public virtual void UpdateLearners(RecipeInference.SuggestedRecipe.SuggestedLearner[] availableLearners)
{
AvailableLearners = availableLearners;
foreach (var learner in AvailableLearners)
{
AutoMlUtils.PopulateSweepableParams(learner);
}
}
public virtual void SetSpace(TransformInference.SuggestedTransform[] availableTransforms,
RecipeInference.SuggestedRecipe.SuggestedLearner[] availableLearners,
Func <PipelinePattern, long, bool> pipelineVerifier,
IDataView originalData, IDataView fullyTransformedData, AutoInference.DependencyMap dependencyMapping,
bool isMaximizingMetric)
{
AvailableLearners = availableLearners;
AvailableTransforms = availableTransforms;
PipelineVerifier = pipelineVerifier;
OriginalData = originalData;
FullyTransformedData = fullyTransformedData;
DependencyMapping = dependencyMapping;
IsMaximizingMetric = isMaximizingMetric;
foreach (var learner in AvailableLearners)
{
AutoMlUtils.PopulateSweepableParams(learner);
}
}
public override PipelinePattern[] GetNextCandidates(IEnumerable <PipelinePattern> history, int numCandidates, RoleMappedData dataRoles)
{
var candidates = new List <PipelinePattern>();
DataRoles = dataRoles;
while (candidates.Count < numCandidates)
{
Contracts.Assert(0 <= _currentLearnerIndex && _currentLearnerIndex < AvailableLearners.Length);
// Select hyperparameters and transforms based on learner and history.
PipelinePattern pipeline;
int count = 0;
bool valid;
var learner = AvailableLearners[_currentLearnerIndex];
// Make sure sweep paramater values exist; if not, populate them from learner object.
if (learner.PipelineNode.SweepParams.Any(p => p.RawValue == null))
{
AutoMlUtils.PopulateSweepableParams(learner);
}
do
{ // Make sure transforms set is valid. Repeat until passes verifier.
pipeline = new PipelinePattern(SampleTransforms(out var transformsBitMask),
learner, "", Env);
valid = PipelineVerifier(pipeline, transformsBitMask);
count++;
} while (!valid && count <= 1000);
// Keep only valid pipelines.
if (valid)
{
candidates.Add(pipeline);
}
// Update current index
_currentLearnerIndex = (_currentLearnerIndex + 1) % AvailableLearners.Length;
}
return(candidates.ToArray());
}
private PipelinePattern[] NextCandidates(PipelinePattern[] history, int numCandidates,
bool defaultHyperParams = false, bool uniformRandomTransforms = false)
{
const int maxNumberAttempts = 10;
double[] learnerWeights = LearnerHistoryToWeights(history, IsMaximizingMetric);
var candidates = new List <PipelinePattern>();
var sampledLearners = new RecipeInference.SuggestedRecipe.SuggestedLearner[numCandidates];
if (_currentStage == (int)Stages.Second || _currentStage == (int)Stages.Third)
{
// Select remaining learners in round-robin fashion.
for (int i = 0; i < numCandidates; i++)
{
sampledLearners[i] = AvailableLearners[i % AvailableLearners.Length].Clone();
}
}
else
{
// Select learners, based on weights.
var indices = ProbUtils.SampleCategoricalDistribution(numCandidates, learnerWeights);
foreach (var item in indices.Select((idx, i) => new { idx, i }))
{
sampledLearners[item.i] = AvailableLearners[item.idx].Clone();
}
}
// Select hyperparameters and transforms based on learner and history.
foreach (var learner in sampledLearners)
{
PipelinePattern pipeline;
int count = 0;
bool valid;
string hashKey;
if (!defaultHyperParams)
{
SampleHyperparameters(learner, history);
}
else
{
AutoMlUtils.PopulateSweepableParams(learner);
}
do
{ // Make sure transforms set is valid and have not seen pipeline before.
// Repeat until passes or runs out of chances.
pipeline = new PipelinePattern(
SampleTransforms(learner, history, out var transformsBitMask, uniformRandomTransforms),
learner, "", Env);
hashKey = GetHashKey(transformsBitMask, learner);
valid = PipelineVerifier(pipeline, transformsBitMask) && !VisitedPipelines.Contains(hashKey);
count++;
} while (!valid && count <= maxNumberAttempts);
// If maxed out chances and at second stage, move onto next stage.
if (count >= maxNumberAttempts && _currentStage == (int)Stages.Second)
{
_currentStage++;
}
// Keep only valid pipelines.
if (valid)
{
VisitedPipelines.Add(hashKey);
candidates.Add(pipeline);
}
}
return(candidates.ToArray());
}
