public Config(OneHotHashVectorOutputKind outputKind, int numberOfBits, uint seed, bool ordered, int maximumNumberOfInverts)
{
OutputKind = outputKind;
NumberOfBits = numberOfBits;
Seed = seed;
Ordered = ordered;
MaximumNumberOfInverts = maximumNumberOfInverts;
}
public Config(OneHotHashVectorOutputKind outputKind, int hashBits, uint seed, bool ordered, int invertHash)
{
OutputKind = outputKind;
HashBits = hashBits;
Seed = seed;
Ordered = ordered;
InvertHash = invertHash;
}
/// <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: array or binary encoded data.</param>
/// <param name="hashBits">Amount of bits to use for hashing.</param>
/// <param name="seed">Seed value used for hashing.</param>
/// <param name="ordered">Whether the position of each term should be included in the hash.</param>
/// <param name="invertHash">Limit the number of keys used to generate the slot name to this many. 0 means no invert hashing, -1 means no limit.</param>
public static Vector <float> OneHotHashEncoding(this Vector <string> input, OneHotHashVectorOutputKind outputKind = DefOut,
int hashBits = DefHashBits, uint seed = DefSeed, bool ordered = DefOrdered, int invertHash = DefInvertHash)
{
Contracts.CheckValue(input, nameof(input));
return(new ImplVector <string>(input, new Config(outputKind, hashBits, seed, ordered, invertHash)));
}
/// <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: array or binary encoded data.</param>
/// <param name="numberOfBits">Amount of bits to use for hashing.</param>
/// <param name="seed">Seed value used for hashing.</param>
/// <param name="ordered">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>
public static Vector <float> OneHotHashEncoding(this VarVector <string> input, OneHotHashVectorOutputKind outputKind = DefOut,
int numberOfBits = DefNumberOfBits, uint seed = DefSeed, bool ordered = DefOrdered, int maximumNumberOfInverts = DefMaximumNumberOfInverts)
{
Contracts.CheckValue(input, nameof(input));
return(new ImplVector <string>(input, new Config(outputKind, numberOfBits, seed, ordered, maximumNumberOfInverts)));
}