private protected override void CheckLabels(RoleMappedData data)
{
Contracts.AssertValue(data);
data.CheckBinaryLabel();
}
private FieldAwareFactorizationMachinePredictor TrainCore(IChannel ch, IProgressChannel pch, RoleMappedData data, RoleMappedData validData, FieldAwareFactorizationMachinePredictor predictor)
{
Host.AssertValue(ch);
Host.AssertValue(pch);
data.CheckBinaryLabel();
var featureColumns = data.Schema.GetColumns(RoleMappedSchema.ColumnRole.Feature);
int fieldCount = featureColumns.Count;
int totalFeatureCount = 0;
int[] fieldColumnIndexes = new int[fieldCount];
for (int f = 0; f < fieldCount; f++)
{
var col = featureColumns[f];
Host.Assert(col.Type.AsVector.VectorSize > 0);
if (col == null)
{
throw ch.ExceptParam(nameof(data), "Empty feature column not allowed");
}
Host.Assert(!data.Schema.Schema.IsHidden(col.Index));
if (!col.Type.IsKnownSizeVector || col.Type.ItemType != NumberType.Float)
{
throw ch.ExceptParam(nameof(data), "Training feature column '{0}' must be a known-size vector of R4, but has type: {1}.", col.Name, col.Type);
}
fieldColumnIndexes[f] = col.Index;
totalFeatureCount += col.Type.AsVector.VectorSize;
}
ch.Check(checked (totalFeatureCount * fieldCount * _latentDimAligned) <= Utils.ArrayMaxSize, "Latent dimension or the number of fields too large");
if (predictor != null)
{
ch.Check(predictor.FeatureCount == totalFeatureCount, "Input model's feature count mismatches training feature count");
ch.Check(predictor.LatentDim == _latentDim, "Input model's latent dimension mismatches trainer's");
}
if (validData != null)
{
validData.CheckBinaryLabel();
var validFeatureColumns = data.Schema.GetColumns(RoleMappedSchema.ColumnRole.Feature);
Host.Assert(fieldCount == validFeatureColumns.Count);
for (int f = 0; f < fieldCount; f++)
{
Host.Assert(featureColumns[f] == validFeatureColumns[f]);
}
}
bool shuffle = _shuffle;
if (shuffle && !data.Data.CanShuffle)
{
ch.Warning("Training data does not support shuffling, so ignoring request to shuffle");
shuffle = false;
}
var rng = shuffle ? Host.Rand : null;
var featureGetters = new ValueGetter <VBuffer <float> > [fieldCount];
var featureBuffer = new VBuffer <float>();
var featureValueBuffer = new float[totalFeatureCount];
var featureIndexBuffer = new int[totalFeatureCount];
var featureFieldBuffer = new int[totalFeatureCount];
var latentSum = new AlignedArray(fieldCount * fieldCount * _latentDimAligned, 16);
var metricNames = new List <string>()
{
"Training-loss"
};
if (validData != null)
{
metricNames.Add("Validation-loss");
}
int iter = 0;
long exampleCount = 0;
long badExampleCount = 0;
long validBadExampleCount = 0;
double loss = 0;
double validLoss = 0;
pch.SetHeader(new ProgressHeader(metricNames.ToArray(), new string[] { "iterations", "examples" }), entry =>
{
entry.SetProgress(0, iter, _numIterations);
entry.SetProgress(1, exampleCount);
});
Func <int, bool> pred = c => fieldColumnIndexes.Contains(c) || c == data.Schema.Label.Index || (data.Schema.Weight != null && c == data.Schema.Weight.Index);
InitializeTrainingState(fieldCount, totalFeatureCount, predictor, out float[] linearWeights,
out AlignedArray latentWeightsAligned, out float[] linearAccSqGrads, out AlignedArray latentAccSqGradsAligned);
// refer to Algorithm 3 in https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf
while (iter++ < _numIterations)
{
using (var cursor = data.Data.GetRowCursor(pred, rng))
{
var labelGetter = RowCursorUtils.GetLabelGetter(cursor, data.Schema.Label.Index);
var weightGetter = data.Schema.Weight == null ? null : RowCursorUtils.GetGetterAs <float>(NumberType.R4, cursor, data.Schema.Weight.Index);
for (int i = 0; i < fieldCount; i++)
{
featureGetters[i] = cursor.GetGetter <VBuffer <float> >(fieldColumnIndexes[i]);
}
loss = 0;
exampleCount = 0;
badExampleCount = 0;
while (cursor.MoveNext())
{
float label = 0;
float weight = 1;
int count = 0;
float modelResponse = 0;
labelGetter(ref label);
weightGetter?.Invoke(ref weight);
float annihilation = label - label + weight - weight;
if (!FloatUtils.IsFinite(annihilation))
{
badExampleCount++;
continue;
}
if (!FieldAwareFactorizationMachineUtils.LoadOneExampleIntoBuffer(featureGetters, featureBuffer, _norm, ref count,
featureFieldBuffer, featureIndexBuffer, featureValueBuffer))
{
badExampleCount++;
continue;
}
// refer to Algorithm 1 in [3] https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf
FieldAwareFactorizationMachineInterface.CalculateIntermediateVariables(fieldCount, _latentDimAligned, count,
featureFieldBuffer, featureIndexBuffer, featureValueBuffer, linearWeights, latentWeightsAligned, latentSum, ref modelResponse);
var slope = CalculateLossSlope(label, modelResponse);
// refer to Algorithm 2 in [3] https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf
FieldAwareFactorizationMachineInterface.CalculateGradientAndUpdate(_lambdaLinear, _lambdaLatent, _learningRate, fieldCount, _latentDimAligned, weight, count,
featureFieldBuffer, featureIndexBuffer, featureValueBuffer, latentSum, slope, linearWeights, latentWeightsAligned, linearAccSqGrads, latentAccSqGradsAligned);
loss += weight * CalculateLoss(label, modelResponse);
exampleCount++;
}
loss /= exampleCount;
}
if (_verbose)
{
if (validData == null)
{
pch.Checkpoint(loss, iter, exampleCount);
}
else
{
validLoss = CalculateAvgLoss(ch, validData, _norm, linearWeights, latentWeightsAligned, _latentDimAligned, latentSum,
featureFieldBuffer, featureIndexBuffer, featureValueBuffer, featureBuffer, ref validBadExampleCount);
pch.Checkpoint(loss, validLoss, iter, exampleCount);
}
}
}
if (badExampleCount != 0)
{
ch.Warning($"Skipped {badExampleCount} examples with bad label/weight/features in training set");
}
if (validBadExampleCount != 0)
{
ch.Warning($"Skipped {validBadExampleCount} examples with bad label/weight/features in validation set");
}
return(new FieldAwareFactorizationMachinePredictor(Host, _norm, fieldCount, totalFeatureCount, _latentDim, linearWeights, latentWeightsAligned));
}
internal override void CheckLabel(RoleMappedData data)
{
data.CheckBinaryLabel();
}
private void CheckLabel(RoleMappedData examples, out int weightSetCount)
{
examples.CheckBinaryLabel();
weightSetCount = 1;
}
private protected override void CheckLabel(RoleMappedData data)
{
data.CheckBinaryLabel();
}