internal static ITransformer CreateTransformer(IHostEnvironment env, Options options, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(RegistrationName);
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
// To each input column to the WordHashBagTransform, a tokenize transform is applied,
// followed by applying WordHashVectorizeTransform.
// Since WordHashBagTransform is a many-to-one column transform, for each
// WordHashBagTransform.Column we may need to define multiple tokenize transform columns.
// NgramHashExtractorTransform may need to define an identical number of HashTransform.Columns.
// The intermediate columns are dropped at the end of using a DropColumnsTransform.
IDataView view = input;
var uniqueSourceNames = NgramExtractionUtils.GenerateUniqueSourceNames(h, options.Columns, view.Schema);
Contracts.Assert(uniqueSourceNames.Length == options.Columns.Length);
var tokenizeColumns = new List <WordTokenizingEstimator.ColumnOptions>();
var extractorCols = new NgramHashExtractingTransformer.Column[options.Columns.Length];
var colCount = options.Columns.Length;
List <string> tmpColNames = new List <string>();
for (int iinfo = 0; iinfo < colCount; iinfo++)
{
var column = options.Columns[iinfo];
int srcCount = column.Source.Length;
var curTmpNames = new string[srcCount];
Contracts.Assert(uniqueSourceNames[iinfo].Length == options.Columns[iinfo].Source.Length);
for (int isrc = 0; isrc < srcCount; isrc++)
{
tokenizeColumns.Add(new WordTokenizingEstimator.ColumnOptions(curTmpNames[isrc] = uniqueSourceNames[iinfo][isrc], options.Columns[iinfo].Source[isrc]));
}
tmpColNames.AddRange(curTmpNames);
extractorCols[iinfo] =
new NgramHashExtractingTransformer.Column
{
Name = column.Name,
Source = curTmpNames,
NumberOfBits = column.NumberOfBits,
NgramLength = column.NgramLength,
Seed = column.Seed,
SkipLength = column.SkipLength,
Ordered = column.Ordered,
MaximumNumberOfInverts = column.MaximumNumberOfInverts,
FriendlyNames = options.Columns[iinfo].Source,
UseAllLengths = column.UseAllLengths
};
}
ITransformer t1 = new WordTokenizingEstimator(env, tokenizeColumns.ToArray()).Fit(view);
var featurizeArgs =
new NgramHashExtractingTransformer.Options
{
UseAllLengths = options.UseAllLengths,
NumberOfBits = options.NumberOfBits,
NgramLength = options.NgramLength,
SkipLength = options.SkipLength,
Ordered = options.Ordered,
Seed = options.Seed,
Columns = extractorCols.ToArray(),
MaximumNumberOfInverts = options.MaximumNumberOfInverts
};
view = t1.Transform(view);
ITransformer t2 = NgramHashExtractingTransformer.Create(h, featurizeArgs, view);
// Since we added columns with new names, we need to explicitly drop them before we return the IDataTransform.
ITransformer t3 = new ColumnSelectingTransformer(env, null, tmpColNames.ToArray());
return(new TransformerChain <ITransformer>(new[] { t1, t2, t3 }));
}
public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(RegistrationName);
h.CheckValue(args, nameof(args));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(args.Column) > 0, nameof(args.Column), "Columns must be specified");
// To each input column to the WordHashBagTransform, a tokenize transform is applied,
// followed by applying WordHashVectorizeTransform.
// Since WordHashBagTransform is a many-to-one column transform, for each
// WordHashBagTransform.Column we may need to define multiple tokenize transform columns.
// NgramHashExtractorTransform may need to define an identical number of HashTransform.Columns.
// The intermediate columns are dropped at the end of using a DropColumnsTransform.
IDataView view = input;
var uniqueSourceNames = NgramExtractionUtils.GenerateUniqueSourceNames(h, args.Column, view.Schema);
Contracts.Assert(uniqueSourceNames.Length == args.Column.Length);
var tokenizeColumns = new List <WordTokenizingTransformer.ColumnInfo>();
var extractorCols = new NgramHashExtractingTransformer.Column[args.Column.Length];
var colCount = args.Column.Length;
List <string> tmpColNames = new List <string>();
for (int iinfo = 0; iinfo < colCount; iinfo++)
{
var column = args.Column[iinfo];
int srcCount = column.Source.Length;
var curTmpNames = new string[srcCount];
Contracts.Assert(uniqueSourceNames[iinfo].Length == args.Column[iinfo].Source.Length);
for (int isrc = 0; isrc < srcCount; isrc++)
{
tokenizeColumns.Add(new WordTokenizingTransformer.ColumnInfo(args.Column[iinfo].Source[isrc], curTmpNames[isrc] = uniqueSourceNames[iinfo][isrc]));
}
tmpColNames.AddRange(curTmpNames);
extractorCols[iinfo] =
new NgramHashExtractingTransformer.Column
{
Name = column.Name,
Source = curTmpNames,
HashBits = column.HashBits,
NgramLength = column.NgramLength,
Seed = column.Seed,
SkipLength = column.SkipLength,
Ordered = column.Ordered,
InvertHash = column.InvertHash,
FriendlyNames = args.Column[iinfo].Source,
AllLengths = column.AllLengths
};
}
view = new WordTokenizingEstimator(env, tokenizeColumns.ToArray()).Fit(view).Transform(view);
var featurizeArgs =
new NgramHashExtractingTransformer.Arguments
{
AllLengths = args.AllLengths,
HashBits = args.HashBits,
NgramLength = args.NgramLength,
SkipLength = args.SkipLength,
Ordered = args.Ordered,
Seed = args.Seed,
Column = extractorCols.ToArray(),
InvertHash = args.InvertHash
};
view = NgramHashExtractingTransformer.Create(h, featurizeArgs, view);
// Since we added columns with new names, we need to explicitly drop them before we return the IDataTransform.
return(ColumnSelectingTransformer.CreateDrop(h, view, tmpColNames.ToArray()));
}
