/// <include file='doc.xml' path='doc/members/member[@name="WordEmbeddings"]/*' />
/// <param name="input">Vector of tokenized text.</param>
/// <param name="modelKind">The pretrained word embedding model.</param>
/// <returns></returns>
public static Vector <float> WordEmbeddings(this VarVector <string> input, WordEmbeddingsTransform.PretrainedModelKind modelKind = WordEmbeddingsTransform.PretrainedModelKind.Sswe)
{
Contracts.CheckValue(input, nameof(input));
return(new OutColumn(input, modelKind));
}
public static VarVector <Key <uint> > Hash <T>(this VarVector <T> me) => _rec.VarVector <Key <uint> >(me);
public static VarVector <Key <uint, string> > Hash <T>(this VarVector <T> me, int invertHashTokens) => _rec.VarVector <Key <uint, string> >(me);
public static VarVector <string> Tokenize(this VarVector <string> me) => _rec.VarVector <string>(me);
public static VarVector <Key <uint, T> > Dictionarize <T>(this VarVector <T> me) => _rec.VarVector <Key <uint, T> >(me);
public static VarVector <Key <uint, string> > Hash <T>(this VarVector <T> me, int maximumNumberOfInvertsTokens) => _rec.VarVector <Key <uint, string> >(me);
public static VarVector <T> ConcatWith <T>(this VarVector <T> me, params ScalarOrVectorOrVarVector <T>[] i) => _rec.VarVector <T>(Helper(me, i));
public OutPipelineColumn(VarVector <Key <uint, string> > input, int hashBits, int ngramLength, int skipLength, bool allLengths, uint seed, bool ordered, int invertHash)
: base(new Reconciler(hashBits, ngramLength, skipLength, allLengths, seed, ordered, invertHash), input)
{
Input = input;
}
public static Vector <float> BagVectorize <T, TVal>(this VarVector <Key <T, TVal> > me) => _rec.Vector <float>(me);
public OutPipelineColumn(VarVector <string> input, Language language)
: base(new Reconciler(language), input)
{
Input = input;
}
/// <summary>
/// Remove stop words from incoming text.
/// </summary>
/// <param name="input">The column to apply to.</param>
/// <param name="language">Langauge of the input text.</param>
public static VarVector <string> RemoveStopwords(this VarVector <string> input,
Language language = Language.English) => new OutPipelineColumn(input, language);
/// <summary> /// Convert to variable array of floats. /// </summary> /// <param name="input">The input column.</param> /// <returns >Column with variable array of floats.</returns> public static VarVector <float> ToFloat(this VarVector <sbyte> input) => new ImplVarVector <sbyte>(Contracts.CheckRef(input, nameof(input)), DataKind.R4);
/// <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 VarVector <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)));
}
public OutColumn(VarVector <string> input, string customModelFile = null)
: base(new Reconciler(customModelFile), input)
{
Input = input;
}
/// <include file='doc.xml' path='doc/members/member[@name="WordEmbeddings"]/*' />
/// <param name="input">Vector of tokenized text.</param>
/// <param name="customModelFile">The custom word embedding model file.</param>
public static Vector <float> WordEmbeddings(this VarVector <string> input, string customModelFile)
{
Contracts.CheckValue(input, nameof(input));
return(new OutColumn(input, customModelFile));
}
/// <summary> /// Given a set of columns including at least one variable sized vector column, concatenate them /// together into a vector valued column of the same type. /// </summary> /// <typeparam name="T">The value type.</typeparam> /// <param name="me">The first input column.</param> /// <param name="others">Subsequent input columns.</param> /// <returns>The result of concatenating all input columns together.</returns> public static VarVector <T> ConcatWith <T>(this VarVector <T> me, params ScalarOrVectorOrVarVector <T>[] others) => new ImplVar <T>(Join(me, others));
public OutColumn(VarVector <string> input, WordEmbeddingsTransform.PretrainedModelKind modelKind = WordEmbeddingsTransform.PretrainedModelKind.Sswe)
: base(new Reconciler(modelKind), input)
{
Input = input;
}
public OutVarVectorColumn(VarVector <TValue> input)
: base(Reconciler.Inst, input)
{
Input = input;
}