pdstools.explanations
=====================

.. py:module:: pdstools.explanations


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/pdstools/explanations/Aggregate/index
   /autoapi/pdstools/explanations/Explanations/index
   /autoapi/pdstools/explanations/ExplanationsUtils/index
   /autoapi/pdstools/explanations/FilterWidget/index
   /autoapi/pdstools/explanations/Plots/index
   /autoapi/pdstools/explanations/Preprocess/index
   /autoapi/pdstools/explanations/Reports/index


Classes
-------

.. autoapisummary::

   pdstools.explanations.Explanations


Package Contents
----------------

.. py:class:: Explanations(root_dir: str = '.tmp', data_folder: str = 'explanations_data', model_name: Optional[str] = '', from_date: Optional[datetime.datetime] = None, to_date: Optional[datetime.datetime] = None)

   Process and explore explanation data for Adaptive Gradient Boost models.

   Class is initialied with data location, which should point to the location of the
   model's explanation parquet files downloaded from the explanations file repository.
   These parquet files can then be processed to create aggregates to explain the contribution
   of different predictors on a global level.

   :param data_folder: The path of the folder containing the model explanation parquet files for processing.
   :type data_folder: str
   :param model_name: The name of the model rule. Will be used to identify files in the data folder
                      and to validate that the correct files are being processed.
   :type model_name: str, optional
   :param end_date: Defines the end date of the duration over which aggregates will be collected.
   :type end_date: datetime, optional, default = datetime.today()
   :param start_date: Defines the start date of the duration over which aggregaates wille be collected.
   :type start_date: datetime, optional, default = end_date - timedelta(7)
   :param Environment variables:
   :param -------------------:
   :param BATCH_LIMIT: The maximum number of unique contexts to process in a single batch. Default is 10.
   :type BATCH_LIMIT: int
   :param MEMORY_LIMIT: Set the memory limit for the duckdb buffer manager.
                        If not set will use 80% of RAM. Default is 2(in GB).
   :type MEMORY_LIMIT: int
   :param THREAD_COUNT: Set the amount of threads for duck db parallel query execution. Default is 4.
   :type THREAD_COUNT: int
   :param PROGRESS_BAR: Show progress bar when running duckdb queries.
                        0 = no progress bar, 1 = show progress bar. Default is 0.
   :type PROGRESS_BAR: int


   .. py:attribute:: root_dir
      :value: '.tmp'



   .. py:attribute:: data_folder
      :value: 'explanations_data'



   .. py:attribute:: model_name
      :value: ''



   .. py:attribute:: from_date
      :value: None



   .. py:attribute:: to_date
      :value: None



   .. py:attribute:: preprocess


   .. py:attribute:: aggregate


   .. py:attribute:: plot


   .. py:attribute:: report


   .. py:attribute:: filter


   .. py:method:: _set_date_range(from_date: Optional[datetime.datetime], to_date: Optional[datetime.datetime], days: int = 7)

      Set the date range for processing explanation files.

      :param start_date: The start date for the date range. If None, defaults to 7 days before end_date.
      :type start_date: datetime, optional
      :param end_date: The end date for the date range. If None, defaults to today.
      :type end_date: datetime, optional