cgeniepy.skill
==============

.. py:module:: cgeniepy.skill


Classes
-------

.. autoapisummary::

   cgeniepy.skill.ArrComparison
   cgeniepy.skill.DFComparison
   cgeniepy.skill.TaylorDiagram


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

.. py:class:: ArrComparison(model, observation, model_name='Model', obs_name='Observation', label=None)

   quantitatively compare similarity metrics between two 2D arrays (model and observation)


   .. py:attribute:: model


   .. py:attribute:: data


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



   .. py:attribute:: obs_name
      :value: 'Observation'



   .. py:attribute:: label
      :value: None



   .. py:method:: safe_unveil(array)

      get pure array from a numpy masked array object



   .. py:method:: intersect_index(verbose=False)

      Return the index where corresponding values are not
      nan in both input arrays. One then can filter the array
      by the output boolean array.



   .. py:method:: mscore()

      Calculate skill metric M-score. See more in the paper Watterson, I. G. (1996)



   .. py:method:: pearson_r()

      calculate pearson correlation coefficient for 2D array



   .. py:method:: spearman_r()

      calculate spearman correlation



   .. py:method:: mae()

      Mean Absolute Error (MAE)



   .. py:method:: cos_similarity()

      Cosine similarity that ignores the magnitude of data, but focuses on the direction



   .. py:method:: rmse()

      Root Mean Sqaure Error (rmse, or rmsd)



   .. py:method:: mse()

      Mean Squared Error (MSE)



   .. py:method:: nrmse()

      Normalised RMSE facilitating the comparison between datasets or models with different scales



   .. py:method:: crmse()

      centred Root Mean Sqaure Error (rmse, or rmsd). See Talor, K. E. (2001) JGR



   .. py:method:: lm_pvalue(method='pearson')

      get p-value from linear regression



   .. py:method:: plot(ax=None, diagonal=True, log_scale=False, title='Model vs Observation', savefig_name=None, metric=['rmse', 'r2', 'm', 'p'], *args, **kwargs)


.. py:class:: DFComparison(df, model_col, observation_col, *args, **kwargs)

   Bases: :py:obj:`ArrComparison`


   Quantitatively compare similarity metrics between two columns in a dataframe-like objects


   .. py:attribute:: model


   .. py:attribute:: data


.. py:class:: TaylorDiagram(ac: Union[ArrComparison, list])

   Bases: :py:obj:`object`


   Taylor diagram.

   A visualisation of model-data comparison considering (1) RMSE; (2) Correlation; (3) Standard Deviation.

   In practical it is a polar axis with point with `std` as radiance and `corr` as theta.
   The cRMSE then measures the distance from reference point, which is at (ref_std, 0)

   see https://en.wikipedia.org/wiki/Taylor_diagram#/media/File:Taylor_diagram_fig2.png
   and https://bookdown.org/david_carslaw/openair/sections/model-evaluation/taylor-diagram.html (Figure 20.2)

   This class is modified from Yannick Copin, https://gist.github.com/ycopin/3342888


   .. py:attribute:: ac


   .. py:method:: extract_data()


   .. py:method:: setup_ax(fig=None, positive_only=True, crmse_contour=False)


   .. py:method:: add_point(correlation, std, *args, **kwargs)


   .. py:method:: plot(cmap=None, add_legend=True, *args, **kwargs)


   .. py:method:: savefig(*args, **kwargs)


   .. py:method:: add_line(theta1, radius1, theta2, radius2, *args, **kwargs)

      Add a line in the polar axis

      If you need to convert the correlation into theta/radian, use np.arccos(correlation)