explabox

The Explabox aims to support data scientists and machine learning (ML) engineers in explaining, testing and documenting AI/ML models, developed in-house or acquired externally. The explabox turns your ingestibles (AI/ML model and/or dataset) into digestibles (statistics, explanations or sensitivity insights)!

To install run:

$ pip3 install explabox

Currently, the main interface for working with the Explabox is Jupyter Notebook. For more help, read the documentation at https://explabox.rtfd.io.

Explabox is developed by the Dutch National Police Lab AI (NPAI), and released under the GNU Lesser General Public License v3.0 (GNU LGPLv3).

class explabox.Explabox(ingestibles=None, locale='en', **kwargs)

Bases: Readable, IngestiblesMixin

Use the Explabox to .explore, .examine, .expose and .explain your AI model.

Example

>>> from explabox import Explabox
>>> box = Explabox(data=data, model=model)

Parameters:

• ingestibles (Optional[Ingestible], optional) – Ingestibles (data and model). Defaults to None.

• locale (str, optional) – Language of dataset. Defaults to ‘en’.

• **kwargs – Arguments used to construct an Ingestible (if the ingestibles argument is None).

Subpackages:

• explabox.digestibles
  • Dataset
    • Dataset.content
    • Dataset.data
    • Dataset.filter()
    • Dataset.get_by_index()
    • Dataset.get_by_key()
    • Dataset.head()
    • Dataset.instances
    • Dataset.keys
    • Dataset.labels
    • Dataset.sample()
    • Dataset.tail()
  • Descriptives
    • Descriptives.content
  • Performance
    • Performance.content
    • Performance.metrics
  • WronglyClassified
    • WronglyClassified.content
    • WronglyClassified.wrongly_classified
• explabox.examine
  • Examiner
    • Examiner.performance()
    • Examiner.wrongly_classified()
• explabox.explain
  • explabox.explain.text
    • Explainer
      • Explainer.explain_prediction()
      • Explainer.prototypes()
      • Explainer.prototypes_criticisms()
      • Explainer.token_frequency()
      • Explainer.token_information()
• explabox.explore
  • Explorer
    • Explorer.descriptives()
    • Explorer.instances()
• explabox.expose
  • explabox.expose.text
    • Exposer
      • Exposer.compare_metric()
      • Exposer.input_space()
      • Exposer.invariance()
      • Exposer.mean_score()
    • explabox.expose.text.characters module
      • add_typos()
      • delete_random()
      • random_case_swap()
      • random_lower()
      • random_spaces()
      • random_upper()
      • swap_random()
    • explabox.expose.text.sentences module
      • repeat_k_times()
      • to_lower()
      • to_upper()
    • explabox.expose.text.words module
• explabox.ingestibles
  • Ingestible
    • Ingestible.check_requirements()
    • Ingestible.data
    • Ingestible.get_named_split()
    • Ingestible.labels
    • Ingestible.labelset
    • Ingestible.model
    • Ingestible.splits
    • Ingestible.test
    • Ingestible.train
    • Ingestible.validation
  • explabox.ingestibles.data
  • explabox.ingestibles.model
• explabox.ui
  • explabox.ui.notebook module
    • MAIN_COLOR
    • PACKAGE_LINK
    • PACKAGE_NAME
    • GBRenderRestyled
    • Render
      • Render.format_title()
      • Render.get_renderer()
      • Render.render_subtitle()
    • RestyleMixin
      • RestyleMixin.restyle()
    • TERenderRestyled
    • TSRenderRestyled
    • dataset_renderer()
    • descriptives_renderer()
    • format_table()
    • replace_renderer()
    • restyle()
    • wrongly_classified_renderer()
• explabox.utils
  • MultipleReturn
    • MultipleReturn.html
    • MultipleReturn.raw_html
    • MultipleReturn.to_config()
  • explabox.utils.io module
    • create_output_dir()

Submodules:

explabox.config module

Configuration for default paths and variables.

explabox.mixins module

Extensions to classes.

class explabox.mixins.IngestiblesMixin

Bases: object

check_requirements(elements=['data', 'model'])

Check if the required elements are in the ingestibles.

Parameters:

elements (List[str], optional) – Elements to check. Defaults to [‘data’, ‘model’].

Raises:

ValueError – The required element is not in the ingestibles.

Returns:

True if all requirements are included.

Return type:

bool

property data

All data.

property labels

Labelprovider.

property labelset

Names of labels.

property model

Predictive model.

property splits

Named splits.

class explabox.mixins.ModelMixin

Bases: object

property is_classifier: bool

Whether the included model is a classifier (True) or not (False).