public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register("CategoricalHash");
using (var ch = h.Start("CategoricalHash"))
{
h.CheckValue(args, nameof(args));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(args.Column) > 0, nameof(args.Column), "Columns must be specified");
if (args.HashBits < 1 || args.HashBits >= NumBitsLim)
{
throw h.ExceptUserArg(nameof(args.HashBits), "Number of bits must be between 1 and {0}", NumBitsLim - 1);
}
// creating the Hash function
var hashArgs = new HashTransform.Arguments
{
HashBits = args.HashBits,
Seed = args.Seed,
Ordered = args.Ordered,
InvertHash = args.InvertHash,
Column = new HashTransform.Column[args.Column.Length]
};
for (int i = 0; i < args.Column.Length; i++)
{
var column = args.Column[i];
if (!column.TrySanitize())
{
throw h.ExceptUserArg(nameof(Column.Name));
}
h.Assert(!string.IsNullOrWhiteSpace(column.Name));
h.Assert(!string.IsNullOrWhiteSpace(column.Source));
hashArgs.Column[i] = new HashTransform.Column
{
HashBits = column.HashBits,
Seed = column.Seed,
Ordered = column.Ordered,
Name = column.Name,
Source = column.Source,
InvertHash = column.InvertHash,
};
}
return(CategoricalTransform.CreateTransformCore(
args.OutputKind, args.Column,
args.Column.Select(col => col.OutputKind).ToList(),
new HashTransform(h, hashArgs, input),
h,
env,
args));
}
}
public static CommonOutputs.TransformOutput CatTransformDict(IHostEnvironment env, CategoricalTransform.Arguments input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("CatTransformDict");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
var xf = CategoricalTransform.Create(host, input, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModel(env, xf, input.Data), OutputData = xf
});
}