Extracts linguistic features from Spanish text for ML applications.

Provides feature vectors for:

• Text classification
• Similarity computation
• Information retrieval
• Clustering

Features

• Lexical: word counts, n-grams, TF-IDF
• Syntactic: POS tags, phrase structures
• Semantic: entities, sentiment indicators
• Statistical: sentence length, type-token ratio

Example

iex> doc = parse("El gato se sentó en la alfombra")
iex> features = FeatureExtractor.extract(doc)
%{
  word_count: 7,
  sentence_count: 1,
  avg_sentence_length: 7.0,
  noun_count: 2,
  verb_count: 1,
  entities: [:animal, :furniture],
  ...
}