/// <summary>
/// This is very similar to <see cref="Create(DataViewType, string, string)"/> but adds one extra metadata field to the only score column.
/// </summary>
/// <param name="scoreType">Output element's type of quantile regressor. Note that a quantile regressor can produce an array of <see cref="PrimitiveDataViewType"/>.</param>
/// <param name="quantiles">Quantiles used in quantile regressor.</param>
/// <returns><see cref="DataViewSchema"/> of quantile regressor's output.</returns>
public static DataViewSchema CreateQuantileRegressionSchema(DataViewType scoreType, double[] quantiles)
{
Contracts.CheckValue(scoreType, nameof(scoreType));
Contracts.CheckValue(scoreType as PrimitiveDataViewType, nameof(scoreType));
Contracts.AssertValue(quantiles);
// Create a schema using standard function. The produced schema will be modified by adding one metadata column.
var partialSchema = Create(new VectorType(scoreType as PrimitiveDataViewType, quantiles.Length), MetadataUtils.Const.ScoreColumnKind.QuantileRegression);
var metadataBuilder = new MetadataBuilder();
// Add the extra metadata.
metadataBuilder.AddSlotNames(quantiles.Length, (ref VBuffer <ReadOnlyMemory <char> > value) =>
{
var bufferEditor = VBufferEditor.Create(ref value, quantiles.Length);
for (int i = 0; i < quantiles.Length; ++i)
{
bufferEditor.Values[i] = string.Format("Quantile-{0}", quantiles[i]).AsMemory();
}
value = bufferEditor.Commit();
});
// Copy default metadata from the partial schema.
metadataBuilder.Add(partialSchema[0].Metadata, (string kind) => true);
// Build a schema consisting of a single column. Comparing with partial schema, the only difference is a metadata field.
var schemaBuilder = new SchemaBuilder();
schemaBuilder.AddColumn(partialSchema[0].Name, partialSchema[0].Type, metadataBuilder.GetMetadata());
return(schemaBuilder.GetSchema());
}
public DataView(IHostEnvironment env, ArrayDataViewBuilder builder, int rowCount)
{
Contracts.AssertValue(env, "env");
_host = env.Register("ArrayDataView");
_host.AssertValue(builder);
_host.Assert(rowCount >= 0);
_host.Assert(builder._names.Count == builder._columns.Count);
_columns = builder._columns.ToArray();
var schemaBuilder = new SchemaBuilder();
for (int i = 0; i < _columns.Length; i++)
{
var meta = new MetadataBuilder();
if (builder._getSlotNames.TryGetValue(builder._names[i], out var slotNamesGetter))
{
meta.AddSlotNames(_columns[i].Type.GetVectorSize(), slotNamesGetter);
}
if (builder._getKeyValues.TryGetValue(builder._names[i], out var keyValueGetter))
{
meta.AddKeyValues(_columns[i].Type.GetKeyCount(), TextType.Instance, keyValueGetter);
}
schemaBuilder.AddColumn(builder._names[i], _columns[i].Type, meta.GetMetadata());
}
_schema = schemaBuilder.GetSchema();
_rowCount = rowCount;
}
/// <summary>
/// Create a <see cref="Schema"/> with two columns for binary classifier. The first column, indexed by 0, is the score column.
/// The second column is the probability column. For example, for linear support vector machine, score column stands for the inner product
/// of linear coefficients and the input feature vector and we convert score column to probability column using a calibrator.
/// </summary>
/// <param name="scoreColumnName">Column name of score column</param>
/// <param name="probabilityColumnName">Column name of probability column</param>
/// <returns><see cref="Schema"/> of binary classifier's output.</returns>
public static Schema CreateBinaryClassificationSchema(string scoreColumnName = MetadataUtils.Const.ScoreValueKind.Score,
string probabilityColumnName = MetadataUtils.Const.ScoreValueKind.Probability)
{
// Schema of Score column. We are going to extend it by adding a Probability column.
var partialSchema = Create(NumberType.Float, MetadataUtils.Const.ScoreColumnKind.BinaryClassification, scoreColumnName);
var schemaBuilder = new SchemaBuilder();
// Copy Score column from partialSchema.
schemaBuilder.AddColumn(partialSchema[0].Name, partialSchema[0].Type, partialSchema[0].Metadata);
// Create Probability column's metadata.
var probabilityMetadataBuilder = new MetadataBuilder();
probabilityMetadataBuilder.Add(MetadataUtils.Kinds.IsNormalized, BoolType.Instance, (ref bool value) => { value = true; });
probabilityMetadataBuilder.Add(MetadataUtils.Kinds.ScoreColumnKind, TextType.Instance,
(ref ReadOnlyMemory <char> value) => { value = MetadataUtils.Const.ScoreColumnKind.BinaryClassification.AsMemory(); });
probabilityMetadataBuilder.Add(MetadataUtils.Kinds.ScoreValueKind, TextType.Instance,
(ref ReadOnlyMemory <char> value) => { value = MetadataUtils.Const.ScoreValueKind.Probability.AsMemory(); });
// Add probability column.
schemaBuilder.AddColumn(probabilityColumnName, NumberType.Float, probabilityMetadataBuilder.GetMetadata());
return(schemaBuilder.GetSchema());
}
/// <summary>
/// Return a <see cref="DataViewSchema"/> which contains a single score column.
/// </summary>
/// <param name="scoreType">The type of the score column.</param>
/// <param name="scoreColumnKindValue">The kind of the score column. It's the value of <see cref="MetadataUtils.Kinds.ScoreColumnKind"/> in the score column's metadata.</param>
/// <param name="scoreColumnName">The score column's name in the generated <see cref="DataViewSchema"/>.</param>
/// <returns><see cref="DataViewSchema"/> which contains only one column.</returns>
public static DataViewSchema Create(DataViewType scoreType, string scoreColumnKindValue, string scoreColumnName = MetadataUtils.Const.ScoreValueKind.Score)
{
Contracts.CheckValue(scoreType, nameof(scoreType));
Contracts.CheckNonEmpty(scoreColumnKindValue, nameof(scoreColumnKindValue));
// Two metadata fields. One can set up by caller of this function while the other one is a constant.
var metadataBuilder = new MetadataBuilder();
metadataBuilder.Add(MetadataUtils.Kinds.ScoreColumnKind, TextDataViewType.Instance,
(ref ReadOnlyMemory <char> value) => { value = scoreColumnKindValue.AsMemory(); });
metadataBuilder.Add(MetadataUtils.Kinds.ScoreValueKind, TextDataViewType.Instance,
(ref ReadOnlyMemory <char> value) => { value = MetadataUtils.Const.ScoreValueKind.Score.AsMemory(); });
// Build a schema consisting of a single column.
var schemaBuilder = new SchemaBuilder();
schemaBuilder.AddColumn(scoreColumnName, scoreType, metadataBuilder.GetMetadata());
return(schemaBuilder.GetSchema());
}
private static DataViewSchema CreateSchema(ColumnBindingsBase inputBindings)
{
Contracts.CheckValue(inputBindings, nameof(inputBindings));
var builder = new SchemaBuilder();
for (int i = 0; i < inputBindings.ColumnCount; i++)
{
var meta = new MetadataBuilder();
foreach (var kvp in inputBindings.GetMetadataTypes(i))
{
var getter = Utils.MarshalInvoke(GetMetadataGetterDelegate <int>, kvp.Value.RawType, inputBindings, i, kvp.Key);
meta.Add(kvp.Key, kvp.Value, getter);
}
builder.AddColumn(inputBindings.GetColumnName(i), inputBindings.GetColumnType(i), meta.GetMetadata());
}
return(builder.GetSchema());
}
public BoundMapper(IExceptionContext ectx, TreeEnsembleFeaturizerBindableMapper owner,
RoleMappedSchema schema)
{
Contracts.AssertValue(ectx);
ectx.AssertValue(owner);
ectx.AssertValue(schema);
ectx.Assert(schema.Feature.HasValue);
_ectx = ectx;
_owner = owner;
InputRoleMappedSchema = schema;
// A vector containing the output of each tree on a given example.
var treeValueType = new VectorType(NumberType.Float, owner._ensemble.TrainedEnsemble.NumTrees);
// An indicator vector with length = the total number of leaves in the ensemble, indicating which leaf the example
// ends up in all the trees in the ensemble.
var leafIdType = new VectorType(NumberType.Float, owner._totalLeafCount);
// An indicator vector with length = the total number of nodes in the ensemble, indicating the nodes on
// the paths of the example in all the trees in the ensemble.
// The total number of nodes in a binary tree is equal to the number of internal nodes + the number of leaf nodes,
// and it is also equal to the number of children of internal nodes (which is 2 * the number of internal nodes)
// plus one (since the root node is not a child of any node). So we have #internal + #leaf = 2*(#internal) + 1,
// which means that #internal = #leaf - 1.
// Therefore, the number of internal nodes in the ensemble is #leaf - #trees.
var pathIdType = new VectorType(NumberType.Float, owner._totalLeafCount - owner._ensemble.TrainedEnsemble.NumTrees);
// Start creating output schema with types derived above.
var schemaBuilder = new SchemaBuilder();
// Metadata of tree values.
var treeIdMetadataBuilder = new MetadataBuilder();
treeIdMetadataBuilder.Add(MetadataUtils.Kinds.SlotNames, MetadataUtils.GetNamesType(treeValueType.Size),
(ValueGetter <VBuffer <ReadOnlyMemory <char> > >)owner.GetTreeSlotNames);
// Add the column of trees' output values
schemaBuilder.AddColumn(OutputColumnNames.Trees, treeValueType, treeIdMetadataBuilder.GetMetadata());
// Metadata of leaf IDs.
var leafIdMetadataBuilder = new MetadataBuilder();
leafIdMetadataBuilder.Add(MetadataUtils.Kinds.SlotNames, MetadataUtils.GetNamesType(leafIdType.Size),
(ValueGetter <VBuffer <ReadOnlyMemory <char> > >)owner.GetLeafSlotNames);
leafIdMetadataBuilder.Add(MetadataUtils.Kinds.IsNormalized, BoolType.Instance, (ref bool value) => value = true);
// Add the column of leaves' IDs where the input example reaches.
schemaBuilder.AddColumn(OutputColumnNames.Leaves, leafIdType, leafIdMetadataBuilder.GetMetadata());
// Metadata of path IDs.
var pathIdMetadataBuilder = new MetadataBuilder();
pathIdMetadataBuilder.Add(MetadataUtils.Kinds.SlotNames, MetadataUtils.GetNamesType(pathIdType.Size),
(ValueGetter <VBuffer <ReadOnlyMemory <char> > >)owner.GetPathSlotNames);
pathIdMetadataBuilder.Add(MetadataUtils.Kinds.IsNormalized, BoolType.Instance, (ref bool value) => value = true);
// Add the column of encoded paths which the input example passes.
schemaBuilder.AddColumn(OutputColumnNames.Paths, pathIdType, pathIdMetadataBuilder.GetMetadata());
OutputSchema = schemaBuilder.GetSchema();
// Tree values must be the first output column.
Contracts.Assert(OutputSchema[OutputColumnNames.Trees].Index == TreeValuesColumnId);
// leaf IDs must be the second output column.
Contracts.Assert(OutputSchema[OutputColumnNames.Leaves].Index == LeafIdsColumnId);
// Path IDs must be the third output column.
Contracts.Assert(OutputSchema[OutputColumnNames.Paths].Index == PathIdsColumnId);
}
/// <summary>
/// This function returns a schema for sequence predictor's output. Its output column is always called <see cref="MetadataUtils.Const.ScoreValueKind.PredictedLabel"/>.
/// </summary>
/// <param name="scoreType">Score column's type produced by sequence predictor.</param>
/// <param name="scoreColumnKindValue">A metadata value of score column. It's the value associated with key
/// <see cref="MetadataUtils.Kinds.ScoreColumnKind"/>.</param>
/// <param name="keyNames">Sequence predictor usually generates integer outputs. This field tells the tags of all possible output values.
/// For example, output integer 0 cound be mapped to "Sell" and 0 to "Buy" when predicting stock trend.</param>
/// <returns><see cref="DataViewSchema"/> of sequence predictor's output.</returns>
public static DataViewSchema CreateSequencePredictionSchema(DataViewType scoreType, string scoreColumnKindValue, VBuffer <ReadOnlyMemory <char> > keyNames = default)
{
Contracts.CheckValue(scoreType, nameof(scoreType));
Contracts.CheckValue(scoreColumnKindValue, nameof(scoreColumnKindValue));
var metadataBuilder = new MetadataBuilder();
// Add metadata columns including their getters. We starts with key names of predicted keys if they exist.
if (keyNames.Length > 0)
{
metadataBuilder.AddKeyValues(keyNames.Length, TextDataViewType.Instance,
(ref VBuffer <ReadOnlyMemory <char> > value) => value = keyNames);
}
metadataBuilder.Add(MetadataUtils.Kinds.ScoreColumnKind, TextDataViewType.Instance,
(ref ReadOnlyMemory <char> value) => value = scoreColumnKindValue.AsMemory());
metadataBuilder.Add(MetadataUtils.Kinds.ScoreValueKind, TextDataViewType.Instance,
(ref ReadOnlyMemory <char> value) => value = MetadataUtils.Const.ScoreValueKind.PredictedLabel.AsMemory());
// Build a schema consisting of a single column.
var schemaBuilder = new SchemaBuilder();
schemaBuilder.AddColumn(MetadataUtils.Const.ScoreValueKind.PredictedLabel, scoreType, metadataBuilder.GetMetadata());
return(schemaBuilder.GetSchema());
}
/// <summary>
/// Append label names to score column as its metadata.
/// </summary>
private DataViewSchema DecorateOutputSchema(DataViewSchema partialSchema, int scoreColumnIndex, VectorType labelNameType,
ValueGetter <VBuffer <T> > labelNameGetter, string labelNameKind)
{
var builder = new SchemaBuilder();
// Sequentially add columns so that the order of them is not changed comparing with the schema in the mapper
// that computes score column.
for (int i = 0; i < partialSchema.Count; ++i)
{
var meta = new MetadataBuilder();
if (i == scoreColumnIndex)
{
// Add label names for score column.
meta.Add(partialSchema[i].Metadata, selector: s => s != labelNameKind);
meta.Add(labelNameKind, labelNameType, labelNameGetter);
}
else
{
// Copy all existing metadata because this transform only affects score column.
meta.Add(partialSchema[i].Metadata, selector: s => true);
}
// Instead of appending extra metadata to the existing score column, we create new one because
// metadata is read-only.
builder.AddColumn(partialSchema[i].Name, partialSchema[i].Type, meta.GetMetadata());
}
return(builder.GetSchema());
}
public RowMapper(IHostEnvironment env, BindableMapper parent, RoleMappedSchema schema)
{
Contracts.AssertValue(env);
_env = env;
_env.AssertValue(schema);
_env.AssertValue(parent);
_env.Assert(schema.Feature.HasValue);
_parent = parent;
InputRoleMappedSchema = schema;
var genericMapper = parent.GenericMapper.Bind(_env, schema);
_genericRowMapper = genericMapper as ISchemaBoundRowMapper;
var featureSize = FeatureColumn.Type.GetVectorSize();
if (parent.Stringify)
{
var builder = new SchemaBuilder();
builder.AddColumn(DefaultColumnNames.FeatureContributions, TextType.Instance, null);
_outputSchema = builder.GetSchema();
if (FeatureColumn.HasSlotNames(featureSize))
{
FeatureColumn.Metadata.GetValue(MetadataUtils.Kinds.SlotNames, ref _slotNames);
}
else
{
_slotNames = VBufferUtils.CreateEmpty <ReadOnlyMemory <char> >(featureSize);
}
}
else
{
var metadataBuilder = new MetadataBuilder();
if (InputSchema[FeatureColumn.Index].HasSlotNames(featureSize))
{
metadataBuilder.AddSlotNames(featureSize, (ref VBuffer <ReadOnlyMemory <char> > value) =>
FeatureColumn.Metadata.GetValue(MetadataUtils.Kinds.SlotNames, ref value));
}
var schemaBuilder = new SchemaBuilder();
var featureContributionType = new VectorType(NumberType.R4, FeatureColumn.Type as VectorType);
schemaBuilder.AddColumn(DefaultColumnNames.FeatureContributions, featureContributionType, metadataBuilder.GetMetadata());
_outputSchema = schemaBuilder.GetSchema();
}
_outputGenericSchema = _genericRowMapper.OutputSchema;
OutputSchema = new ZipBinding(new Schema[] { _outputGenericSchema, _outputSchema, }).OutputSchema;
}
internal static Schema Create(ISchema inputSchema)
{
Contracts.CheckValue(inputSchema, nameof(inputSchema));
if (inputSchema is Schema s)
{
return(s);
}
var builder = new SchemaBuilder();
for (int i = 0; i < inputSchema.ColumnCount; i++)
{
var meta = new MetadataBuilder();
foreach (var kvp in inputSchema.GetMetadataTypes(i))
{
var getter = Utils.MarshalInvoke(GetMetadataGetterDelegate <int>, kvp.Value.RawType, inputSchema, i, kvp.Key);
meta.Add(kvp.Key, kvp.Value, getter);
}
builder.AddColumn(inputSchema.GetColumnName(i), inputSchema.GetColumnType(i), meta.GetMetadata());
}
return(builder.GetSchema());
}