internal static ITransformer Create(IHostEnvironment env, Options options, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
var chain = new TransformerChain <ITransformer>();
// To each input column to the NgramHashExtractorArguments, a HashTransform using 31
// bits (to minimize collisions) is applied first, followed by an NgramHashTransform.
var hashColumns = new List <HashingEstimator.ColumnOptions>();
var ngramHashColumns = new NgramHashingEstimator.ColumnOptions[options.Columns.Length];
var colCount = options.Columns.Length;
// The NGramHashExtractor has a ManyToOne column type. To avoid stepping over the source
// column name when a 'name' destination column name was specified, we use temporary column names.
string[][] tmpColNames = new string[colCount][];
for (int iinfo = 0; iinfo < colCount; iinfo++)
{
var column = options.Columns[iinfo];
h.CheckUserArg(!string.IsNullOrWhiteSpace(column.Name), nameof(column.Name));
h.CheckUserArg(Utils.Size(column.Source) > 0 &&
column.Source.All(src => !string.IsNullOrWhiteSpace(src)), nameof(column.Source));
int srcCount = column.Source.Length;
tmpColNames[iinfo] = new string[srcCount];
for (int isrc = 0; isrc < srcCount; isrc++)
{
var tmpName = input.Schema.GetTempColumnName(column.Source[isrc]);
tmpColNames[iinfo][isrc] = tmpName;
hashColumns.Add(new HashingEstimator.ColumnOptions(tmpName, column.Source[isrc],
30, column.Seed ?? options.Seed, false, column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts));
}
ngramHashColumns[iinfo] =
new NgramHashingEstimator.ColumnOptions(column.Name, tmpColNames[iinfo],
column.NgramLength ?? options.NgramLength,
column.SkipLength ?? options.SkipLength,
column.UseAllLengths ?? options.UseAllLengths,
column.NumberOfBits ?? options.NumberOfBits,
column.Seed ?? options.Seed,
column.Ordered ?? options.Ordered,
column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts);
ngramHashColumns[iinfo].FriendlyNames = column.FriendlyNames;
}
var hashing = new HashingEstimator(h, hashColumns.ToArray()).Fit(input);
return(chain.Append(hashing)
.Append(new NgramHashingEstimator(h, ngramHashColumns).Fit(hashing.Transform(input)))
.Append(new ColumnSelectingTransformer(h, null, tmpColNames.SelectMany(cols => cols).ToArray())));
}
internal static ITransformer Create(IHostEnvironment env, Options options, IDataView input, TermLoaderArguments termLoaderArgs = null)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
var chain = new TransformerChain <ITransformer>();
var termCols = new List <Column>();
var isTermCol = new bool[options.Columns.Length];
for (int i = 0; i < options.Columns.Length; i++)
{
var col = options.Columns[i];
h.CheckNonWhiteSpace(col.Name, nameof(col.Name));
h.CheckNonWhiteSpace(col.Source, nameof(col.Source));
int colId;
if (input.Schema.TryGetColumnIndex(col.Source, out colId) &&
input.Schema[colId].Type.GetItemType() is TextDataViewType)
{
termCols.Add(col);
isTermCol[i] = true;
}
}
// If the column types of args.column are text, apply term transform to convert them to keys.
// Otherwise, skip term transform and apply n-gram transform directly.
// This logic allows NgramExtractorTransform to handle both text and key input columns.
// Note: n-gram transform handles the validation of the types natively (in case the types
// of args.column are not text nor keys).
if (termCols.Count > 0)
{
var columnOptions = new List <ValueToKeyMappingEstimator.ColumnOptionsBase>();
string[] missingDropColumns = termLoaderArgs != null && termLoaderArgs.DropUnknowns ? new string[termCols.Count] : null;
for (int iinfo = 0; iinfo < termCols.Count; iinfo++)
{
var column = termCols[iinfo];
var colOptions = new ValueToKeyMappingEstimator.ColumnOptions(
column.Name,
column.Source,
maximumNumberOfKeys: Utils.Size(column.MaxNumTerms) > 0 ? column.MaxNumTerms[0] :
Utils.Size(options.MaxNumTerms) > 0 ? options.MaxNumTerms[0] :
termLoaderArgs == null ? NgramExtractingEstimator.Defaults.MaximumNgramsCount : int.MaxValue,
keyOrdinality: termLoaderArgs?.Sort ?? ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence);
if (termLoaderArgs != null)
{
colOptions.Key = termLoaderArgs.Term;
colOptions.Keys = termLoaderArgs.Terms;
}
columnOptions.Add(colOptions);
if (missingDropColumns != null)
{
missingDropColumns[iinfo] = column.Name;
}
}
IDataView keyData = null;
if (termLoaderArgs?.DataFile != null)
{
using (var ch = env.Start("Create key data view"))
keyData = ValueToKeyMappingTransformer.GetKeyDataViewOrNull(env, ch, termLoaderArgs.DataFile, termLoaderArgs.TermsColumn, termLoaderArgs.Loader, out var autoConvert);
}
chain = chain.Append <ITransformer>(new ValueToKeyMappingEstimator(h, columnOptions.ToArray(), keyData).Fit(input));
if (missingDropColumns != null)
{
chain = chain.Append <ITransformer>(new MissingValueDroppingTransformer(h, missingDropColumns.Select(x => (x, x)).ToArray()));
}
}
var ngramColumns = new NgramExtractingEstimator.ColumnOptions[options.Columns.Length];
for (int iinfo = 0; iinfo < options.Columns.Length; iinfo++)
{
var column = options.Columns[iinfo];
ngramColumns[iinfo] = new NgramExtractingEstimator.ColumnOptions(column.Name,
column.NgramLength ?? options.NgramLength,
column.SkipLength ?? options.SkipLength,
column.UseAllLengths ?? options.UseAllLengths,
column.Weighting ?? options.Weighting,
column.MaxNumTerms ?? options.MaxNumTerms,
isTermCol[iinfo] ? column.Name : column.Source
);
}
input = chain.Transform(input);
return(chain.Append <ITransformer>(new NgramExtractingEstimator(env, ngramColumns).Fit(input)));
}