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);
}
public static CommonOutputs.TransformOutput TextToKey(IHostEnvironment env, ValueToKeyMappingTransformer.Arguments input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("Term");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
var xf = ValueToKeyMappingTransformer.Create(host, input, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModelImpl(env, xf, input.Data), OutputData = xf
});
}