(input.Outputs.PredictorModel.VarName))
{
args.Outputs.PredictorModel = new Var <IPredictorModel>
{
VarName = mapping[input.Outputs.PredictorModel.VarName]
};
}
else
{
args.Outputs.PredictorModel = null;
}
if (input.Outputs.TransformModel != null && mapping.ContainsKey(input.Outputs.TransformModel.VarName))
{
args.Outputs.TransformModel = new Var <ITransformModel>
{
VarName = mapping[input.Outputs.TransformModel.VarName]
};
}
else
{
args.Outputs.TransformModel = null;
}
// Set train/test trainer kind to match.
args.Kind = input.Kind;
// Set the input bindings for the TrainTest entry point.
var inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var trainingData = new SimpleParameterBinding(nameof(args.TrainingData));
inputBindingMap.Add(nameof(args.TrainingData), new List <ParameterBinding> {
trainingData
});
inputMap.Add(trainingData, new ArrayIndexVariableBinding(cvSplitOutput.TrainData.VarName, k));
var testingData = new SimpleParameterBinding(nameof(args.TestingData));
inputBindingMap.Add(nameof(args.TestingData), new List <ParameterBinding> {
testingData
});
inputMap.Add(testingData, new ArrayIndexVariableBinding(cvSplitOutput.TestData.VarName, k));
var outputMap = new Dictionary <string, string>();
var transformModelVar = new Var <ITransformModel>();
var predModelVar = new Var <IPredictorModel>();
if (input.Outputs.PredictorModel == null)
{
outputMap.Add(nameof(TrainTestMacro.Output.TransformModel), transformModelVar.VarName);
transformModelVars[k] = transformModelVar;
ML.Transforms.ModelCombiner.Output modelCombineOutput = null;
if (transformModelVarName != null && transformModelVarName.VariableName != null)
{
var modelCombine = new ML.Transforms.ModelCombiner
{
Models = new ArrayVar <ITransformModel>(
new Var <ITransformModel>[] {
new Var <ITransformModel> {
VarName = transformModelVarName.VariableName
},
transformModelVar
}
)
};
exp.Reset();
modelCombineOutput = exp.Add(modelCombine);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
transformModelVars[k] = modelCombineOutput.OutputModel;
}
}
else
{
outputMap.Add(nameof(TrainTestMacro.Output.PredictorModel), predModelVar.VarName);
predModelVars[k] = predModelVar;
ML.Transforms.TwoHeterogeneousModelCombiner.Output modelCombineOutput = null;
if (transformModelVarName != null && transformModelVarName.VariableName != null)
{
var modelCombine = new ML.Transforms.TwoHeterogeneousModelCombiner
{
TransformModel = { VarName = transformModelVarName.VariableName },
PredictorModel = predModelVar
};
exp.Reset();
modelCombineOutput = exp.Add(modelCombine);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
predModelVars[k] = modelCombineOutput.PredictorModel;
}
}
var warningVar = new Var <IDataView>();
outputMap.Add(nameof(TrainTestMacro.Output.Warnings), warningVar.VarName);
warningsVars[k] = warningVar;
var overallMetric = new Var <IDataView>();
outputMap.Add(nameof(TrainTestMacro.Output.OverallMetrics), overallMetric.VarName);
overallMetricsVars[k] = overallMetric;
var instanceMetric = new Var <IDataView>();
outputMap.Add(nameof(TrainTestMacro.Output.PerInstanceMetrics), instanceMetric.VarName);
instanceMetricsVars[k] = instanceMetric;
var confusionMatrix = new Var <IDataView>();
outputMap.Add(nameof(TrainTestMacro.Output.ConfusionMatrix), confusionMatrix.VarName);
confusionMatrixVars[k] = confusionMatrix;
const string trainTestEvaluatorMacroEntryPoint = "Models.TrainTestEvaluator";
subGraphNodes.Add(EntryPointNode.Create(env, trainTestEvaluatorMacroEntryPoint, args, node.Catalog, node.Context, inputBindingMap, inputMap, outputMap));
}
exp.Reset();
// Convert predictors from all folds into an array of predictors.
if (input.Outputs.PredictorModel == null)
{
var outModels = new ML.Data.TransformModelArrayConverter
{
TransformModel = new ArrayVar <ITransformModel>(transformModelVars)
};
var outModelsOutput = new ML.Data.TransformModelArrayConverter.Output();
outModelsOutput.OutputModel.VarName = node.GetOutputVariableName(nameof(Output.TransformModel));
exp.Add(outModels, outModelsOutput);
}
else
{
var outModels = new ML.Data.PredictorModelArrayConverter
{
Model = new ArrayVar <IPredictorModel>(predModelVars)
};
var outModelsOutput = new ML.Data.PredictorModelArrayConverter.Output();
outModelsOutput.OutputModel.VarName = node.GetOutputVariableName(nameof(Output.PredictorModel));
exp.Add(outModels, outModelsOutput);
}
// Convert warnings data views from all folds into an array of data views.
var warnings = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(warningsVars)
};
var warningsOutput = new ML.Data.IDataViewArrayConverter.Output();
exp.Add(warnings, warningsOutput);
// Convert overall metrics data views from all folds into an array of data views.
var overallMetrics = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(overallMetricsVars)
};
var overallMetricsOutput = new ML.Data.IDataViewArrayConverter.Output();
exp.Add(overallMetrics, overallMetricsOutput);
// Convert per instance data views from all folds into an array of data views.
var instanceMetrics = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(instanceMetricsVars)
};
var instanceMetricsOutput = new ML.Data.IDataViewArrayConverter.Output();
exp.Add(instanceMetrics, instanceMetricsOutput);
ML.Data.IDataViewArrayConverter.Output confusionMatricesOutput = null;
if (input.Kind == MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer ||
input.Kind == MacroUtils.TrainerKinds.SignatureMultiClassClassifierTrainer)
{
// Convert confusion matrix data views from all folds into an array of data views.
var confusionMatrices = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(confusionMatrixVars)
};
confusionMatricesOutput = new ML.Data.IDataViewArrayConverter.Output();
exp.Add(confusionMatrices, confusionMatricesOutput);
}
var combineArgs = new CombineMetricsInput();
combineArgs.Kind = input.Kind;
combineArgs.LabelColumn = input.LabelColumn;
combineArgs.WeightColumn = input.WeightColumn;
combineArgs.GroupColumn = input.GroupColumn;
combineArgs.NameColumn = input.NameColumn;
// Set the input bindings for the CombineMetrics entry point.
var combineInputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var combineInputMap = new Dictionary <ParameterBinding, VariableBinding>();
var warningsArray = new SimpleParameterBinding(nameof(combineArgs.Warnings));
combineInputBindingMap.Add(nameof(combineArgs.Warnings), new List <ParameterBinding> {
warningsArray
});
combineInputMap.Add(warningsArray, new SimpleVariableBinding(warningsOutput.OutputData.VarName));
var overallArray = new SimpleParameterBinding(nameof(combineArgs.OverallMetrics));
combineInputBindingMap.Add(nameof(combineArgs.OverallMetrics), new List <ParameterBinding> {
overallArray
});
combineInputMap.Add(overallArray, new SimpleVariableBinding(overallMetricsOutput.OutputData.VarName));
var combinePerInstArray = new SimpleParameterBinding(nameof(combineArgs.PerInstanceMetrics));
combineInputBindingMap.Add(nameof(combineArgs.PerInstanceMetrics), new List <ParameterBinding> {
combinePerInstArray
});
combineInputMap.Add(combinePerInstArray, new SimpleVariableBinding(instanceMetricsOutput.OutputData.VarName));
if (confusionMatricesOutput != null)
{
var combineConfArray = new SimpleParameterBinding(nameof(combineArgs.ConfusionMatrix));
combineInputBindingMap.Add(nameof(combineArgs.ConfusionMatrix), new List <ParameterBinding> {
combineConfArray
});
combineInputMap.Add(combineConfArray, new SimpleVariableBinding(confusionMatricesOutput.OutputData.VarName));
}
var combineOutputMap = new Dictionary <string, string>();
var combineWarningVar = new Var <IDataView>();
combineWarningVar.VarName = node.GetOutputVariableName(nameof(Output.Warnings));
combineOutputMap.Add(nameof(Output.Warnings), combineWarningVar.VarName);
var combineOverallMetric = new Var <IDataView>();
combineOverallMetric.VarName = node.GetOutputVariableName(nameof(Output.OverallMetrics));
combineOutputMap.Add(nameof(Output.OverallMetrics), combineOverallMetric.VarName);
var combineInstanceMetric = new Var <IDataView>();
combineInstanceMetric.VarName = node.GetOutputVariableName(nameof(Output.PerInstanceMetrics));
combineOutputMap.Add(nameof(Output.PerInstanceMetrics), combineInstanceMetric.VarName);
if (confusionMatricesOutput != null)
{
var combineConfusionMatrix = new Var <IDataView>();
combineConfusionMatrix.VarName = node.GetOutputVariableName(nameof(Output.ConfusionMatrix));
combineOutputMap.Add(nameof(TrainTestMacro.Output.ConfusionMatrix), combineConfusionMatrix.VarName);
}
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
subGraphNodes.Add(EntryPointNode.Create(env, "Models.CrossValidationResultsCombiner", combineArgs, node.Catalog, node.Context, combineInputBindingMap, combineInputMap, combineOutputMap));
return(new CommonOutputs.MacroOutput <Output>()
{
Nodes = subGraphNodes
});
}
public static CommonOutputs.MacroOutput <Output> CrossValidateBinary(
IHostEnvironment env,
Arguments input,
EntryPointNode node)
{
// This will be the final resulting list of nodes that is returned from the macro.
var subGraphNodes = new List <EntryPointNode>();
// Split the input data into folds.
var exp = new Experiment(env);
var cvSplit = new ML.Models.CrossValidatorDatasetSplitter();
cvSplit.Data.VarName = node.GetInputVariable("Data").ToJson();
cvSplit.NumFolds = input.NumFolds;
cvSplit.StratificationColumn = input.StratificationColumn;
var cvSplitOutput = exp.Add(cvSplit);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
var predModelVars = new Var <IPredictorModel> [input.NumFolds];
var warningsVars = new Var <IDataView> [input.NumFolds];
var overallMetricsVars = new Var <IDataView> [input.NumFolds];
var instanceMetricsVars = new Var <IDataView> [input.NumFolds];
var confusionMatrixVars = new Var <IDataView> [input.NumFolds];
// Instantiate the subgraph for each fold.
for (int k = 0; k < input.NumFolds; k++)
{
// Parse the nodes in input.Nodes into a temporary run context.
var context = new RunContext(env);
var graph = EntryPointNode.ValidateNodes(env, context, input.Nodes, node.Catalog);
// Rename all the variables such that they don't conflict with the ones in the outer run context.
var mapping = new Dictionary <string, string>();
foreach (var entryPointNode in graph)
{
entryPointNode.RenameAllVariables(mapping);
}
// Instantiate a TrainTest entry point for this fold.
var args = new TrainTestBinaryMacro.Arguments
{
Nodes = new JArray(graph.Select(n => n.ToJson()).ToArray())
};
args.Inputs.Data = new Var <IDataView>
{
VarName = mapping[input.Inputs.Data.VarName]
};
args.Outputs.Model = new Var <IPredictorModel>
{
VarName = mapping[input.Outputs.Model.VarName]
};
// Set the input bindings for the TrainTest entry point.
var inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var trainingData = new SimpleParameterBinding(nameof(args.TrainingData));
inputBindingMap.Add(nameof(args.TrainingData), new List <ParameterBinding> {
trainingData
});
inputMap.Add(trainingData, new ArrayIndexVariableBinding(cvSplitOutput.TrainData.VarName, k));
var testingData = new SimpleParameterBinding(nameof(args.TestingData));
inputBindingMap.Add(nameof(args.TestingData), new List <ParameterBinding> {
testingData
});
inputMap.Add(testingData, new ArrayIndexVariableBinding(cvSplitOutput.TestData.VarName, k));
var outputMap = new Dictionary <string, string>();
var predModelVar = new Var <IPredictorModel>();
outputMap.Add(nameof(TrainTestBinaryMacro.Output.PredictorModel), predModelVar.VarName);
predModelVars[k] = predModelVar;
var warningVar = new Var <IDataView>();
outputMap.Add(nameof(TrainTestBinaryMacro.Output.Warnings), warningVar.VarName);
warningsVars[k] = warningVar;
var overallMetric = new Var <IDataView>();
outputMap.Add(nameof(TrainTestBinaryMacro.Output.OverallMetrics), overallMetric.VarName);
overallMetricsVars[k] = overallMetric;
var instanceMetric = new Var <IDataView>();
outputMap.Add(nameof(TrainTestBinaryMacro.Output.PerInstanceMetrics), instanceMetric.VarName);
instanceMetricsVars[k] = instanceMetric;
var confusionMatrix = new Var <IDataView>();
outputMap.Add(nameof(TrainTestBinaryMacro.Output.ConfusionMatrix), confusionMatrix.VarName);
confusionMatrixVars[k] = confusionMatrix;
subGraphNodes.Add(EntryPointNode.Create(env, "Models.TrainTestBinaryEvaluator", args, node.Catalog, node.Context, inputBindingMap, inputMap, outputMap));
}
exp.Reset();
var outModels = new ML.Data.PredictorModelArrayConverter
{
Model = new ArrayVar <IPredictorModel>(predModelVars)
};
var outModelsOutput = new ML.Data.PredictorModelArrayConverter.Output();
outModelsOutput.OutputModel.VarName = node.GetOutputVariableName(nameof(Output.PredictorModel));
exp.Add(outModels, outModelsOutput);
var warnings = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(warningsVars)
};
var warningsOutput = new ML.Data.IDataViewArrayConverter.Output();
warningsOutput.OutputData.VarName = node.GetOutputVariableName(nameof(Output.Warnings));
exp.Add(warnings, warningsOutput);
var overallMetrics = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(overallMetricsVars)
};
var overallMetricsOutput = new ML.Data.IDataViewArrayConverter.Output();
overallMetricsOutput.OutputData.VarName = node.GetOutputVariableName(nameof(Output.OverallMetrics));
exp.Add(overallMetrics, overallMetricsOutput);
var instanceMetrics = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(instanceMetricsVars)
};
var instanceMetricsOutput = new ML.Data.IDataViewArrayConverter.Output();
instanceMetricsOutput.OutputData.VarName = node.GetOutputVariableName(nameof(Output.PerInstanceMetrics));
exp.Add(instanceMetrics, instanceMetricsOutput);
var confusionMatrices = new ML.Data.IDataViewArrayConverter
{
Data = new ArrayVar <IDataView>(confusionMatrixVars)
};
var confusionMatricesOutput = new ML.Data.IDataViewArrayConverter.Output();
confusionMatricesOutput.OutputData.VarName = node.GetOutputVariableName(nameof(Output.ConfusionMatrix));
exp.Add(confusionMatrices, confusionMatricesOutput);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
return(new CommonOutputs.MacroOutput <Output>()
{
Nodes = subGraphNodes
});
}
private static Tuple <List <EntryPointNode>, Var <IPredictorModel> > ProcessClass(IHostEnvironment env, int k, string label, Arguments input, EntryPointNode node)
{
var macroNodes = new List <EntryPointNode>();
// Convert label into T,F based on k.
var remapper = new ML.Transforms.LabelIndicator
{
ClassIndex = k,
Column = new[]
{
new ML.Transforms.LabelIndicatorTransformColumn
{
ClassIndex = k,
Name = label,
Source = label
}
},
Data = { VarName = node.GetInputVariable(nameof(input.TrainingData)).ToJson() }
};
var exp = new Experiment(env);
var remapperOutNode = exp.Add(remapper);
var subNodes = EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog);
macroNodes.AddRange(subNodes);
// Parse the nodes in input.Nodes into a temporary run context.
var subGraphRunContext = new RunContext(env);
var subGraphNodes = EntryPointNode.ValidateNodes(env, subGraphRunContext, input.Nodes, node.Catalog);
// Rename all the variables such that they don't conflict with the ones in the outer run context.
var mapping = new Dictionary <string, string>();
bool foundOutput = false;
Var <IPredictorModel> predModelVar = null;
foreach (var entryPointNode in subGraphNodes)
{
// Rename variables in input/output maps, and in subgraph context.
entryPointNode.RenameAllVariables(mapping);
foreach (var kvp in mapping)
{
subGraphRunContext.RenameContextVariable(kvp.Key, kvp.Value);
}
// Grab a hold of output model from this subgraph.
if (entryPointNode.GetOutputVariableName("PredictorModel") is string mvn)
{
predModelVar = new Var <IPredictorModel> {
VarName = mvn
};
foundOutput = true;
}
// Connect label remapper output to wherever training data was expected within the input graph.
if (entryPointNode.GetInputVariable(nameof(input.TrainingData)) is VariableBinding vb)
{
vb.Rename(remapperOutNode.OutputData.VarName);
}
// Change node to use the main context.
entryPointNode.SetContext(node.Context);
}
// Move the variables from the subcontext to the main context.
node.Context.AddContextVariables(subGraphRunContext);
// Make sure we found the output variable for this model.
if (!foundOutput)
{
throw new Exception("Invalid input graph. Does not output predictor model.");
}
// Add training subgraph to our context.
macroNodes.AddRange(subGraphNodes);
return(new Tuple <List <EntryPointNode>, Var <IPredictorModel> >(macroNodes, predModelVar));
}
private static Var <PredictorModel> ProcessClass(IHostEnvironment env, List <EntryPointNode> macroNodes, int k, string label, Arguments input, EntryPointNode node)
{
Contracts.AssertValue(macroNodes);
// Convert label into T,F based on k.
var labelIndicatorArgs = new LabelIndicatorTransform.Arguments();
labelIndicatorArgs.ClassIndex = k;
labelIndicatorArgs.Column = new[] { new LabelIndicatorTransform.Column()
{
Name = label, Source = label
} };
var inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var paramBinding = new SimpleParameterBinding(nameof(labelIndicatorArgs.Data));
inputBindingMap.Add(nameof(labelIndicatorArgs.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, node.GetInputVariable(nameof(input.TrainingData)));
var outputMap = new Dictionary <string, string>();
var remappedLabelVar = new Var <IDataView>();
outputMap.Add(nameof(CommonOutputs.TransformOutput.OutputData), remappedLabelVar.VarName);
var labelIndicatorNode = EntryPointNode.Create(env, "Transforms.LabelIndicator", labelIndicatorArgs, node.Context,
inputBindingMap, inputMap, outputMap);
macroNodes.Add(labelIndicatorNode);
// Parse the nodes in input.Nodes into a temporary run context.
var subGraphRunContext = new RunContext(env);
var subGraphNodes = EntryPointNode.ValidateNodes(env, subGraphRunContext, input.Nodes);
// Rename all the variables such that they don't conflict with the ones in the outer run context.
var mapping = new Dictionary <string, string>();
bool foundOutput = false;
Var <PredictorModel> predModelVar = null;
foreach (var entryPointNode in subGraphNodes)
{
// Rename variables in input/output maps, and in subgraph context.
entryPointNode.RenameAllVariables(mapping);
foreach (var kvp in mapping)
{
subGraphRunContext.RenameContextVariable(kvp.Key, kvp.Value);
}
// Grab a hold of output model from this subgraph.
if (entryPointNode.GetOutputVariableName("PredictorModel") is string mvn)
{
predModelVar = new Var <PredictorModel> {
VarName = mvn
};
foundOutput = true;
}
// Connect label remapper output to wherever training data was expected within the input graph.
if (entryPointNode.GetInputVariable(nameof(input.TrainingData)) is VariableBinding vb)
{
vb.Rename(remappedLabelVar.VarName);
}
// Change node to use the main context.
entryPointNode.SetContext(node.Context);
}
// Move the variables from the subcontext to the main context.
node.Context.AddContextVariables(subGraphRunContext);
// Make sure we found the output variable for this model.
if (!foundOutput)
{
throw new Exception("Invalid input graph. Does not output predictor model.");
}
// Add training subgraph to our context.
macroNodes.AddRange(subGraphNodes);
return(predModelVar);
}