demcompare.stats_dataset
========================

.. py:module:: demcompare.stats_dataset

.. autoapi-nested-parse::

   Mainly contains the StatsDataset class
   contains the computed stats of a pair of DEMs
   for the different classification layers



Classes
-------

.. autoapisummary::

   demcompare.stats_dataset.StatsDataset


Module Contents
---------------

.. py:class:: StatsDataset(image: numpy.ndarray, dem_processing_method: str = None)

   StatsDataset class

   The StatsDataset class contains a list of one
   xr.dataset per classification layer

   Each xr.Dataset contains :

   :image: 2D (row, col) input image as xarray.DataArray,

   :image_by_class: 3D (row, col; nb_classes)

       xarray.DataArray containing
       the image pixels belonging
       to each class considering the valid pixels

   :image_by_class_intersection: 3D (row, col; nb_classes)

       xarray.DataArray containing
       the image pixels belonging
       to each class considering the intersection mode

   :image_by_class_exclusion: 3D (row, col; nb_classes)

       xarray.DataArray containing
       the image pixels belonging
       to each class considering the exclusion mode

   :attributes:

               - name : name of the classification_layer. str

               - stats_by_class : dictionary containing
                 the stats per class considering the standard mode

               - stats_by_class_intersection : dictionary containing
                 the stats per class considering the intersection mode

               - stats_by_class_exclusion : dictionary containing
                 the stats per class considering the exclusion mode



   .. py:attribute:: classif_layers_and_modes
      :type:  Dict


   .. py:attribute:: image
      :type:  numpy.ndarray


   .. py:attribute:: classif_layers_dataset
      :type:  List[xarray.Dataset]
      :value: []



   .. py:method:: add_classif_layer_and_mode_stats(classif_name: str, input_stats: List[Dict], mode_name: str)

      Add the stats of a classification layer and
      a mode to the corresponding xarray dataset

      :param classif_name: classification_layer name
      :type classif_name: str
      :param input_stats: input statistics
      :type input_stats: List[str]
      :mode_name: name of the mode (standard (no name),
        intersection, exclusion)
      :type mode_name: str
      :return: None



   .. py:method:: save_as_csv_and_json(classif_name: str, stats_dir: str)

      Saves the classification layer's results to csv and json
      files on the stats_dir
      :param classif_name: classification_layer name
      :type classif_name: str
      :param stats_dir: output stats directory
      :type stats_dir: str
      :return: None



   .. py:method:: get_classification_layer_names()

      Returns the available classification layers

      :return: None



   .. py:method:: get_classification_layer_dataset(classification_layer: str) -> xarray.Dataset

      Returns the xr.Dataset corresponding to
      the input classification layer name

      :param classification_layer: classification_layer name
      :type classification_layer: str
      :return: stats dictionary
      :rtype: xr.Dataset



   .. py:method:: get_classification_layer_stats(classification_layer: str) -> Dict

      Returns all the stats corresponding to
      the input classification layer name

      :param classification_layer: classification_layer name
      :type classification_layer: str
      :return: stats dictionary
      :rtype: Dict



   .. py:method:: get_classification_layer_metrics(classification_layer: str) -> List[str]

      Returns the metric names available on the
      input classification layer and mode

      :param classification_layer: classification_layer name
      :type classification_layer: str
      :return: available metric names
      :rtype: List[str]



   .. py:method:: get_classification_layer_metric(classification_layer: str, classif_class: int = None, mode: str = '', metric: str = None) -> Union[List, Tuple[numpy.ndarray, numpy.ndarray], numpy.ndarray, float]

      Returns the metric corresponding to the
      input classification layer and mode

      :param classification_layer: classification_layer name
      :type classification_layer: str
      :param classif_class: classification_layer class
      :type classif_class: int
      :param mode: mode (standard (no name), intersection, exclusion)
      :type mode: str
      :param metric: metric
      :type metric: str
      :return: metric
      :rtype: Union[List,Tuple[np.ndarray, np.ndarray], np.ndarray, float]