asreview.models.feature_extraction.EmbeddingLSTM

class asreview.models.feature_extraction.EmbeddingLSTM(*args, loop_sequence=1, num_words=20000, max_sequence_length=1000, padding='post', truncating='post', n_jobs=1, **kwargs)[source]

Embedding LSTM feature extraction technique (embedding-lstm).

Feature extraction technique for asreview.models.classifiers.LSTMBaseClassifier and asreview.models.classifiers.LSTMPoolClassifier models.

Note

This feature extraction technique requires tensorflow to be installed. Use pip install tensorflow or install all optional ASReview dependencies with pip install asreview[all]

Parameters

  • loop_sequence (bool) – Instead of zeros at the start/end of sequence loop it.

  • num_words (int) – Maximum number of unique words to be processed.

  • max_sequence_length (int) – Maximum length of the sequence. Shorter get struncated. Longer sequences get either padded with zeros or looped.

  • padding (str) – Which side should be padded [pre/post].

  • truncating – Which side should be truncated [pre/post].

  • n_jobs – Number of processors used in reading the embedding matrix.

Attributes

default_param

Get the default parameters of the model.

label

name

param

Get the (assigned) parameters of the model.

Methods

fit(texts)

Fit the model to the texts.

fit_transform(texts[, titles, abstracts, ...])

Fit and transform a list of texts.

full_hyper_space()

get_embedding_matrix(texts, embedding_fp)

hyper_space()

transform(texts)

Transform a list of texts.