public static CommonOutputs.TransformOutput PrepareClassificationLabel(IHostEnvironment env, ClassificationLabelInput input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("PrepareClassificationLabel");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
var labelCol = input.Data.Schema.GetColumnOrNull(input.LabelColumn);
if (!labelCol.HasValue)
{
throw host.ExceptSchemaMismatch(nameof(input), "Label", input.LabelColumn);
}
var labelType = labelCol.Value.Type;
if (labelType is KeyType || labelType is BoolType)
{
var nop = NopTransform.CreateIfNeeded(env, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModelImpl(env, nop, input.Data), OutputData = nop
});
}
var args = new ValueToKeyMappingTransformer.Arguments()
{
Column = new[]
{
new ValueToKeyMappingTransformer.Column()
{
Name = input.LabelColumn,
Source = input.LabelColumn,
TextKeyValues = input.TextKeyValues,
Sort = ValueToKeyMappingTransformer.SortOrder.Value
}
}
};
var xf = ValueToKeyMappingTransformer.Create(host, args, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModelImpl(env, xf, input.Data), OutputData = xf
});
}
public static CommonOutputs.TransformOutput PrepareClassificationLabel(IHostEnvironment env, ClassificationLabelInput input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("PrepareClassificationLabel");
host.CheckValue(input, nameof(input));
EntryPointUtils.CheckInputArgs(host, input);
int labelCol;
if (!input.Data.Schema.TryGetColumnIndex(input.LabelColumn, out labelCol))
{
throw host.Except($"Column '{input.LabelColumn}' not found.");
}
var labelType = input.Data.Schema[labelCol].Type;
if (labelType.IsKey || labelType.IsBool)
{
var nop = NopTransform.CreateIfNeeded(env, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModelImpl(env, nop, input.Data), OutputData = nop
});
}
var args = new ValueToKeyMappingTransformer.Arguments()
{
Column = new[]
{
new ValueToKeyMappingTransformer.Column()
{
Name = input.LabelColumn,
Source = input.LabelColumn,
TextKeyValues = input.TextKeyValues,
Sort = ValueToKeyMappingTransformer.SortOrder.Value
}
}
};
var xf = ValueToKeyMappingTransformer.Create(host, args, input.Data);
return(new CommonOutputs.TransformOutput {
Model = new TransformModelImpl(env, xf, input.Data), OutputData = xf
});
}
public static CommonOutputs.TransformOutput TermTransform(IHostEnvironment env, ValueToKeyMappingTransformer.Arguments input)
{
var h = EntryPointUtils.CheckArgsAndCreateHost(env, "TermTransform", input);
var xf = ValueToKeyMappingTransformer.Create(h, input, input.Data);
return(new CommonOutputs.TransformOutput()
{
Model = new TransformModelImpl(h, xf, input.Data),
OutputData = xf
});
}
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 <ValueToKeyMappingTransformer.Column> termCols = null;
if (termLoaderArgs != null)
{
termCols = new List <ValueToKeyMappingTransformer.Column>();
}
var hashColumns = new List <HashingTransformer.Column>();
var ngramHashColumns = new NgramHashingTransformer.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 ValueToKeyMappingTransformer.Column
{
Name = tmpName,
Source = column.Source[isrc]
});
}
hashColumns.Add(
new HashingTransformer.Column
{
Name = tmpName,
Source = termLoaderArgs == null ? column.Source[isrc] : tmpName,
HashBits = 30,
Seed = column.Seed,
Ordered = false,
InvertHash = column.InvertHash
});
}
ngramHashColumns[iinfo] =
new NgramHashingTransformer.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 ValueToKeyMappingTransformer.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 = ValueToKeyMappingTransformer.Create(h, termArgs, view);
if (termLoaderArgs.DropUnknowns)
{
var missingDropColumns = new (string input, string output)[termCols.Count];
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)
{
ValueToKeyMappingTransformer.Arguments termArgs = null;
string[] missingDropColumns = null;
if (termLoaderArgs != null)
{
termArgs =
new ValueToKeyMappingTransformer.Arguments()
{
MaxNumTerms = int.MaxValue,
Terms = termLoaderArgs.Terms,
Term = termLoaderArgs.Term,
DataFile = termLoaderArgs.DataFile,
Loader = termLoaderArgs.Loader,
TermsColumn = termLoaderArgs.TermsColumn,
Sort = termLoaderArgs.Sort,
Column = new ValueToKeyMappingTransformer.Column[termCols.Count]
};
if (termLoaderArgs.DropUnknowns)
{
missingDropColumns = new string[termCols.Count];
}
}
else
{
termArgs =
new ValueToKeyMappingTransformer.Arguments()
{
MaxNumTerms = Utils.Size(args.MaxNumTerms) > 0 ? args.MaxNumTerms[0] : NgramExtractingEstimator.Defaults.MaxNumTerms,
Column = new ValueToKeyMappingTransformer.Column[termCols.Count]
};
}
for (int iinfo = 0; iinfo < termCols.Count; iinfo++)
{
var column = termCols[iinfo];
termArgs.Column[iinfo] =
new ValueToKeyMappingTransformer.Column()
{
Name = column.Name,
Source = column.Source,
MaxNumTerms = Utils.Size(column.MaxNumTerms) > 0 ? column.MaxNumTerms[0] : default(int?)
};
if (missingDropColumns != null)
{
missingDropColumns[iinfo] = column.Name;
}
}
view = ValueToKeyMappingTransformer.Create(h, termArgs, view);
if (missingDropColumns != null)
{
view = new MissingValueDroppingTransformer(h, missingDropColumns.Select(x => (x, x)).ToArray()).Transform(view);
}
}
var ngramColumns = new NgramExtractingTransformer.ColumnInfo[args.Column.Length];
for (int iinfo = 0; iinfo < args.Column.Length; iinfo++)
{
var column = args.Column[iinfo];
ngramColumns[iinfo] = new NgramExtractingTransformer.ColumnInfo(isTermCol[iinfo] ? column.Name : column.Source, column.Name,
column.NgramLength ?? args.NgramLength,
column.SkipLength ?? args.SkipLength,
column.AllLengths ?? args.AllLengths,
column.Weighting ?? args.Weighting,
column.MaxNumTerms ?? args.MaxNumTerms
);
}
return(new NgramExtractingEstimator(env, ngramColumns).Fit(view).Transform(view) as IDataTransform);
}
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 <ValueToKeyMappingTransformer.Column> termCols = null;
if (termLoaderArgs != null)
{
termCols = new List <ValueToKeyMappingTransformer.Column>();
}
var hashColumns = new List <HashingTransformer.ColumnInfo>();
var ngramHashColumns = new NgramHashingTransformer.ColumnInfo[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 ValueToKeyMappingTransformer.Column
{
Name = tmpName,
Source = column.Source[isrc]
});
}
hashColumns.Add(new HashingTransformer.ColumnInfo(termLoaderArgs == null ? column.Source[isrc] : tmpName,
tmpName, 30, column.Seed ?? args.Seed, false, column.InvertHash ?? args.InvertHash));
}
ngramHashColumns[iinfo] =
new NgramHashingTransformer.ColumnInfo(tmpColNames[iinfo], column.Name,
column.NgramLength ?? args.NgramLength,
column.SkipLength ?? args.SkipLength,
column.AllLengths ?? args.AllLengths,
column.HashBits ?? args.HashBits,
column.Seed ?? args.Seed,
column.Ordered ?? args.Ordered,
column.InvertHash ?? args.InvertHash);
ngramHashColumns[iinfo].FriendlyNames = column.FriendlyNames;
}
if (termLoaderArgs != null)
{
h.Assert(Utils.Size(termCols) == hashColumns.Count);
var termArgs =
new ValueToKeyMappingTransformer.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 = ValueToKeyMappingTransformer.Create(h, termArgs, view);
if (termLoaderArgs.DropUnknowns)
{
var missingDropColumns = new (string input, string output)[termCols.Count];