/// <summary>
/// Convert a text column into hash-based one-hot encoded vector.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="inputColumn">The input column</param>
/// <param name="outputColumn">The output column. If <c>null</c>, <paramref name="inputColumn"/> is used.</param>
/// <param name="hashBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
/// <param name="invertHash">During hashing we constuct mappings between original values and the produced hash values.
/// Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
/// <paramref name="invertHash"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
/// <value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
/// <param name="outputKind">The conversion mode.</param>
/// <returns></returns>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string inputColumn,
string outputColumn = null,
int hashBits = OneHotHashEncodingEstimator.Defaults.HashBits,
int invertHash = OneHotHashEncodingEstimator.Defaults.InvertHash,
OneHotEncodingTransformer.OutputKind outputKind = OneHotEncodingTransformer.OutputKind.Ind)
=> new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, hashBits, invertHash, outputKind);
/// <summary>
/// Convert a text column into hash-based one-hot encoded vector.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
/// <param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
/// Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
/// <paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
/// <value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
/// <param name="outputKind">The conversion mode.</param>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string outputColumnName,
string inputColumnName = null,
int numberOfBits = OneHotHashEncodingEstimator.Defaults.NumberOfBits,
int maximumNumberOfInverts = OneHotHashEncodingEstimator.Defaults.MaximumNumberOfInverts,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.OutputKind.Indicator)
=> new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, inputColumnName ?? outputColumnName, numberOfBits, maximumNumberOfInverts, outputKind);
/// <summary>
/// Convert text columns into one-hot encoded vectors.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="outputKind">Output kind: Bag (multi-set vector), Ind (indicator vector), Key (index), or Binary encoded indicator vector.</param>
/// <param name="maximumNumberOfKeys">Maximum number of terms to keep per column when auto-training.</param>
/// <param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence"/> choosen they will be in the order encountered.
/// If <see cref="ValueToKeyMappingEstimator.KeyOrdinality.ByValue"/>, items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
/// <param name="keyData">Specifies an ordering for the encoding. If specified, this should be a single column data view,
/// and the key-values will be taken from that column. If unspecified, the ordering will be determined from the input data upon fitting.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string outputColumnName,
string inputColumnName = null,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.Defaults.OutKind,
int maximumNumberOfKeys = ValueToKeyMappingEstimator.Defaults.MaximumNumberOfKeys,
ValueToKeyMappingEstimator.KeyOrdinality keyOrdinality = ValueToKeyMappingEstimator.Defaults.Ordinality,
IDataView keyData = null)
=> new OneHotEncodingEstimator(CatalogUtils.GetEnvironment(catalog),
new[] { new OneHotEncodingEstimator.ColumnOptions(outputColumnName, inputColumnName, outputKind, maximumNumberOfKeys, keyOrdinality) }, keyData);
/// <summary>
/// Convert a text column into hash-based one-hot encoded vector.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="outputKind">The conversion mode.</param>
/// <param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
/// <param name="seed">Hashing seed.</param>
/// <param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
/// <param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
/// Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
/// <paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
/// <value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string outputColumnName,
string inputColumnName = null,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.OutputKind.Indicator,
int numberOfBits = OneHotHashEncodingEstimator.Defaults.NumberOfBits,
uint seed = OneHotHashEncodingEstimator.Defaults.Seed,
bool useOrderedHashing = OneHotHashEncodingEstimator.Defaults.UseOrderedHashing,
int maximumNumberOfInverts = OneHotHashEncodingEstimator.Defaults.MaximumNumberOfInverts)
=> new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog),
new[] { new OneHotHashEncodingEstimator.ColumnOptions(outputColumnName, inputColumnName, outputKind, numberOfBits, seed, useOrderedHashing, maximumNumberOfInverts) });
/// <summary>
/// Convert text columns into one-hot encoded vectors.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="columns">Specifies the names of the columns on which to apply the transformation.</param>
/// <param name="outputKind">Output kind: Bag (multi-set vector), Ind (indicator vector), Key (index), or Binary encoded indicator vector.</param>
/// <param name="maximumNumberOfKeys">Maximum number of terms to keep per column when auto-training.</param>
/// <param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence"/> choosen they will be in the order encountered.
/// If <see cref="ValueToKeyMappingEstimator.KeyOrdinality.ByValue"/>, items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
/// <param name="keyData">Specifies an ordering for the encoding. If specified, this should be a single column data view,
/// and the key-values will be taken from that column. If unspecified, the ordering will be determined from the input data upon fitting.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.CategoricalTransforms catalog,
InputOutputColumnPair[] columns,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.Defaults.OutKind,
int maximumNumberOfKeys = ValueToKeyMappingEstimator.Defaults.MaximumNumberOfKeys,
ValueToKeyMappingEstimator.KeyOrdinality keyOrdinality = ValueToKeyMappingEstimator.Defaults.Ordinality,
IDataView keyData = null)
{
var env = CatalogUtils.GetEnvironment(catalog);
env.CheckValue(columns, nameof(columns));
var columnOptions = columns.Select(x => new OneHotEncodingEstimator.ColumnOptions(x.OutputColumnName, x.InputColumnName, outputKind, maximumNumberOfKeys, keyOrdinality)).ToArray();
return(new OneHotEncodingEstimator(env, columnOptions, keyData));
}
/// <summary>
/// Convert text columns into hash-based one-hot encoded vector columns.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="columns">Specifies the names of the columns on which to apply the transformation.</param>
/// <param name="outputKind">The conversion mode.</param>
/// <param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
/// <param name="seed">Hashing seed.</param>
/// <param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
/// <param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
/// Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
/// <paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
/// <value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
InputOutputColumnPair[] columns,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.OutputKind.Indicator,
int numberOfBits = OneHotHashEncodingEstimator.Defaults.NumberOfBits,
uint seed = OneHotHashEncodingEstimator.Defaults.Seed,
bool useOrderedHashing = OneHotHashEncodingEstimator.Defaults.UseOrderedHashing,
int maximumNumberOfInverts = OneHotHashEncodingEstimator.Defaults.MaximumNumberOfInverts)
{
var env = CatalogUtils.GetEnvironment(catalog);
env.CheckValue(columns, nameof(columns));
var columnOptions = columns.Select(x => new OneHotHashEncodingEstimator.ColumnOptions(x.OutputColumnName, x.InputColumnName, outputKind, numberOfBits, seed, useOrderedHashing, maximumNumberOfInverts)).ToArray();
return(new OneHotHashEncodingEstimator(env, columnOptions));
}
/// <summary>
/// Initializes a new instance of <see cref="ValueToKeyMappingEstimator"/> loading the terms to use from <paramref name="file"/>.
/// </summary>
/// <param name="catalog">The categorical transform's catalog.</param>
/// <param name="columns">The data columns to map to keys.</param>
/// <param name="file">The path of the file containing the terms.</param>
/// <param name="termsColumn"></param>
/// <param name="loaderFactory"></param>
public static ValueToKeyMappingEstimator MapValueToKey(this TransformsCatalog.CategoricalTransforms catalog,
ValueToKeyMappingTransformer.ColumnInfo[] columns,
string file = null,
string termsColumn = null,
IComponentFactory <IMultiStreamSource, IDataLoader> loaderFactory = null)
=> new ValueToKeyMappingEstimator(CatalogUtils.GetEnvironment(catalog), columns, file, termsColumn, loaderFactory);
/// <summary>
/// Initializes a new instance of <see cref="ValueToKeyMappingEstimator"/>.
/// </summary>
/// <param name="catalog">The categorical transform's catalog.</param>
/// <param name="inputColumn">Name of the column to be transformed.</param>
/// <param name="outputColumn">Name of the output column. If this is null '<paramref name="inputColumn"/>' will be used.</param>
/// <param name="maxNumTerms">Maximum number of keys to keep per column when auto-training.</param>
/// <param name="sort">How items should be ordered when vectorized. By default, they will be in the order encountered.
/// If by value items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
public static ValueToKeyMappingEstimator MapValueToKey(this TransformsCatalog.CategoricalTransforms catalog,
string inputColumn,
string outputColumn = null,
int maxNumTerms = ValueToKeyMappingEstimator.Defaults.MaxNumTerms,
ValueToKeyMappingTransformer.SortOrder sort = ValueToKeyMappingEstimator.Defaults.Sort)
=> new ValueToKeyMappingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, maxNumTerms, sort);
internal static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.CategoricalTransforms catalog,
OneHotEncodingEstimator.ColumnOptions[] columns,
IDataView keyData = null)
=> new OneHotEncodingEstimator(CatalogUtils.GetEnvironment(catalog), columns, keyData);
internal static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.CategoricalTransforms catalog,
params OneHotEncodingEstimator.ColumnOptions[] columns)
=> new OneHotEncodingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
/// <summary>
/// Convert several text column into hash-based one-hot encoded vectors.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="columns">The column settings.</param>
/// <returns></returns>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
params OneHotHashEncodingEstimator.ColumnInfo[] columns)
=> new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
/// <summary>
/// Convert a text column into hash-based one-hot encoded vector.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="inputColumn">The input column</param>
/// <param name="outputColumn">The output column. If <c>null</c>, <paramref name="inputColumn"/> is used.</param>
/// <param name="outputKind">The conversion mode.</param>
/// <returns></returns>
public static OneHotHashEncodingEstimator OneHotHashEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string inputColumn, string outputColumn = null, CategoricalTransform.OutputKind outputKind = CategoricalTransform.OutputKind.Ind)
=> new OneHotHashEncodingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, outputKind);
/// <summary>
/// Convert a text column into one-hot encoded vector.
/// </summary>
/// <param name="catalog">The transform catalog</param>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="outputKind">The conversion mode.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]></format>
/// </example>
public static OneHotEncodingEstimator OneHotEncoding(this TransformsCatalog.CategoricalTransforms catalog,
string outputColumnName,
string inputColumnName = null,
OneHotEncodingEstimator.OutputKind outputKind = OneHotEncodingEstimator.OutputKind.Indicator)
=> new OneHotEncodingEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, inputColumnName, outputKind);
