Keras2Vec Data Generator¶
-
class
keras2vec.data_generator.
DataGenerator
(documents, seq_size, neg_samples)¶ The DataGenerator class is used to encode documents and generate training/testing data for a Keras2Vec instance. Currently this object is only used internally within the Keras2Vec class and not intended for direct use.
- Args:
- documents (
list
ofDocument
): List of documents to vectorize
-
build_vocabs
()¶ Build the vocabularies for the document ids, labels, and text of the provided documents
-
create_encodings
()¶ Build the encodings for each of the provided data types
-
encode_doc
(doc, neg_sampling=False, num_neg_samps=3)¶ Encodes a document for the keras model
- Args:
- doc(Document): The document to encode neg_sampling(Boolean): Whether or not to generate negative samples for the document NOTE: Currently not implemented
-
generator
()¶ Generates a single epoch of encoded data for the keras model