LatentDirichletAllocation<T>

Models & Types ยท AiDotNet.Preprocessing.DimensionalityReduction

Latent Dirichlet Allocation for topic modeling.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> โ†’ LatentDirichletAllocation<T>

For Beginners

LDA finds hidden themes (topics) in your data:

  • Input: Document-term matrix (rows=documents, columns=word counts)
  • Output: Document-topic distribution (what topics each document is about)
  • Also learns: Topic-word distribution (what words define each topic)
  • Use for: Topic modeling, document clustering, feature extraction

How It Works

LDA is a generative probabilistic model that discovers latent topics in a collection of documents (or more generally, in count data). Each document is modeled as a mixture of topics, and each topic is a distribution over words (features).

The model assumes:

  • Each document has a distribution over topics (theta)
  • Each topic has a distribution over words (beta)
  • Words in documents are generated by first sampling a topic, then sampling a word

Constructors

Constructor Summary
LatentDirichletAllocation(int nComponents, double? docTopicPrior, double? topicWordPrior, LdaLearningMethod learningMethod, int maxIter, double tol, int batchSize, int? randomState, int[] columnIndices) Creates a new instance of LatentDirichletAllocation.

Properties

Property Summary
LdaLearningMethod LearningMethod { get; } Gets the learning method.
Matrix<T> Components { get; } Gets the topic-word distribution matrix (topics x vocabulary).
bool SupportsInverseTransform { get; } Gets whether this transformer supports inverse transformation.
double DocTopicPrior { get; } Gets the document-topic prior (alpha).
double TopicWordPrior { get; } Gets the topic-word prior (beta/eta).
int NComponents { get; } Gets the number of topics.
int NVocab { get; } Gets the vocabulary size.

Methods

Method Summary
string[] GetFeatureNamesOut(string[] inputFeatureNames) Gets the output feature names after transformation.
string[][] GetTopWordsPerTopic(int nTopWords, string[] featureNames) Gets the top words for each topic.