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());
}
private TransformInference.SuggestedTransform[] SampleTransforms(RecipeInference.SuggestedRecipe.SuggestedLearner learner,
PipelinePattern[] history, out long transformsBitMask, bool uniformRandomSampling = false)
{
var sampledTransforms =
new List <TransformInference.SuggestedTransform>(
AutoMlUtils.GetMandatoryTransforms(AvailableTransforms));
var remainingAvailableTransforms =
AvailableTransforms.Where(t => !sampledTransforms.Any(t.Equals)).ToArray();
var mask = AutoMlUtils.TransformsToBitmask(sampledTransforms.ToArray());
foreach (var transform in remainingAvailableTransforms)
{
// Add pseudo-mass to encourage sampling of untried transforms.
double maxWeight = history.Length > 0 ? history.Max(w => w.PerformanceSummary.MetricValue) : 0d;
double allWeight = Math.Max(maxWeight, 1d);
double learnerWeight = Math.Max(maxWeight, 1d);
int allCounts = 1;
int learnerCounts = 1;
// Add mass according to performance.
foreach (var pipeline in history)
{
if (pipeline.Transforms.Any(transform.Equals))
{
allWeight +=
AutoMlUtils.ProcessWeight(pipeline.PerformanceSummary.MetricValue,
maxWeight, IsMaximizingMetric);
allCounts++;
if (pipeline.Learner.LearnerName == learner.LearnerName)
{
learnerWeight += pipeline.PerformanceSummary.MetricValue;
learnerCounts++;
}
}
}
// Take average mass as weight, and take convex combination of
// learner-specific weight and unconditioned weight.
allWeight /= allCounts > 0 ? allCounts : 1;
learnerWeight /= learnerCounts > 0 ? learnerCounts : 1;
var lambda = MathUtils.Sigmoid(learnerCounts - 3);
var combinedWeight = uniformRandomSampling ?
0.5 : lambda * learnerWeight + (1 - lambda) * allWeight;
// Sample transform according to combined weight.
if (ProbUtils.SampleUniform() <= combinedWeight / maxWeight)
{
mask |= 1L << transform.AtomicGroupId;
}
}
// Add all chosen transforms.
sampledTransforms.AddRange(remainingAvailableTransforms.Where(t =>
AutoMlUtils.AtomicGroupPresent(mask, t.AtomicGroupId)));
// Add final features concat transform. NOTE: computed bitmask should always
// exclude the final features concat. If we forget to exclude that one, will
// cause an error in verification, since it isn't included in the original
// dependency mapping (i.e., its level isn't in the dictionary).
sampledTransforms.AddRange(AutoMlUtils.GetFinalFeatureConcat(Env, FullyTransformedData,
DependencyMapping, sampledTransforms.ToArray(), AvailableTransforms, DataRoles));
transformsBitMask = mask;
return(sampledTransforms.ToArray());
}
