diff --git a/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj b/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj index 8aa272922c..4aebfb6b91 100644 --- a/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj +++ b/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj @@ -4,6 +4,7 @@ netstandard2.0 Microsoft.ML CORECLR + ..\..\bin\obj\AnyCPU.Debug\Microsoft.ML.Transforms diff --git a/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt b/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt index 21ab890d78..57c93978ab 100644 Binary files a/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt and b/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt differ diff --git a/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs b/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs index 96bf44b4c2..4ce69cf7db 100644 --- a/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs +++ b/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs @@ -90,7 +90,10 @@ public enum Language Polish = 12, Czech = 13, Arabic = 14, - Japanese = 15 + Japanese = 15, + + [HideEnumValue] + Norwegian_Bokmal_v1 = 256 } public sealed class Column : OneToOneColumn @@ -198,6 +201,11 @@ public ColInfoEx(ModelLoadContext ctx, ISchema input) // int: the id of languages column name Lang = (Language)ctx.Reader.ReadInt32(); Contracts.CheckDecode(Enum.IsDefined(typeof(Language), Lang)); + if(Lang == Language.Norwegian_Bokmal + && ctx.Header.ModelVerWritten == 0x00010001) + { + Lang = Language.Norwegian_Bokmal_v1; + } _langsColName = ctx.LoadStringOrNull(); if (_langsColName != null) { @@ -229,8 +237,8 @@ private static VersionInfo GetVersionInfo() { return new VersionInfo( modelSignature: "STOPWRDR", - verWrittenCur: 0x00010001, // Initial - verReadableCur: 0x00010001, + verWrittenCur: 0x00010002, // Initial + verReadableCur: 0x00010002, verWeCanReadBack: 0x00010001, loaderSignature: LoaderSignature); }