public RowCursor(NgramHashTransform parent, IRowCursor input, bool[] active, FinderDecorator decorator = null)
: base(parent.Host, input)
{
Ch.AssertValue(parent);
Ch.Assert(active == null || active.Length == parent._bindings.ColumnCount);
Ch.AssertValueOrNull(decorator);
_bindings = parent._bindings;
_active = active;
_getters = new Delegate[_bindings.Infos.Length];
for (int iinfo = 0; iinfo < _bindings.Infos.Length; iinfo++)
{
if (IsIndexActive(iinfo))
{
_getters[iinfo] = parent.MakeGetter(Ch, Input, iinfo, decorator);
}
}
}
public InvertHashHelper(NgramHashTransform parent, string[][] friendlyNames, Func <int, bool> inputPred, int[] invertHashMaxCounts)
{
Contracts.AssertValue(parent);
Contracts.AssertValue(friendlyNames);
Contracts.Assert(friendlyNames.Length == parent._bindings.InfoCount);
Contracts.AssertValue(inputPred);
Contracts.AssertValue(invertHashMaxCounts);
Contracts.Assert(invertHashMaxCounts.Length == parent._bindings.InfoCount);
_parent = parent;
// One per iinfo (some may be null).
_iinfoToCollector = new InvertHashCollector <NGram> [_parent._bindings.InfoCount];
// One per source column (some may be null).
_srcTextGetters = new ValueMapper <uint, StringBuilder> [_parent.Source.Schema.ColumnCount];
_invertHashMaxCounts = invertHashMaxCounts;
for (int i = 0; i < _srcTextGetters.Length; ++i)
{
if (inputPred(i))
{
_srcTextGetters[i] = InvertHashUtils.GetSimpleMapper <uint>(_parent.Source.Schema, i);
}
}
_friendlyNames = friendlyNames;
}
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(SelectColumnsTransform.CreateDrop(h, view, tmpColNames.SelectMany(cols => cols).ToArray()));
}
public Bindings(ModelLoadContext ctx, ISchema schemaInput, NgramHashTransform parent)
: base(ctx, schemaInput, TestTypes)
{
Types = new VectorType[Infos.Length];
_parent = parent;
}
public Bindings(Arguments args, ISchema schemaInput, NgramHashTransform parent)
: base(args.Column, schemaInput, TestTypes)
{
Types = new VectorType[args.Column.Length];
_parent = parent;
}