internal static IDataTransform Create(IHostEnvironment env, Options options, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register("Categorical");
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns));
var columns = new List <OneHotEncodingEstimator.ColumnInfo>();
foreach (var column in options.Columns)
{
var col = new OneHotEncodingEstimator.ColumnInfo(
column.Name,
column.Source ?? column.Name,
column.OutputKind ?? options.OutputKind,
column.MaxNumTerms ?? options.MaxNumTerms,
column.Sort ?? options.Sort,
column.Terms ?? options.Terms);
col.SetTerms(column.Term ?? options.Term);
columns.Add(col);
}
IDataView keyData = null;
if (!string.IsNullOrEmpty(options.DataFile))
{
using (var ch = h.Start("Load term data"))
keyData = ValueToKeyMappingTransformer.GetKeyDataViewOrNull(env, ch, options.DataFile, options.TermsColumn, options.Loader, out bool autoLoaded);
h.AssertValue(keyData);
}
var transformed = new OneHotEncodingEstimator(env, columns.ToArray(), keyData).Fit(input).Transform(input);
return((IDataTransform)transformed);
}
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 <OneHotEncodingEstimator.ColumnInfo>();
foreach (var column in args.Column)
{
var col = new OneHotEncodingEstimator.ColumnInfo(
column.Source ?? column.Name,
column.Name,
column.OutputKind ?? args.OutputKind,
column.MaxNumTerms ?? args.MaxNumTerms,
column.Sort ?? args.Sort,
column.Term ?? args.Term);
col.SetTerms(column.Terms ?? args.Terms);
columns.Add(col);
}
return(new OneHotEncodingEstimator(env, columns.ToArray(), args.DataFile, args.TermsColumn, args.Loader).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 OneHotEncodingEstimator.ColumnInfo[toOutput.Length];
Action <TermTransform> onFit = null;
for (int i = 0; i < toOutput.Length; ++i)
{
var tcol = (ICategoricalCol)toOutput[i];
infos[i] = new OneHotEncodingEstimator.ColumnInfo(inputNames[tcol.Input], outputNames[toOutput[i]], (OneHotEncodingTransformer.OutputKind)tcol.Config.OutputKind,
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 OneHotEncodingEstimator(env, infos);
if (onFit != null)
{
est.WrapTermWithDelegate(onFit);
}
return(est);
}