:py:mod:`orcanet.history`
=========================

.. py:module:: orcanet.history


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

Classes
~~~~~~~

.. autoapisummary::

   orcanet.history.HistoryHandler




.. py:class:: HistoryHandler(main_folder)

   
   For reading and plotting data from summary and train log files.
















   ..
       !! processed by numpydoc !!
   .. py:property:: summary_file


   .. py:property:: train_log_folder


   .. py:method:: plot_metric(metric_name, **kwargs)

      
      Plot the training and validation history of a metric.

      This will read out data from the summary file, as well as
      all training log files, and plot them over the epoch.

      :Parameters:

          **metric_name** : str
              Name of the metric to be plotted over the epoch. This name is what
              was written in the head line of the summary.txt file, except without
              the train_ or val_ prefix.

          **kwargs**
              Keyword arguments for the plot_history function.














      ..
          !! processed by numpydoc !!

   .. py:method:: plot_lr(**kwargs)

      
      Plot the learning rate over the epochs.


      :Parameters:

          **kwargs**
              Keyword arguments for the plot_history function.

      :Returns:

          **fig** : matplotlib.figure.Figure
              The plot.













      ..
          !! processed by numpydoc !!

   .. py:method:: get_metrics()

      
      Get the name of the metrics from the first line in the summary file.

      This will be the actual name of the metric, i.e. "loss" and not
      "train_loss" or "val_loss".


      :Returns:

          **all_metrics** : List
              A list of the metrics.













      ..
          !! processed by numpydoc !!

   .. py:method:: get_summary_data()

      
      Read out the summary file in the output folder.



      :Returns:

          **summary_data** : ndarray
              Numpy structured array with the column names as datatypes.
              Its shape is the number of lines with data.













      ..
          !! processed by numpydoc !!

   .. py:method:: get_best_epoch_info(metric='val_loss', mini=True)

      
      Get the line in the summary file where the given metric is best, i.e.
      either minimal  or maximal.


      :Parameters:

          **metric** : str
              Which metric to look up.

          **mini** : bool
              If true, look up the minimum. Else the maximum.





      :Raises:

          ValueError
              If there is no best line (e.g. no validation has been done).









      ..
          !! processed by numpydoc !!

   .. py:method:: get_best_epoch_fileno(metric='val_loss', mini=True)

      
      Get the epoch/fileno tuple where the given metric is smallest.
















      ..
          !! processed by numpydoc !!

   .. py:method:: get_column_names()

      
      Get the str in the first line in each column.



      :Returns:

          **tuple** : column_names
              The names in the same order as they appear in the summary.txt.













      ..
          !! processed by numpydoc !!

   .. py:method:: get_train_data()

      
      Read out all training logfiles in the output folder.

      Read out the data from the summary.txt file, and from all training
      log files in the train_log folder, which is in the same directory
      as the summary.txt file.


      :Returns:

          **summary_data** : numpy.ndarray
              Structured array containing the data from the summary.txt file.
              Its shape is the number of lines with data.













      ..
          !! processed by numpydoc !!

   .. py:method:: get_state()

      
      Get the state of a training.

      For every line in the summary logfile, get a dict with the epoch
      as a float, and is_trained and is_validated bools.


      :Returns:

          **state_dicts** : List
              List of dicts.













      ..
          !! processed by numpydoc !!