public void ValueToKeyFromSideData()
{
// In this case, whatever the value of the input, the term mapping should come from the optional side data if specified.
var data = new[] { new TestStringClass()
{
A = "Stay"
}, new TestStringClass()
{
A = "awhile and listen"
} };
var mlContext = new MLContext();
var dataView = mlContext.Data.LoadFromEnumerable(data);
var sideDataBuilder = new ArrayDataViewBuilder(mlContext);
sideDataBuilder.AddColumn("Hello", "hello", "my", "friend");
var sideData = sideDataBuilder.GetDataView();
// For some reason the column info is on the *transformer*, not the estimator. Already tracked as issue #1760.
var ci = new ValueToKeyMappingEstimator.ColumnOptions("CatA", "A");
var pipe = mlContext.Transforms.Conversion.MapValueToKey(new[] { ci }, sideData);
var output = pipe.Fit(dataView).Transform(dataView);
VBuffer <ReadOnlyMemory <char> > slotNames = default;
output.Schema["CatA"].Annotations.GetValue(AnnotationUtils.Kinds.KeyValues, ref slotNames);
Assert.Equal(3, slotNames.Length);
Assert.Equal("hello", slotNames.GetItemOrDefault(0).ToString());
Assert.Equal("my", slotNames.GetItemOrDefault(1).ToString());
Assert.Equal("friend", slotNames.GetItemOrDefault(2).ToString());
Done();
}
internal static IEstimator <ITransformer> CreateEstimator(IHostEnvironment env, Options options, SchemaShape inputSchema, TermLoaderArguments termLoaderArgs = null)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(options, nameof(options));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
var chain = new EstimatorChain <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));
if (inputSchema.TryFindColumn(col.Source, out var colShape) &&
colShape.ItemType 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));
if (missingDropColumns != null)
{
chain = chain.Append <ITransformer>(new MissingValueDroppingEstimator(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
);
}
return(chain.Append <ITransformer>(new NgramExtractingEstimator(env, ngramColumns)));
}
