/// <summary>
/// Create a <see cref="CountFeatureSelectingEstimator"/>, which selects the slots for which the count of non-default values is greater than or equal to a threshold.
/// </summary>
/// <param name="catalog">The transform's catalog.</param>
/// <param name="columns">Specifies the names of the columns on which to apply the transformation.</param>
/// <param name="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this TransformsCatalog.FeatureSelectionTransforms catalog,
InputOutputColumnPair[] columns,
long count = CountSelectDefaults.Count)
{
var env = CatalogUtils.GetEnvironment(catalog);
env.CheckValue(columns, nameof(columns));
var columnOptions = columns.Select(x => new CountFeatureSelectingEstimator.ColumnOptions(x.OutputColumnName, x.InputColumnName, count)).ToArray();
return(new CountFeatureSelectingEstimator(env, columnOptions));
}
/// <include file='doc.xml' path='doc/members/member[@name="MutualInformationFeatureSelection"]/*' />
/// <param name="catalog">The transform's catalog.</param>
/// <param name="labelColumn">Name of the column to use for labels.</param>
/// <param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
/// <param name="numBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
/// <param name="columns">Specifies the names of the input columns for the transformation, and their respective output column names.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
string labelColumn = MutualInfoSelectDefaults.LabelColumn,
int slotsInOutput = MutualInfoSelectDefaults.SlotsInOutput,
int numBins = MutualInfoSelectDefaults.NumBins,
params (string input, string output)[] columns)
/// <summary>
/// Create a <see cref="CountFeatureSelectingEstimator"/>, which selects the slots for which the count of non-default values is greater than or equal to a threshold.
/// </summary>
/// <param name="catalog">The transform's 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="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this TransformsCatalog.FeatureSelectionTransforms catalog,
string outputColumnName,
string inputColumnName = null,
long count = CountSelectDefaults.Count)
=> new CountFeatureSelectingEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, inputColumnName, count);
internal static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this TransformsCatalog.FeatureSelectionTransforms catalog,
params CountFeatureSelectingEstimator.ColumnOptions[] columns)
=> new CountFeatureSelectingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
/// <summary>
/// Create a <see cref="MutualInformationFeatureSelectingEstimator"/>, which selects the top k slots across all specified columns ordered by their mutual information with the label column.
/// </summary>
/// <param name="catalog">The transform's catalog.</param>
/// <param name="columns">Specifies the names of the input columns for the transformation, and their respective output column names.</param>
/// <param name="labelColumnName">The name of the label column.</param>
/// <param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
/// <param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
InputOutputColumnPair[] columns,
string labelColumnName = MutualInfoSelectDefaults.LabelColumn,
int slotsInOutput = MutualInfoSelectDefaults.SlotsInOutput,
int numberOfBins = MutualInfoSelectDefaults.NumBins)
{
var env = CatalogUtils.GetEnvironment(catalog);
env.CheckValue(columns, nameof(columns));
return(new MutualInformationFeatureSelectingEstimator(env, labelColumnName, slotsInOutput, numberOfBins,
columns.Select(x => (x.OutputColumnName, x.InputColumnName)).ToArray()));
}
/// <summary>
/// Create a <see cref="MutualInformationFeatureSelectingEstimator"/>, which selects the top k slots across all specified columns ordered by their mutual information with the label column.
/// </summary>
/// <param name="catalog">The transform's 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="labelColumnName">The name of the label column.</param>
/// <param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
/// <param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
string outputColumnName, string inputColumnName = null,
string labelColumnName = MutualInfoSelectDefaults.LabelColumn,
int slotsInOutput = MutualInfoSelectDefaults.SlotsInOutput,
int numberOfBins = MutualInfoSelectDefaults.NumBins)
=> new MutualInformationFeatureSelectingEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, inputColumnName, labelColumnName, slotsInOutput, numberOfBins);
internal static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
string labelColumnName = MutualInfoSelectDefaults.LabelColumn,
int slotsInOutput = MutualInfoSelectDefaults.SlotsInOutput,
int numberOfBins = MutualInfoSelectDefaults.NumBins,
params ColumnOptions[] columns)
=> new MutualInformationFeatureSelectingEstimator(CatalogUtils.GetEnvironment(catalog), labelColumnName, slotsInOutput, numberOfBins,
ColumnOptions.ConvertToValueTuples(columns));
/// <include file='doc.xml' path='doc/members/member[@name="MutualInformationFeatureSelection"]/*' />
/// <param name="catalog">The transform's catalog.</param>
/// <param name="labelColumn">Name of the column to use for labels.</param>
/// <param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
/// <param name="numBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
/// <param name="columns">Specifies the names of the input columns for the transformation, and their respective output column names.</param>
/// <example>
/// <format type="text/markdown">
/// <]
/// ]]>
/// </format>
/// </example>
public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
string labelColumn = MutualInfoSelectDefaults.LabelColumn,
int slotsInOutput = MutualInfoSelectDefaults.SlotsInOutput,
int numBins = MutualInfoSelectDefaults.NumBins,
params SimpleColumnInfo[] columns)
=> new MutualInformationFeatureSelectingEstimator(CatalogUtils.GetEnvironment(catalog), labelColumn, slotsInOutput, numBins,
SimpleColumnInfo.ConvertToValueTuples(columns));
