/// <summary>
/// Checks the given JSON object key-value pair is a valid EntryPoint output.
/// Extracts out any variables that need to be populated and adds them to the
/// EntryPoint context.
/// </summary>
private void CheckAndMarkOutputValue(KeyValuePair <string, JToken> pair)
{
if (!VariableBinding.IsBindingToken(pair.Value))
{
throw _host.Except("Only variables allowed as outputs");
}
// Output variable.
var varBinding = VariableBinding.Create(_host, pair.Value.Value <string>());
if (!(varBinding is SimpleVariableBinding))
{
throw _host.Except($"Output '{pair.Key}' can only be bound to a variable");
}
var valueType = _outputHelper.GetFieldType(pair.Key);
if (valueType == null)
{
throw _host.Except($"Unexpected output name: '{pair.Key}");
}
if (!EntryPointVariable.IsValidType(valueType))
{
throw _host.Except($"Output '{pair.Key}' has invalid type");
}
_context.AddOutputVariable(varBinding.VariableName, valueType);
_outputMap[pair.Key] = varBinding.VariableName;
}
public void AddInputVariable(VariableBinding binding, Type type)
{
_ectx.AssertValue(binding);
_ectx.AssertValue(type);
if (binding is ArrayIndexVariableBinding)
{
type = Utils.MarshalInvoke(MakeArray <int>, type);
}
else if (binding is DictionaryKeyVariableBinding)
{
type = Utils.MarshalInvoke(MakeDictionary <int>, type);
}
EntryPointVariable v;
if (!_vars.TryGetValue(binding.VariableName, out v))
{
v = new EntryPointVariable(_ectx, binding.VariableName, type);
_vars[binding.VariableName] = v;
}
else if (v.Type != type)
{
throw _ectx.Except($"Variable '{v.Name}' is used as {v.Type} and as {type}");
}
v.MarkUsage(true);
}
public object GetValueOrNull(VariableBinding binding)
{
_ectx.AssertValue(binding);
EntryPointVariable v;
if (!TryGetVariable(binding.VariableName, out v))
{
return(null);
}
return(binding.GetVariableValueOrNull(v));
}
public void RenameInputVariable(string oldName, VariableBinding newBinding)
{
var toModify = new List <ParameterBinding>();
foreach (var kvp in _inputMap)
{
if (kvp.Value.VariableName == oldName)
{
toModify.Add(kvp.Key);
}
}
foreach (var parameterBinding in toModify)
{
_inputMap[parameterBinding] = newBinding;
}
}
public static CommonOutputs.MacroOutput <Output> TrainTest(
IHostEnvironment env,
Arguments input,
EntryPointNode node)
{
// Create default pipeline ID if one not given.
input.PipelineId = input.PipelineId ?? Guid.NewGuid().ToString("N");
// Parse the subgraph.
var subGraphRunContext = new RunContext(env);
var subGraphNodes = EntryPointNode.ValidateNodes(env, subGraphRunContext, input.Nodes, node.Catalog);
// Change the subgraph to use the training data as input.
var varName = input.Inputs.Data.VarName;
VariableBinding transformModelVarName = null;
if (input.TransformModel != null)
{
transformModelVarName = node.GetInputVariable(nameof(input.TransformModel));
}
if (!subGraphRunContext.TryGetVariable(varName, out var dataVariable))
{
throw env.Except($"Invalid variable name '{varName}'.");
}
var trainingVar = node.GetInputVariable(nameof(input.TrainingData));
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.RenameInputVariable(dataVariable.Name, trainingVar);
}
subGraphRunContext.RemoveVariable(dataVariable);
// Change the subgraph to use the model variable as output.
varName = input.Outputs.Model.VarName;
if (!subGraphRunContext.TryGetVariable(varName, out dataVariable))
{
throw env.Except($"Invalid variable name '{varName}'.");
}
string outputVarName = node.GetOutputVariableName(nameof(Output.PredictorModel));
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.RenameOutputVariable(dataVariable.Name, outputVarName);
}
subGraphRunContext.RemoveVariable(dataVariable);
// Move the variables from the subcontext to the main context.
node.Context.AddContextVariables(subGraphRunContext);
// Change all the subgraph nodes to use the main context.
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.SetContext(node.Context);
}
// Testing using test data set
var testingVar = node.GetInputVariable(nameof(input.TestingData));
var exp = new Experiment(env);
//combine the predictor model with any potential transfrom model passed from the outer graph
if (transformModelVarName != null && transformModelVarName.VariableName != null)
{
var modelCombine = new ML.Transforms.TwoHeterogeneousModelCombiner
{
TransformModel = { VarName = transformModelVarName.VariableName },
PredictorModel = { VarName = outputVarName }
};
var modelCombineOutput = exp.Add(modelCombine);
outputVarName = modelCombineOutput.PredictorModel.VarName;
}
// Add the scoring node for testing.
var scoreNode = new ML.Transforms.DatasetScorer
{
Data = { VarName = testingVar.ToJson() },
PredictorModel = { VarName = outputVarName }
};
var scoreNodeOutput = exp.Add(scoreNode);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
// Do not double-add previous nodes.
exp.Reset();
// REVIEW: we need to extract the proper label column name here to pass to the evaluators.
// This is where you would add code to do it.
var settings = new MacroUtils.EvaluatorSettings
{
LabelColumn = DefaultColumnNames.Label
};
string outVariableName;
if (input.IncludeTrainingMetrics)
{
// Add the scoring node for training.
var scoreNodeTraining = new ML.Transforms.DatasetScorer
{
Data = { VarName = trainingVar.ToJson() },
PredictorModel = { VarName = outputVarName }
};
var scoreNodeTrainingOutput = exp.Add(scoreNodeTraining);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
// Do not double-add previous nodes.
exp.Reset();
// Add the evaluator node for training.
var evalInputOutputTraining = MacroUtils.GetEvaluatorInputOutput(input.Kind, settings);
var evalNodeTraining = evalInputOutputTraining.Item1;
var evalOutputTraining = evalInputOutputTraining.Item2;
evalNodeTraining.Data.VarName = scoreNodeTrainingOutput.ScoredData.VarName;
if (node.OutputMap.TryGetValue(nameof(Output.TrainingWarnings), out outVariableName))
{
evalOutputTraining.Warnings.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingOverallMetrics), out outVariableName))
{
evalOutputTraining.OverallMetrics.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingPerInstanceMetrics), out outVariableName))
{
evalOutputTraining.PerInstanceMetrics.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingConfusionMatrix), out outVariableName) &&
evalOutputTraining is CommonOutputs.IClassificationEvaluatorOutput eoTraining)
{
eoTraining.ConfusionMatrix.VarName = outVariableName;
}
exp.Add(evalNodeTraining, evalOutputTraining);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
}
// Do not double-add previous nodes.
exp.Reset();
// Add the evaluator node for testing.
var evalInputOutput = MacroUtils.GetEvaluatorInputOutput(input.Kind, settings);
var evalNode = evalInputOutput.Item1;
var evalOutput = evalInputOutput.Item2;
evalNode.Data.VarName = scoreNodeOutput.ScoredData.VarName;
if (node.OutputMap.TryGetValue(nameof(Output.Warnings), out outVariableName))
{
evalOutput.Warnings.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.OverallMetrics), out outVariableName))
{
evalOutput.OverallMetrics.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.PerInstanceMetrics), out outVariableName))
{
evalOutput.PerInstanceMetrics.VarName = outVariableName;
}
if (node.OutputMap.TryGetValue(nameof(Output.ConfusionMatrix), out outVariableName) &&
evalOutput is CommonOutputs.IClassificationEvaluatorOutput eo)
{
eo.ConfusionMatrix.VarName = outVariableName;
}
exp.Add(evalNode, evalOutput);
subGraphNodes.AddRange(EntryPointNode.ValidateNodes(env, node.Context, exp.GetNodes(), node.Catalog));
// Marks as an atomic unit that can be run in
// a distributed fashion.
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.StageId = input.PipelineId;
}
return(new CommonOutputs.MacroOutput <Output>()
{
Nodes = subGraphNodes
});
}
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
};
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;
// Set the input bindings for the CombineMetrics entry point.
var combineInputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var combineInputMap = new Dictionary <ParameterBinding, VariableBinding>();
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> 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 splitArgs = new CVSplit.Input();
splitArgs.NumFolds = input.NumFolds;
splitArgs.StratificationColumn = input.StratificationColumn;
var inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
var inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var inputData = node.GetInputVariable(nameof(splitArgs.Data));
ParameterBinding paramBinding = new SimpleParameterBinding(nameof(splitArgs.Data));
inputBindingMap.Add(nameof(splitArgs.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, inputData);
var outputMap = new Dictionary <string, string>();
var splitOutputTrainData = new ArrayVar <IDataView>();
var splitOutputTestData = new ArrayVar <IDataView>();
outputMap.Add(nameof(CVSplit.Output.TrainData), splitOutputTrainData.VarName);
outputMap.Add(nameof(CVSplit.Output.TestData), splitOutputTestData.VarName);
var splitNode = EntryPointNode.Create(env, "Models.CrossValidatorDatasetSplitter", splitArgs,
node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(splitNode);
var predModelVars = new Var <PredictorModel> [input.NumFolds];
var inputTransformModelVars = new Var <PredictorModel> [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);
// 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 <TransformModel> {
VarName = transformModelVarName.VariableName
}
}
;
args.Inputs.Data = new Var <IDataView>
{
VarName = mapping[input.Inputs.Data.VarName]
};
args.Outputs.PredictorModel = new Var <PredictorModel>
{
VarName = mapping[input.Outputs.PredictorModel.VarName]
};
// Set train/test trainer kind to match.
args.Kind = input.Kind;
// Set the input bindings for the TrainTest entry point.
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
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(splitOutputTrainData.VarName, k));
var testingData = new SimpleParameterBinding(nameof(args.TestingData));
inputBindingMap.Add(nameof(args.TestingData), new List <ParameterBinding> {
testingData
});
inputMap.Add(testingData, new ArrayIndexVariableBinding(splitOutputTestData.VarName, k));
outputMap = new Dictionary <string, string>();
var transformModelVar = new Var <TransformModel>();
var predModelVar = new Var <PredictorModel>();
outputMap.Add(nameof(TrainTestMacro.Output.PredictorModel), predModelVar.VarName);
predModelVars[k] = predModelVar;
if (transformModelVarName != null && transformModelVarName.VariableName != null)
{
var combineModelsArgs = new ModelOperations.SimplePredictorModelInput();
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var inputTransformModel = new SimpleVariableBinding(transformModelVarName.VariableName);
var inputPredictorModel = new SimpleVariableBinding(predModelVar.VarName);
paramBinding = new SimpleParameterBinding(nameof(combineModelsArgs.TransformModel));
inputBindingMap.Add(nameof(combineModelsArgs.TransformModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, inputTransformModel);
paramBinding = new SimpleParameterBinding(nameof(combineModelsArgs.PredictorModel));
inputBindingMap.Add(nameof(combineModelsArgs.PredictorModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, inputPredictorModel);
outputMap = new Dictionary <string, string>();
var combineNodeOutputPredictorModel = new Var <PredictorModel>();
predModelVars[k] = combineNodeOutputPredictorModel;
outputMap.Add(nameof(ModelOperations.PredictorModelOutput.PredictorModel), combineNodeOutputPredictorModel.VarName);
EntryPointNode combineNode = EntryPointNode.Create(env, "Transforms.TwoHeterogeneousModelCombiner", combineModelsArgs,
node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(combineNode);
}
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.Context, inputBindingMap, inputMap, outputMap));
}
// Convert the predictor models to an array of predictor models.
MacroUtils.ConvertIPredictorModelsToArray(env, node.Context, subGraphNodes, predModelVars, node.GetOutputVariableName(nameof(Output.PredictorModel)));
// Convert the warnings, overall, per instance and confusion matrix data views into an array.
var warningsArrayVar = new ArrayVar <IDataView>();
var overallArrayVar = new ArrayVar <IDataView>();
var instanceArrayVar = new ArrayVar <IDataView>();
ArrayVar <IDataView> confusionMatrixArrayVar = null;
MacroUtils.ConvertIdataViewsToArray(env, node.Context, subGraphNodes, warningsVars, warningsArrayVar.VarName);
MacroUtils.ConvertIdataViewsToArray(env, node.Context, subGraphNodes, overallMetricsVars, overallArrayVar.VarName);
MacroUtils.ConvertIdataViewsToArray(env, node.Context, subGraphNodes, instanceMetricsVars, instanceArrayVar.VarName);
if (input.Kind == MacroUtils.TrainerKinds.SignatureBinaryClassifierTrainer ||
input.Kind == MacroUtils.TrainerKinds.SignatureMultiClassClassifierTrainer)
{
confusionMatrixArrayVar = new ArrayVar <IDataView>();
MacroUtils.ConvertIdataViewsToArray(env, node.Context, subGraphNodes, confusionMatrixVars, confusionMatrixArrayVar.VarName);
}
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(warningsArrayVar.VarName));
var overallArray = new SimpleParameterBinding(nameof(combineArgs.OverallMetrics));
combineInputBindingMap.Add(nameof(combineArgs.OverallMetrics), new List <ParameterBinding> {
overallArray
});
combineInputMap.Add(overallArray, new SimpleVariableBinding(overallArrayVar.VarName));
var combinePerInstArray = new SimpleParameterBinding(nameof(combineArgs.PerInstanceMetrics));
combineInputBindingMap.Add(nameof(combineArgs.PerInstanceMetrics), new List <ParameterBinding> {
combinePerInstArray
});
combineInputMap.Add(combinePerInstArray, new SimpleVariableBinding(instanceArrayVar.VarName));
if (confusionMatrixArrayVar != null)
{
var combineConfArray = new SimpleParameterBinding(nameof(combineArgs.ConfusionMatrix));
combineInputBindingMap.Add(nameof(combineArgs.ConfusionMatrix), new List <ParameterBinding> {
combineConfArray
});
combineInputMap.Add(combineConfArray, new SimpleVariableBinding(confusionMatrixArrayVar.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 (confusionMatrixArrayVar != null)
{
var combineConfusionMatrix = new Var <IDataView>();
combineConfusionMatrix.VarName = node.GetOutputVariableName(nameof(Output.ConfusionMatrix));
combineOutputMap.Add(nameof(TrainTestMacro.Output.ConfusionMatrix), combineConfusionMatrix.VarName);
}
var combineMetricsNode = EntryPointNode.Create(env, "Models.CrossValidationResultsCombiner",
combineArgs, node.Context, combineInputBindingMap, combineInputMap, combineOutputMap);
subGraphNodes.Add(combineMetricsNode);
return(new CommonOutputs.MacroOutput <Output>()
{
Nodes = subGraphNodes
});
}
/// <summary>
/// Checks the given JSON object key-value pair is a valid EntryPoint input and
/// extracts out any variables that need to be populated. These variables will be
/// added to the EntryPoint context. Input parameters that are not set to variables
/// will be immediately set using the input builder instance.
/// </summary>
private void CheckAndSetInputValue(KeyValuePair <string, JToken> pair)
{
var inputName = _inputBuilder.GetFieldNameOrNull(pair.Key);
if (VariableBinding.IsBindingToken(pair.Value))
{
Type valueType = _inputBuilder.GetFieldTypeOrNull(pair.Key);
if (valueType == null)
{
throw _host.Except($"Unexpected input name: '{pair.Key}'");
}
if (!EntryPointVariable.IsValidType(valueType))
{
throw _host.Except($"Unexpected input variable type: {valueType}");
}
var varBinding = VariableBinding.Create(_host, pair.Value.Value <string>());
_context.AddInputVariable(varBinding, valueType);
if (!_inputBindingMap.ContainsKey(inputName))
{
_inputBindingMap[inputName] = new List <ParameterBinding>();
}
var paramBinding = new SimpleParameterBinding(inputName);
_inputBindingMap[inputName].Add(paramBinding);
_inputMap[paramBinding] = varBinding;
}
else if (pair.Value is JArray &&
((JArray)pair.Value).Any(tok => VariableBinding.IsBindingToken(tok)))
{
// REVIEW: EntryPoint arrays and dictionaries containing
// variables must ONLY contain variables right now.
if (!((JArray)pair.Value).All(tok => VariableBinding.IsBindingToken(tok)))
{
throw _host.Except($"Input {pair.Key} may ONLY contain variables.");
}
Type valueType = _inputBuilder.GetFieldTypeOrNull(pair.Key);
if (valueType == null || !valueType.HasElementType)
{
throw _host.Except($"Unexpected input name: '{pair.Key}'");
}
valueType = valueType.GetElementType();
int i = 0;
foreach (var varName in (JArray)pair.Value)
{
var varBinding = VariableBinding.Create(_host, varName.Value <string>());
_context.AddInputVariable(varBinding, valueType);
if (!_inputBindingMap.ContainsKey(inputName))
{
_inputBindingMap[inputName] = new List <ParameterBinding>();
}
var paramBinding = new ArrayIndexParameterBinding(inputName, i++);
_inputBindingMap[inputName].Add(paramBinding);
_inputMap[paramBinding] = varBinding;
}
}
// REVIEW: Implement support for Dictionary of variable values. We need to differentiate
// between a Dictionary and a Component here, and likely need to support nested components
// all of which might have variables. Our current machinery only works at the 'Node' level.
else
{
// This is not a variable.
if (!_inputBuilder.TrySetValueJson(pair.Key, pair.Value))
{
throw _host.Except($"Unexpected input: '{pair.Key}'");
}
}
}
public static CommonOutputs.MacroOutput <Output> TrainTest(
IHostEnvironment env,
Arguments input,
EntryPointNode node)
{
// Create default pipeline ID if one not given.
input.PipelineId = input.PipelineId ?? Guid.NewGuid().ToString("N");
// Parse the subgraph.
var subGraphRunContext = new RunContext(env);
var subGraphNodes = EntryPointNode.ValidateNodes(env, subGraphRunContext, input.Nodes, label: input.LabelColumn,
input.GroupColumn.IsExplicit ? input.GroupColumn.Value : null,
input.WeightColumn.IsExplicit ? input.WeightColumn.Value : null,
input.NameColumn.IsExplicit ? input.NameColumn.Value : null);
// Change the subgraph to use the training data as input.
var varName = input.Inputs.Data.VarName;
VariableBinding transformModelVarName = null;
if (input.TransformModel != null)
{
transformModelVarName = node.GetInputVariable(nameof(input.TransformModel));
}
if (!subGraphRunContext.TryGetVariable(varName, out var dataVariable))
{
throw env.Except($"Invalid variable name '{varName}'.");
}
var trainingVar = node.GetInputVariable(nameof(input.TrainingData));
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.RenameInputVariable(dataVariable.Name, trainingVar);
}
subGraphRunContext.RemoveVariable(dataVariable);
// Change the subgraph to use the model variable as output.
varName = input.Outputs.PredictorModel.VarName;
if (!subGraphRunContext.TryGetVariable(varName, out dataVariable))
{
throw env.Except($"Invalid variable name '{varName}'.");
}
string predictorModelVarName = node.GetOutputVariableName(nameof(Output.PredictorModel));
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.RenameOutputVariable(dataVariable.Name, predictorModelVarName);
}
subGraphRunContext.RemoveVariable(dataVariable);
// Move the variables from the subcontext to the main context.
node.Context.AddContextVariables(subGraphRunContext);
// Change all the subgraph nodes to use the main context.
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.SetContext(node.Context);
}
// Testing using test data set
var testingVar = node.GetInputVariable(nameof(input.TestingData));
//var exp = new Experiment(env);
Dictionary <string, List <ParameterBinding> > inputBindingMap;
Dictionary <ParameterBinding, VariableBinding> inputMap;
ParameterBinding paramBinding;
Dictionary <string, string> outputMap;
//combine the predictor model with any potential transfrom model passed from the outer graph
if (transformModelVarName != null && transformModelVarName.VariableName != null)
{
var combineArgs = new ModelOperations.SimplePredictorModelInput();
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var inputTransformModel = new SimpleVariableBinding(transformModelVarName.VariableName);
var inputPredictorModel = new SimpleVariableBinding(predictorModelVarName);
paramBinding = new SimpleParameterBinding(nameof(combineArgs.TransformModel));
inputBindingMap.Add(nameof(combineArgs.TransformModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, inputTransformModel);
paramBinding = new SimpleParameterBinding(nameof(combineArgs.PredictorModel));
inputBindingMap.Add(nameof(combineArgs.PredictorModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, inputPredictorModel);
outputMap = new Dictionary <string, string>();
var combineNodeOutputPredictorModel = new Var <PredictorModel>();
predictorModelVarName = combineNodeOutputPredictorModel.VarName;
outputMap.Add(nameof(ModelOperations.PredictorModelOutput.PredictorModel), combineNodeOutputPredictorModel.VarName);
EntryPointNode combineNode = EntryPointNode.Create(env, "Transforms.TwoHeterogeneousModelCombiner", combineArgs,
node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(combineNode);
}
// Add the scoring node for testing.
var args = new ScoreModel.Input();
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
paramBinding = new SimpleParameterBinding(nameof(args.Data));
inputBindingMap.Add(nameof(args.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, testingVar);
var scoreNodeInputPredictorModel = new SimpleVariableBinding(predictorModelVarName);
paramBinding = new SimpleParameterBinding(nameof(args.PredictorModel));
inputBindingMap.Add(nameof(args.PredictorModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, scoreNodeInputPredictorModel);
var scoreNodeOutputScoredData = new Var <IDataView>();
var scoreNodeOutputScoringTransform = new Var <TransformModel>();
outputMap = new Dictionary <string, string>();
outputMap.Add(nameof(ScoreModel.Output.ScoredData), scoreNodeOutputScoredData.VarName);
outputMap.Add(nameof(ScoreModel.Output.ScoringTransform), scoreNodeOutputScoringTransform.VarName);
EntryPointNode scoreNode = EntryPointNode.Create(env, "Transforms.DatasetScorer", args,
node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(scoreNode);
var evalDataVarName = scoreNodeOutputScoredData.VarName;
// REVIEW: add similar support for FeatureColumn.
var settings = new MacroUtils.EvaluatorSettings
{
LabelColumn = input.LabelColumn,
WeightColumn = input.WeightColumn.IsExplicit ? input.WeightColumn.Value : null,
GroupColumn = input.GroupColumn.IsExplicit ? input.GroupColumn.Value : null,
NameColumn = input.NameColumn.IsExplicit ? input.NameColumn.Value : null
};
if (input.IncludeTrainingMetrics)
{
string evalTrainingDataVarName;
args = new ScoreModel.Input();
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
paramBinding = new SimpleParameterBinding(nameof(args.Data));
inputBindingMap.Add(nameof(args.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, trainingVar);
scoreNodeInputPredictorModel = new SimpleVariableBinding(predictorModelVarName);
paramBinding = new SimpleParameterBinding(nameof(args.PredictorModel));
inputBindingMap.Add(nameof(args.PredictorModel), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, scoreNodeInputPredictorModel);
scoreNodeOutputScoredData = new Var <IDataView>();
scoreNodeOutputScoringTransform = new Var <TransformModel>();
outputMap = new Dictionary <string, string>();
outputMap.Add(nameof(ScoreModel.Output.ScoredData), scoreNodeOutputScoredData.VarName);
outputMap.Add(nameof(ScoreModel.Output.ScoringTransform), scoreNodeOutputScoringTransform.VarName);
scoreNode = EntryPointNode.Create(env, "Transforms.DatasetScorer", args,
node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(scoreNode);
evalTrainingDataVarName = scoreNodeOutputScoredData.VarName;
// Add the evaluator node for training.
var evalTrainingArgs = MacroUtils.GetEvaluatorArgs(input.Kind, out var evalTrainingEntryPointName, settings);
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var evalTrainingNodeInputData = new SimpleVariableBinding(evalTrainingDataVarName);
paramBinding = new SimpleParameterBinding(nameof(evalTrainingArgs.Data));
inputBindingMap.Add(nameof(evalTrainingArgs.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, evalTrainingNodeInputData);
outputMap = new Dictionary <string, string>();
if (node.OutputMap.TryGetValue(nameof(Output.TrainingWarnings), out var outTrainingVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.Warnings), outTrainingVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingOverallMetrics), out outTrainingVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.OverallMetrics), outTrainingVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingPerInstanceMetrics), out outTrainingVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.PerInstanceMetrics), outTrainingVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.TrainingConfusionMatrix), out outTrainingVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.ConfusionMatrix), outTrainingVariableName);
}
EntryPointNode evalTrainingNode = EntryPointNode.Create(env, evalTrainingEntryPointName, evalTrainingArgs, node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(evalTrainingNode);
}
// Add the evaluator node for testing.
var evalArgs = MacroUtils.GetEvaluatorArgs(input.Kind, out var evalEntryPointName, settings);
inputBindingMap = new Dictionary <string, List <ParameterBinding> >();
inputMap = new Dictionary <ParameterBinding, VariableBinding>();
var evalNodeInputData = new SimpleVariableBinding(evalDataVarName);
paramBinding = new SimpleParameterBinding(nameof(evalArgs.Data));
inputBindingMap.Add(nameof(evalArgs.Data), new List <ParameterBinding>()
{
paramBinding
});
inputMap.Add(paramBinding, evalNodeInputData);
outputMap = new Dictionary <string, string>();
if (node.OutputMap.TryGetValue(nameof(Output.Warnings), out var outVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.Warnings), outVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.OverallMetrics), out outVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.OverallMetrics), outVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.PerInstanceMetrics), out outVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.PerInstanceMetrics), outVariableName);
}
if (node.OutputMap.TryGetValue(nameof(Output.ConfusionMatrix), out outVariableName))
{
outputMap.Add(nameof(CommonOutputs.ClassificationEvaluateOutput.ConfusionMatrix), outVariableName);
}
EntryPointNode evalNode = EntryPointNode.Create(env, evalEntryPointName, evalArgs, node.Context, inputBindingMap, inputMap, outputMap);
subGraphNodes.Add(evalNode);
// Marks as an atomic unit that can be run in
// a distributed fashion.
foreach (var subGraphNode in subGraphNodes)
{
subGraphNode.StageId = input.PipelineId;
}
return(new CommonOutputs.MacroOutput <Output>()
{
Nodes = subGraphNodes
});
}
