internal static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register("Categorical");
h.CheckValue(args, nameof(args));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(args.Column) > 0, nameof(args.Column));
var columns = new List <OneHotHashEncodingEstimator.ColumnInfo>();
foreach (var column in args.Column)
{
var col = new OneHotHashEncodingEstimator.ColumnInfo(
column.Source ?? column.Name,
column.Name,
column.OutputKind ?? args.OutputKind,
column.HashBits ?? args.HashBits,
column.Seed ?? args.Seed,
column.Ordered ?? args.Ordered,
column.InvertHash ?? args.InvertHash);
columns.Add(col);
}
return(new OneHotHashEncodingEstimator(env, columns.ToArray()).Fit(input).Transform(input) as IDataTransform);
}
public override IEstimator <ITransformer> Reconcile(IHostEnvironment env, PipelineColumn[] toOutput,
IReadOnlyDictionary <PipelineColumn, string> inputNames, IReadOnlyDictionary <PipelineColumn, string> outputNames, IReadOnlyCollection <string> usedNames)
{
var infos = new OneHotHashEncodingEstimator.ColumnInfo[toOutput.Length];
for (int i = 0; i < toOutput.Length; ++i)
{
var tcol = (ICategoricalCol)toOutput[i];
infos[i] = new OneHotHashEncodingEstimator.ColumnInfo(inputNames[tcol.Input], outputNames[toOutput[i]], (CategoricalTransform.OutputKind)tcol.Config.OutputKind,
tcol.Config.HashBits, tcol.Config.Seed, tcol.Config.Ordered, tcol.Config.InvertHash);
}
return(new OneHotHashEncodingEstimator(env, infos));
}
