public Config(OneHotVectorOutputKind outputKind, KeyOrdinality order, int max, Action <ValueToKeyMappingTransformer.TermMap> onFit)
{
OutputKind = outputKind;
Order = order;
Max = max;
OnFit = onFit;
}
/// <summary>
/// Describes how the transformer handles column pairs.
/// </summary>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="maximumNumberOfKeys">Maximum number of keys to keep per column when auto-training.</param>
/// <param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="KeyOrdinality.ByOccurrence"/> choosen they will be in the order encountered.
/// If <see cref="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="addKeyValueAnnotationsAsText">Whether key value annotations should be text, regardless of the actual input type.</param>
public ColumnOptions(string outputColumnName, string inputColumnName = null,
int maximumNumberOfKeys = Defaults.MaximumNumberOfKeys,
KeyOrdinality keyOrdinality = Defaults.Ordinality,
bool addKeyValueAnnotationsAsText = false)
: base(outputColumnName, inputColumnName, maximumNumberOfKeys, keyOrdinality, addKeyValueAnnotationsAsText)
{
}
private protected ColumnOptionsBase(string outputColumnName, string inputColumnName,
int maximumNumberOfKeys, KeyOrdinality keyOrdinality, bool addKeyValueAnnotationsAsText)
{
Contracts.CheckNonWhiteSpace(outputColumnName, nameof(outputColumnName));
OutputColumnName = outputColumnName;
InputColumnName = inputColumnName ?? outputColumnName;
KeyOrdinality = keyOrdinality;
MaximumNumberOfKeys = maximumNumberOfKeys;
AddKeyValueAnnotationsAsText = addKeyValueAnnotationsAsText;
}
/// <summary>
/// Initializes a new instance of <see cref="ValueToKeyMappingEstimator"/>.
/// </summary>
/// <param name="env">Host Environment.</param>
/// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
/// <param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
/// <param name="maximumNumberOfKeys">Maximum number of keys to keep per column when auto-training.</param>
/// <param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="KeyOrdinality.ByOccurrence"/> choosen they will be in the order encountered.
/// If <see cref="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>
internal ValueToKeyMappingEstimator(IHostEnvironment env, string outputColumnName, string inputColumnName = null, int maximumNumberOfKeys = Defaults.MaximumNumberOfKeys, KeyOrdinality keyOrdinality = Defaults.Ordinality) :
this(env, new [] { new ColumnOptions(outputColumnName, inputColumnName ?? outputColumnName, maximumNumberOfKeys, keyOrdinality) })
{
}
/// <summary>
/// Converts the categorical value into an indicator array by building a dictionary of categories based on the data and using the id in the dictionary as the index in the array.
/// </summary>
/// <param name="input">Incoming data.</param>
/// <param name="outputKind">Specify the output type of indicator array: Multiarray, array or binary encoded data.</param>
/// <param name="keyOrdinality">How the Id for each value would be assigined: by occurrence or by value.</param>
/// <param name="maximumNumberOfItems">Maximum number of ids to keep during data scanning.</param>
/// <param name="onFit">Called upon fitting with the learnt enumeration on the dataset.</param>
public static Vector <float> OneHotEncoding(this Vector <string> input, OneHotVectorOutputKind outputKind = DefOut, KeyOrdinality keyOrdinality = DefSort, int maximumNumberOfItems = DefMax,
ToKeyFitResult <ReadOnlyMemory <char> > .OnFit onFit = null)
{
Contracts.CheckValue(input, nameof(input));
return(new ImplVector <string>(input, new Config(outputKind, keyOrdinality, maximumNumberOfItems, Wrap(onFit))));
}
