public static CommonOutputs.TransformOutput CatTransformHash(IHostEnvironment env, CategoricalHashTransform.Arguments input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("CatTransformDict");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
var xf = CategoricalHashTransform.Create(host, input, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModel(env, xf, input.Data), OutputData = xf
});
}
public static IDataTransform CreateTransformCore(
OutputKind argsOutputKind,
OneToOneColumn[] columns,
List <OutputKind?> columnOutputKinds,
IDataTransform input,
IHost h,
IHostEnvironment env,
CategoricalHashTransform.Arguments catHashArgs = null)
{
Contracts.CheckValue(columns, nameof(columns));
Contracts.CheckValue(columnOutputKinds, nameof(columnOutputKinds));
Contracts.CheckParam(columns.Length == columnOutputKinds.Count, nameof(columns));
using (var ch = h.Start("Create Transform Core"))
{
// Create the KeyToVectorTransform, if needed.
List <KeyToVectorTransform.Column> cols = new List <KeyToVectorTransform.Column>();
bool binaryEncoding = argsOutputKind == OutputKind.Bin;
for (int i = 0; i < columns.Length; i++)
{
var column = columns[i];
if (!column.TrySanitize())
{
throw h.ExceptUserArg(nameof(Column.Name));
}
bool? bag;
OutputKind kind = columnOutputKinds[i].HasValue ? columnOutputKinds[i].Value : argsOutputKind;
switch (kind)
{
default:
throw env.ExceptUserArg(nameof(Column.OutputKind));
case OutputKind.Key:
continue;
case OutputKind.Bin:
binaryEncoding = true;
bag = false;
break;
case OutputKind.Ind:
bag = false;
break;
case OutputKind.Bag:
bag = true;
break;
}
var col = new KeyToVectorTransform.Column();
col.Name = column.Name;
col.Source = column.Name;
col.Bag = bag;
cols.Add(col);
}
if (cols.Count == 0)
{
return(input);
}
IDataTransform transform;
if (binaryEncoding)
{
if ((catHashArgs?.InvertHash ?? 0) != 0)
{
ch.Warning("Invert hashing is being used with binary encoding.");
}
var keyToBinaryArgs = new KeyToBinaryVectorTransform.Arguments();
keyToBinaryArgs.Column = cols.ToArray();
transform = new KeyToBinaryVectorTransform(h, keyToBinaryArgs, input);
}
else
{
var keyToVecArgs = new KeyToVectorTransform.Arguments
{
Bag = argsOutputKind == OutputKind.Bag,
Column = cols.ToArray()
};
transform = new KeyToVectorTransform(h, keyToVecArgs, input);
}
ch.Done();
return(transform);
}
}
