public SemanticBagOfWordsSimilarity(SemanticVocabulary learnedVocabulary, TokenSimilarity tokenSimilarity,
bool isSymmetric)
{
InternalTokenSimilarity = tokenSimilarity;
IsSymmetric = isSymmetric;
Vocabulary = learnedVocabulary;
}
public void Initializate()
{
_vocabulary = new SemanticVocabulary();
var standardTokenizer = new StandardTokenizer("the the the some some text");
_vocabulary.AddSource(standardTokenizer);
}
public void SemanticVocabularySerialization()
{
var vocOrigin = new SemanticVocabulary();
var tokenizer =
new StandardTokenizer(
"In computer science, an inverted " +
"index (also referred to as postings file or inverted file) is an index data structure storing a mapping from content, " +
"such as words or numbers, to its locations in a database file, or in a document or a set of documents. " +
"The purpose of an inverted index is to allow fast full text searches, " +
"at a cost of increased processing when a document is added to the database. " +
"The inverted file may be the database file itself, rather than its index. " +
"It is the most popular data structure used in document retrieval systems,[1] " +
"used on a large scale for example in search engines. " +
"Several significant general-purpose mainframe-based database management systems have used " +
"inverted list architectures, including ADABAS, DATACOM/DB, and Model 204.");
vocOrigin.AddSource(tokenizer);
vocOrigin.TotalWords.Should().Be(130);
vocOrigin.UniqueWords.Should().Be(79);
vocOrigin.SaveToFile(VocabularyFileName);
var vocDeser = SemanticVocabulary.LoadFromFile(VocabularyFileName);
// test if the file exist
var fileInfo = new FileInfo(VocabularyFileName);
fileInfo.Exists.Should().BeTrue();
vocOrigin.Equals(vocDeser).Should().BeFalse();
vocDeser.TotalWords.Should().Be(vocOrigin.TotalWords);
vocDeser.UniqueWords.Should().Be(vocOrigin.UniqueWords);
}
public void SemanticWeightWrongInput()
{
// the 3x, some 2x, text 1x
var tokenizer = new StandardTokenizer("the the the some some text");
var vocabulary = new SemanticVocabulary();
vocabulary.AddSource(tokenizer);
vocabulary.GetSemanticWeight(" ");
}
public void SemantciWeghtNotPresentWord()
{
// the 3x, some 2x, text 1x
var tokenizer = new StandardTokenizer("the the the some some text");
var vocabulary = new SemanticVocabulary();
vocabulary.AddSource(tokenizer);
vocabulary.GetSemanticWeight("NotPresent").Should().BeApproximately(1.79, 1e-2);
}
public void SemanticWeightsTest()
{
// the 3x, some 2x, text 1x
var tokenizer = new StandardTokenizer("the the the some some text");
var vocabulary = new SemanticVocabulary();
vocabulary.AddSource(tokenizer);
var wThe = vocabulary.GetSemanticWeight("THE");
var wSome = vocabulary.GetSemanticWeight("SOME");
var wText = vocabulary.GetSemanticWeight("TEXT");
wThe.Should().BeLessThan(wSome);
wSome.Should().BeLessThan(wText);
}
public SemanticBagOfWordsSimilarity(SemanticVocabulary learnedVocabulary, TokenSimilarity tokenSimilarity)
: this(learnedVocabulary, tokenSimilarity, DefaultIsSymmetric)
{
}
/// <summary>
/// Initializes a new instance of the <see cref="SoftTFIDF"/> class.
/// </summary>
/// <param name="learnedVocabulary">The learned vocabulary.</param>
/// <param name="tokenSimilarity">The token similarity.</param>
public SoftTFIDF(SemanticVocabulary learnedVocabulary, TokenSimilarity tokenSimilarity)
{
Vocabulary = learnedVocabulary;
InternalTokenSimilarity = tokenSimilarity;
}
/// <summary>
/// Initializes a new instance of the <see cref="SoftTFIDF"/> class.
/// </summary>
/// <param name="learnedVocabulary">The learned vocabulary.</param>
public SoftTFIDF(SemanticVocabulary learnedVocabulary)
: this(learnedVocabulary, DefaultTokenSimilarity)
{
}
/// <summary>
/// Initializate
/// </summary>
/// <param name="semanticVocabulary">The semantic vocabulary.</param>
public TFIDF(SemanticVocabulary semanticVocabulary)
{
Vocabulary = semanticVocabulary;
}