public override IEstimator <ITransformer> Reconcile(IHostEnvironment env, PipelineColumn[] toOutput,
IReadOnlyDictionary <PipelineColumn, string> inputNames, IReadOnlyDictionary <PipelineColumn, string> outputNames, IReadOnlyCollection <string> usedNames)
{
var infos = new TermTransform.ColumnInfo[toOutput.Length];
Action <TermTransform> onFit = null;
for (int i = 0; i < toOutput.Length; ++i)
{
var tcol = (ITermCol)toOutput[i];
infos[i] = new TermTransform.ColumnInfo(inputNames[tcol.Input], outputNames[toOutput[i]],
tcol.Config.Max, (TermTransform.SortOrder)tcol.Config.Order);
if (tcol.Config.OnFit != null)
{
int ii = i; // Necessary because if we capture i that will change to toOutput.Length on call.
onFit += tt => tcol.Config.OnFit(tt.GetTermMap(ii));
}
}
var est = new TermEstimator(env, infos);
if (onFit == null)
{
return(est);
}
return(est.WithOnFitDelegate(onFit));
}
public CategoricalTransform(TermEstimator term, IEstimator <ITransformer> toVector, IDataView input)
{
if (toVector != null)
{
_transformer = term.Append(toVector).Fit(input);
}
else
{
_transformer = new TransformerChain <ITransformer>(term.Fit(input));
}
}
public CategoricalEstimator(IHostEnvironment env, params ColumnInfo[] columns)
{
Contracts.CheckValue(env, nameof(env));
_host = env.Register(nameof(TermEstimator));
_term = new TermEstimator(_host, columns);
var cols = new List <(string input, string output, bool bag)>();
bool binaryEncoding = false;
for (int i = 0; i < columns.Length; i++)
{
var column = columns[i];
bool bag;
CategoricalTransform.OutputKind kind = columns[i].OutputKind;
switch (kind)
{
default:
throw _host.ExceptUserArg(nameof(column.OutputKind));
case CategoricalTransform.OutputKind.Key:
continue;
case CategoricalTransform.OutputKind.Bin:
binaryEncoding = true;
bag = false;
break;
case CategoricalTransform.OutputKind.Ind:
bag = false;
break;
case CategoricalTransform.OutputKind.Bag:
bag = true;
break;
}
cols.Add((column.Output, column.Output, bag));
if (binaryEncoding)
{
_keyToSomething = new KeyToBinaryVectorEstimator(_host, cols.Select(x => new KeyToBinaryVectorTransform.ColumnInfo(x.input, x.output)).ToArray());
}
else
{
_keyToSomething = new KeyToVectorEstimator(_host, cols.Select(x => new KeyToVectorTransform.ColumnInfo(x.input, x.output, x.bag)).ToArray());
}
}
}
internal void WrapTermWithDelegate(Action <TermTransform> onFit)
{
_term = (TermEstimator)_term.WithOnFitDelegate(onFit);
}
public CategoricalEstimator(IHostEnvironment env, params ColumnInfo[] columns)
{
Contracts.CheckValue(env, nameof(env));
_host = env.Register(nameof(TermEstimator));
_term = new TermEstimator(_host, columns);
var binaryCols = new List <(string input, string output)>();
var cols = new List <(string input, string output, bool bag)>();
for (int i = 0; i < columns.Length; i++)
{
var column = columns[i];
CategoricalTransform.OutputKind kind = columns[i].OutputKind;
switch (kind)
{
default:
throw _host.ExceptUserArg(nameof(column.OutputKind));
case CategoricalTransform.OutputKind.Key:
continue;
case CategoricalTransform.OutputKind.Bin:
binaryCols.Add((column.Output, column.Output));
break;
case CategoricalTransform.OutputKind.Ind:
cols.Add((column.Output, column.Output, false));
break;
case CategoricalTransform.OutputKind.Bag:
cols.Add((column.Output, column.Output, true));
break;
}
}
IEstimator <ITransformer> toBinVector = null;
IEstimator <ITransformer> toVector = null;
if (binaryCols.Count > 0)
{
toBinVector = new KeyToBinaryVectorEstimator(_host, binaryCols.Select(x => new KeyToBinaryVectorTransform.ColumnInfo(x.input, x.output)).ToArray());
}
if (cols.Count > 0)
{
toVector = new KeyToVectorEstimator(_host, cols.Select(x => new KeyToVectorTransform.ColumnInfo(x.input, x.output, x.bag)).ToArray());
}
if (toBinVector != null && toVector != null)
{
_toSomething = toVector.Append(toBinVector);
}
else
{
if (toBinVector != null)
{
_toSomething = toBinVector;
}
else
{
_toSomething = toVector;
}
}
}
public CategoricalTransform(TermEstimator term, IEstimator <ITransformer> toVector, IDataView input)
{
var chain = term.Append(toVector);
_transformer = chain.Fit(input);
}
