public static CommonOutputs.TransformOutput TextToKey(IHostEnvironment env, TermTransform.Arguments input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("Term");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
var xf = new TermTransform(host, input, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModel(env, xf, input.Data), OutputData = xf
});
}
public 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));
return(CreateTransformCore(
args.OutputKind,
args.Column,
args.Column.Select(col => col.OutputKind).ToList(),
TermTransform.Create(h, args, args.Column, input),
h,
env));
}
/// <summary>
/// Re-apply constructor.
/// </summary>
private TermTransform(IHostEnvironment env, TermTransform transform, IDataView newSource)
: base(env, RegistrationName, transform, newSource, TestIsKnownDataKind)
{
Host.AssertNonEmpty(Infos);
Host.Assert(Infos.Length == transform.Infos.Length);
_textMetadata = transform._textMetadata;
_termMap = new BoundTermMap[Infos.Length];
for (int iinfo = 0; iinfo < Infos.Length; ++iinfo)
{
TermMap map = transform._termMap[iinfo].Map;
if (!map.ItemType.Equals(Infos[iinfo].TypeSrc.ItemType))
{
// Column with the same name, but different types.
throw Host.Except(
"For column '{0}', term map was trained on items of type '{1}' but being applied to type '{2}'",
Infos[iinfo].Name, map.ItemType, Infos[iinfo].TypeSrc.ItemType);
}
_termMap[iinfo] = map.Bind(this, iinfo);
}
_types = ComputeTypesAndMetadata();
}
public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input,
TermLoaderArguments termLoaderArgs = null)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
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 NgramHashExtractorArguments, a HashTransform using 31
// bits (to minimize collisions) is applied first, followed by an NgramHashTransform.
IDataView view = input;
List <TermTransform.Column> termCols = null;
if (termLoaderArgs != null)
{
termCols = new List <TermTransform.Column>();
}
var hashColumns = new List <HashTransformer.Column>();
var ngramHashColumns = new NgramHashTransform.Column[args.Column.Length];
var colCount = args.Column.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 = args.Column[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;
if (termLoaderArgs != null)
{
termCols.Add(
new TermTransform.Column
{
Name = tmpName,
Source = column.Source[isrc]
});
}
hashColumns.Add(
new HashTransformer.Column
{
Name = tmpName,
Source = termLoaderArgs == null ? column.Source[isrc] : tmpName,
HashBits = 30,
Seed = column.Seed,
Ordered = false,
InvertHash = column.InvertHash
});
}
ngramHashColumns[iinfo] =
new NgramHashTransform.Column
{
Name = column.Name,
Source = tmpColNames[iinfo],
AllLengths = column.AllLengths,
HashBits = column.HashBits,
NgramLength = column.NgramLength,
RehashUnigrams = false,
Seed = column.Seed,
SkipLength = column.SkipLength,
Ordered = column.Ordered,
InvertHash = column.InvertHash,
// REVIEW: This is an ugly internal hack to get around
// the problem that we want the *original* source names surfacing
// in the descriptions where appropriate, rather than _tmp000 and
// what have you. The alternative is we do something elaborate
// with metadata or something but I'm not sure that's better.
FriendlyNames = column.FriendlyNames
};
}
if (termLoaderArgs != null)
{
h.Assert(Utils.Size(termCols) == hashColumns.Count);
var termArgs =
new TermTransform.Arguments()
{
MaxNumTerms = int.MaxValue,
Terms = termLoaderArgs.Terms,
Term = termLoaderArgs.Term,
DataFile = termLoaderArgs.DataFile,
Loader = termLoaderArgs.Loader,
TermsColumn = termLoaderArgs.TermsColumn,
Sort = termLoaderArgs.Sort,
Column = termCols.ToArray()
};
view = TermTransform.Create(h, termArgs, view);
if (termLoaderArgs.DropUnknowns)
{
var naDropArgs = new NADropTransform.Arguments {
Column = new NADropTransform.Column[termCols.Count]
};
for (int iinfo = 0; iinfo < termCols.Count; iinfo++)
{
naDropArgs.Column[iinfo] =
new NADropTransform.Column {
Name = termCols[iinfo].Name, Source = termCols[iinfo].Name
};
}
view = new NADropTransform(h, naDropArgs, view);
}
}
// Args for the Hash function with multiple columns
var hashArgs =
new HashTransformer.Arguments
{
HashBits = 31,
Seed = args.Seed,
Ordered = false,
Column = hashColumns.ToArray(),
InvertHash = args.InvertHash
};
view = HashTransformer.Create(h, hashArgs, view);
// creating the NgramHash function
var ngramHashArgs =
new NgramHashTransform.Arguments
{
AllLengths = args.AllLengths,
HashBits = args.HashBits,
NgramLength = args.NgramLength,
SkipLength = args.SkipLength,
RehashUnigrams = false,
Ordered = args.Ordered,
Seed = args.Seed,
Column = ngramHashColumns,
InvertHash = args.InvertHash
};
view = new NgramHashTransform(h, ngramHashArgs, view);
return(new DropColumnsTransform(h, new DropColumnsTransform.Arguments()
{
Column = tmpColNames.SelectMany(cols => cols).ToArray()
}, view));
}
public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input,
TermLoaderArguments termLoaderArgs = null)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(args, nameof(args));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(args.Column) > 0, nameof(args.Column), "Columns must be specified");
IDataView view = input;
var termCols = new List <Column>();
var isTermCol = new bool[args.Column.Length];
for (int i = 0; i < args.Column.Length; i++)
{
var col = args.Column[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.GetColumnType(colId).ItemType.IsText)
{
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 ngram transform directly.
// This logic allows NgramExtractorTransform to handle both text and key input columns.
// Note: ngram transform handles the validation of the types natively (in case the types
// of args.column are not text nor keys).
if (termCols.Count > 0)
{
TermTransform.Arguments termArgs = null;
NADropTransform.Arguments naDropArgs = null;
if (termLoaderArgs != null)
{
termArgs =
new TermTransform.Arguments()
{
MaxNumTerms = int.MaxValue,
Terms = termLoaderArgs.Terms,
Term = termLoaderArgs.Term,
DataFile = termLoaderArgs.DataFile,
Loader = termLoaderArgs.Loader,
TermsColumn = termLoaderArgs.TermsColumn,
Sort = termLoaderArgs.Sort,
Column = new TermTransform.Column[termCols.Count]
};
if (termLoaderArgs.DropUnknowns)
{
naDropArgs = new NADropTransform.Arguments {
Column = new NADropTransform.Column[termCols.Count]
}
}
;
}
else
{
termArgs =
new TermTransform.Arguments()
{
MaxNumTerms = Utils.Size(args.MaxNumTerms) > 0 ? args.MaxNumTerms[0] : NgramTransform.Arguments.DefaultMaxTerms,
Column = new TermTransform.Column[termCols.Count]
};
}
for (int iinfo = 0; iinfo < termCols.Count; iinfo++)
{
var column = termCols[iinfo];
termArgs.Column[iinfo] =
new TermTransform.Column()
{
Name = column.Name,
Source = column.Source,
MaxNumTerms = Utils.Size(column.MaxNumTerms) > 0 ? column.MaxNumTerms[0] : default(int?)
};
if (naDropArgs != null)
{
naDropArgs.Column[iinfo] = new NADropTransform.Column {
Name = column.Name, Source = column.Name
}
}
;
}
view = new TermTransform(h, termArgs, view);
if (naDropArgs != null)
{
view = new NADropTransform(h, naDropArgs, view);
}
}
var ngramArgs =
new NgramTransform.Arguments()
{
MaxNumTerms = args.MaxNumTerms,
NgramLength = args.NgramLength,
SkipLength = args.SkipLength,
AllLengths = args.AllLengths,
Weighting = args.Weighting,
Column = new NgramTransform.Column[args.Column.Length]
};
for (int iinfo = 0; iinfo < args.Column.Length; iinfo++)
{
var column = args.Column[iinfo];
ngramArgs.Column[iinfo] =
new NgramTransform.Column()
{
Name = column.Name,
Source = isTermCol[iinfo] ? column.Name : column.Source,
AllLengths = column.AllLengths,
MaxNumTerms = column.MaxNumTerms,
NgramLength = column.NgramLength,
SkipLength = column.SkipLength,
Weighting = column.Weighting
};
}
return(new NgramTransform(h, ngramArgs, view));
}