v1.0.0

This is the first stable release 🎉! The release mainly consists of code cleanup, documentation, and repository organization.

• Datasets:
  • SklearnDataset now checks if the dimensions of features and labels match.
• Query Strategies:
  • ExpectedGradientLengthMaxWord: Cleaned up code and added checks to detect invalid configurations.
• Documentation:
  • The html documentation uses the full screen width.
• Repository:
  • This repository can now be referenced using the respective Zenodo DOI.

v1.0.0b4

This release adds two no query strategies, improves the Dataset interface, and introduces optional dependencies.

Added

• General:
  • We now have a concept for optional dependencies which allows components to rely on soft dependencies, i.e. python dependencies which can be installed on demand (and only when certain functionality is needed).
• Datasets:
  • The Dataset interface now has a clone() method that creates an identical copy of the respective dataset.
• Query Strategies:
  • New strategies: DiscriminativeActiveLearning and SEALS.

Changed

• Datasets:
  • Separated the previous DatasetView implementation into interface (DatasetView) and implementation (SklearnDatasetView).
  • Added clone() method which creates an identical copy of the dataset.
• Query Strategies:
  • EmbeddingBasedQueryStrategy now only embeds instances that are either in the label or in the unlabeled pool (and no longer the entire dataset).
• Code examples:
  • Code structure was unified.
  • Number of iterations can now be passed via an cli argument.
• small_text.integrations.pytorch.utils.data:
  • Method get_class_weights() now scales the resulting multi-class weights so that the smallest class weight is equal to 1.0.

v1.0.0b3

This release adds a new query strategy, improves the docs, and cleans up the interfaces in preparation of v1.0.0.

Added

• Added new query strategy: ContrastiveActiveLearning.
• Added Reproducibility Notes.

Changed

• Cleaned up and unified argument naming: The naming of variables related to datasets and
  indices has been improved and unified. The naming of datasets had been inconsistent,
  and the previous x_ notation for indices was a relict of earlier versions of this library and
  did not reflect the underlying object anymore.

  • PoolBasedActiveLearner:

    • attribute x_indices_labeled was renamed to indices_labeled
    • attribute x_indices_ignored was unified to indices_ignored
    • attribute queried_indices was unified to indices_queried
    • attribute _x_index_to_position was named to _index_to_position
    • arguments x_indices_initial, x_indices_ignored, and x_indices_validation were
      renamed to indices_initial, indices_ignored, and indices_validation. This affects most
      methods of the PoolBasedActiveLearner.

  • QueryStrategy

    • old: query(self, clf, x, x_indices_unlabeled, x_indices_labeled, y, n=10)
    • new: query(self, clf, dataset, indices_unlabeled, indices_labeled, y, n=10)

  • StoppingCriterion

    • old: stop(self, active_learner=None, predictions=None, proba=None, x_indices_stopping=None)
    • new: stop(self, active_learner=None, predictions=None, proba=None, indices_stopping=None)

• Renamed environment variable which sets the small-text temp folder from ALL_TMP to SMALL_TEXT_TEMP

v1.0.0b2

This release fixes some broken links which were caused due to the recent change in naming the git tags (1.0.0a8 -> v1.0.0b1).

Fixed

• Fix links to the documentation in README.md and notebooks.

v1.0.0b1

First beta release with multi-label functionality and stopping criteria. Added/revised large parts of the documentation.

Added

• Added a changelog.
• All provided classifiers are now capable of multi-label classification.

Changed

• Documentation has been overhauled considerably.
• PoolBasedActiveLearner: Renamed incremental_training kwarg to reuse_model.
• SklearnClassifier: Changed __init__(clf) to __init__(model, num_classes, multi_Label=False)
• SklearnClassifierFactory: __init__(clf_template, kwargs={}) to __init__(base_estimator, num_classes, kwargs={}).
• Refactored KimCNNClassifier and TransformerBasedClassification.

Removed

• Removed device kwarg from PytorchDataset.__init__(),
  PytorchTextClassificationDataset.__init__() and TransformersDataset.__init__().