/// <summary>
/// Return a dataset with non-selected features zeroed out.
/// </summary>
public static RoleMappedData SelectFeatures(IHost host, RoleMappedData data, BitArray features)
{
Contracts.AssertValue(host);
Contracts.AssertValue(data);
Contracts.Assert(data.Schema.Feature.HasValue);
Contracts.AssertValue(features);
var featCol = data.Schema.Feature.Value;
var type = featCol.Type;
var typeVectorSize = type.GetVectorSize();
Contracts.Assert(features.Length == typeVectorSize);
int card = Utils.GetCardinality(features);
if (card == typeVectorSize)
{
return(data);
}
// REVIEW: This doesn't preserve metadata on the features column. Should it?
var name = featCol.Name;
var view = LambdaColumnMapper.Create(
host, "FeatureSelector", data.Data, name, name, type, type,
(in VBuffer <Single> src, ref VBuffer <Single> dst) => SelectFeatures(in src, features, card, ref dst));
var res = new RoleMappedData(view, data.Schema.GetColumnRoleNames());
return(res);
}
/// <summary>
/// Create the internal transform (not serialized in the zip file).
/// </summary>
private IDataTransform CreateTemplatedTransform()
{
IDataView view = Source;
var schema = _input.Schema;
int index;
for (int i = 0; i < _args.columns.Length; ++i)
{
if (!schema.TryGetColumnIndex(_args.columns[i].Source, out index))
{
throw _host.Except("Unable to find '{0}'", _args.columns[i].Source);
}
var typeCol = schema.GetColumnType(index);
if (typeCol.IsVector())
{
throw _host.Except("Expected a number as input.");
}
switch (typeCol.RawKind())
{
case DataKind.R4:
view = new PassThroughTransform(_host, new PassThroughTransform.Arguments(),
LambdaColumnMapper.Create(_host, "R42R4", view,
_args.columns[i].Source, _args.columns[i].Name,
NumberType.R4, NumberType.R4,
(in float src, ref float dst) => { dst = src; }));
break;
protected IDataView MapLabelsCore <T>(ColumnType type, RefPredicate <T> equalsTarget, RoleMappedData data, string dstName)
{
Host.AssertValue(type);
Host.Assert(type.RawType == typeof(T));
Host.AssertValue(equalsTarget);
Host.AssertValue(data);
Host.AssertValue(data.Schema.Label);
Host.AssertNonWhiteSpace(dstName);
var lab = data.Schema.Label;
RefPredicate <T> isMissing;
if (!Args.ImputeMissingLabelsAsNegative && Conversions.Instance.TryGetIsNAPredicate(type, out isMissing))
{
return(LambdaColumnMapper.Create(Host, "Label mapper", data.Data,
lab.Name, dstName, type, NumberType.Float,
(ref T src, ref Float dst) =>
dst = equalsTarget(ref src) ? 1 : (isMissing(ref src) ? Float.NaN : default(Float))));
}
return(LambdaColumnMapper.Create(Host, "Label mapper", data.Data,
lab.Name, dstName, type, NumberType.Float,
(ref T src, ref Float dst) =>
dst = equalsTarget(ref src) ? 1 : default(Float)));
}
private static IDataView AppendFloatMapper <TInput>(IHostEnvironment env, IChannel ch, IDataView input,
string col, KeyDataViewType type, int seed)
{
// Any key is convertible to ulong, so rather than add special case handling for all possible
// key-types we just upfront convert it to the most general type (ulong) and work from there.
KeyDataViewType dstType = new KeyDataViewType(typeof(ulong), type.Count);
bool identity;
var converter = Conversions.Instance.GetStandardConversion <TInput, ulong>(type, dstType, out identity);
var isNa = Conversions.Instance.GetIsNAPredicate <TInput>(type);
ValueMapper <TInput, Single> mapper;
if (seed == 0)
{
mapper =
(in TInput src, ref Single dst) =>
{
//Attention: This method is called from multiple threads.
//Do not move the temp variable outside this method.
//If you do, the variable is shared between the threads and results in a race condition.
ulong temp = 0;
if (isNa(in src))
{
dst = Single.NaN;
return;
}
converter(in src, ref temp);
dst = (Single)temp - 1;
};
}
else
{
ch.Check(type.Count > 0, "Label must be of known cardinality.");
int[] permutation = Utils.GetRandomPermutation(RandomUtils.Create(seed), type.GetCountAsInt32(env));
mapper =
(in TInput src, ref Single dst) =>
{
//Attention: This method is called from multiple threads.
//Do not move the temp variable outside this method.
//If you do, the variable is shared between the threads and results in a race condition.
ulong temp = 0;
if (isNa(in src))
{
dst = Single.NaN;
return;
}
converter(in src, ref temp);
dst = (Single)permutation[(int)(temp - 1)];
};
}
return(LambdaColumnMapper.Create(env, "Key to Float Mapper", input, col, col, type, NumberDataViewType.Single, mapper));
}
private static IDataView AppendFloatMapper <TInput>(IHostEnvironment env, IChannel ch, IDataView input,
string col, KeyType type, int seed)
{
// Any key is convertible to ulong, so rather than add special case handling for all possible
// key-types we just upfront convert it to the most general type (ulong) and work from there.
KeyType dstType = new KeyType(DataKind.U8, type.Min, type.Count, type.Contiguous);
bool identity;
var converter = Conversions.Instance.GetStandardConversion <TInput, ulong>(type, dstType, out identity);
var isNa = Conversions.Instance.GetIsNAPredicate <TInput>(type);
ulong temp = 0;
ValueMapper <TInput, Single> mapper;
if (seed == 0)
{
mapper =
(in TInput src, ref Single dst) =>
{
if (isNa(in src))
{
dst = Single.NaN;
return;
}
converter(in src, ref temp);
dst = (Single)(temp - 1);
};
}
else
{
ch.Check(type.Count > 0, "Label must be of known cardinality.");
int[] permutation = Utils.GetRandomPermutation(RandomUtils.Create(seed), type.Count);
mapper =
(in TInput src, ref Single dst) =>
{
if (isNa(in src))
{
dst = Single.NaN;
return;
}
converter(in src, ref temp);
dst = (Single)permutation[(int)(temp - 1)];
};
}
return(LambdaColumnMapper.Create(env, "Key to Float Mapper", input, col, col, type, NumberType.Float, mapper));
}
private protected IDataView MapLabelsCore<T>(DataViewType type, InPredicate<T> equalsTarget, RoleMappedData data)
{
Host.AssertValue(type);
Host.Assert(type.RawType == typeof(T));
Host.AssertValue(equalsTarget);
Host.AssertValue(data);
Host.Assert(data.Schema.Label.HasValue);
var label = data.Schema.Label.Value;
IDataView dataView = data.Data;
if (!Args.ImputeMissingLabelsAsNegative)
dataView = new NAFilter(Host, data.Data, false, label.Name);
return LambdaColumnMapper.Create(Host, "Label mapper", data.Data,
label.Name, label.Name, type, BooleanDataViewType.Instance,
(in T src, ref bool dst) =>
dst = equalsTarget(in src) ? true : false);
}
private IDataView MapLabels(RoleMappedData data, int cls, out string dstName, IChannel ch)
{
var lab = data.Schema.Label.Value;
Host.Assert(!data.Schema.Schema[lab.Index].IsHidden);
Host.Assert(lab.Type.GetKeyCount() > 0 || lab.Type == NumberDataViewType.Single || lab.Type == NumberDataViewType.Double);
// Get the destination label column name.
dstName = data.Schema.Schema.GetTempColumnName();
// Key values are 1-based.
if (lab.Type.GetKeyCount() > 0)
{
uint key = (uint)(cls + 1);
if (_args.downsampling > 0)
{
return(CreateTrainingView(data, key, 1f, -1f, 0f, NumberDataViewType.UInt32, NumberDataViewType.Single, ch));
}
else
{
return(LambdaColumnMapper.Create(Host, "LabelColumnMapper in oOVA (1)", FilterNA(data.Data, lab.Name),
lab.Name, dstName, NumberDataViewType.UInt32, NumberDataViewType.Single,
(in uint src, ref float dst) => { dst = src == key ? 1 : default(float); }));
private protected IDataView MapLabelsCore<T>(ColumnType type, InPredicate<T> equalsTarget, RoleMappedData data)
{
Host.AssertValue(type);
Host.Assert(type.RawType == typeof(T));
Host.AssertValue(equalsTarget);
Host.AssertValue(data);
Host.Assert(data.Schema.Label.HasValue);
var lab = data.Schema.Label.Value;
InPredicate<T> isMissing;
if (!Args.ImputeMissingLabelsAsNegative && Conversions.Instance.TryGetIsNAPredicate(type, out isMissing))
{
return LambdaColumnMapper.Create(Host, "Label mapper", data.Data,
lab.Name, lab.Name, type, NumberType.Float,
(in T src, ref float dst) =>
dst = equalsTarget(in src) ? 1 : (isMissing(in src) ? float.NaN : default(float)));
}
return LambdaColumnMapper.Create(Host, "Label mapper", data.Data,
lab.Name, lab.Name, type, NumberType.Float,
(in T src, ref float dst) =>
dst = equalsTarget(in src) ? 1 : default(float));
}
/// <summary>
/// Create the internal transform (not serialized in the zip file).
/// </summary>
private IDataTransform CreateTemplatedTransform()
{
IDataView view = Source;
var schema = _input.Schema;
int index;
for (int i = 0; i < _args.columns.Length; ++i)
{
index = SchemaHelper.GetColumnIndex(schema, _args.columns[i].Source);
var typeCol = schema[index].Type;
if (typeCol.IsVector())
{
throw _host.Except("Expected a number as input.");
}
switch (typeCol.RawKind())
{
case DataKind.Single:
view = new PassThroughTransform(_host, new PassThroughTransform.Arguments(),
LambdaColumnMapper.Create(_host, "R42R4", view,
_args.columns[i].Source, _args.columns[i].Name,
NumberDataViewType.Single, NumberDataViewType.Single,
(in float src, ref float dst) => { dst = src; }));
break;
IDataTransform AppendToPipeline(IDataView input)
{
IDataView current = input;
if (_shuffleInput)
{
var args1 = new RowShufflingTransformer.Arguments()
{
ForceShuffle = false,
ForceShuffleSeed = _seedShuffle,
PoolRows = _poolRows,
PoolOnly = false,
};
current = new RowShufflingTransformer(Host, args1, current);
}
// We generate a random number.
var columnName = current.Schema.GetTempColumnName();
var args2 = new GenerateNumberTransform.Arguments()
{
Column = new GenerateNumberTransform.Column[] { new GenerateNumberTransform.Column()
{
Name = columnName
} },
Seed = _seed ?? 42
};
IDataTransform currentTr = new GenerateNumberTransform(Host, args2, current);
// We convert this random number into a part.
var cRatios = new float[_ratios.Length];
cRatios[0] = 0;
for (int i = 1; i < _ratios.Length; ++i)
{
cRatios[i] = cRatios[i - 1] + _ratios[i - 1];
}
ValueMapper <float, int> mapper = (in float src, ref int dst) =>
{
for (int i = cRatios.Length - 1; i > 0; --i)
{
if (src >= cRatios[i])
{
dst = i;
return;
}
}
dst = 0;
};
// Get location of columnName
int index;
currentTr.Schema.TryGetColumnIndex(columnName, out index);
var ct = currentTr.Schema.GetColumnType(index);
var view = LambdaColumnMapper.Create(Host, "Key to part mapper", currentTr,
columnName, _newColumn, ct, NumberType.I4, mapper);
// We cache the result to avoid the pipeline to change the random number.
var args3 = new ExtendedCacheTransform.Arguments()
{
inDataFrame = string.IsNullOrEmpty(_cacheFile),
numTheads = _numThreads,
cacheFile = _cacheFile,
reuse = _reuse,
};
currentTr = new ExtendedCacheTransform(Host, args3, view);
// Removing the temporary column.
var finalTr = ColumnSelectingTransformer.CreateDrop(Host, currentTr, new string[] { columnName });
var taggedViews = new List <Tuple <string, ITaggedDataView> >();
// filenames
if (_filenames != null || _tags != null)
{
int nbf = _filenames == null ? 0 : _filenames.Length;
if (nbf > 0 && nbf != _ratios.Length)
{
throw Host.Except("Differen number of filenames and ratios.");
}
int nbt = _tags == null ? 0 : _tags.Length;
if (nbt > 0 && nbt != _ratios.Length)
{
throw Host.Except("Differen number of filenames and ratios.");
}
int nb = Math.Max(nbf, nbt);
using (var ch = Host.Start("Split the datasets and stores each part."))
{
for (int i = 0; i < nb; ++i)
{
if (_filenames == null || !_filenames.Any())
{
ch.Info("Create part {0}: {1} (tag: {2})", i + 1, _ratios[i], _tags[i]);
}
else
{
ch.Info("Create part {0}: {1} (file: {2})", i + 1, _ratios[i], _filenames[i]);
}
var ar1 = new RangeFilter.Arguments()
{
Column = _newColumn, Min = i, Max = i, IncludeMax = true
};
int pardId = i;
var filtView = LambdaFilter.Create <int>(Host, string.Format("Select part {0}", i), currentTr,
_newColumn, NumberType.I4,
(in int part) => { return(part.Equals(pardId)); });