base_environment
================

.. py:module:: base_environment


Classes
-------

.. autoapisummary::

   base_environment.BaseTradingEnv


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

.. py:class:: BaseTradingEnv(data, cfg, features, time_step = (TimeFrameUnit.Day, 1))

   Bases: :py:obj:`gymnasium.Env`, :py:obj:`abc.ABC`


   Base trading environment for reinforcement learning agents.
   Contains common functionality shared between training and testing environments.


   .. py:attribute:: symbols


   .. py:attribute:: stock_dimension


   .. py:attribute:: features


   .. py:attribute:: feature_cols


   .. py:attribute:: cfg
      :type:  trading.cli.alg.config.StockEnv


   .. py:attribute:: time_step


   .. py:attribute:: action_space


   .. py:attribute:: observation_space


   .. py:attribute:: observation_index


   .. py:attribute:: terminal
      :value: False



   .. py:attribute:: observation_timestamp
      :value: None



   .. py:method:: init_data(data)

      Set the data for the environment.
      :param data: DataFrame containing the trading data.



   .. py:method:: observation(df, portfolio_state, feature_cols, prices)
      :classmethod:


      Build observation from dataframe, portfolio state, and prices.



   .. py:method:: _get_observation_df(i = -1)

      Get the dataframe slice for observation at index i.



   .. py:method:: _get_prices(i = -1)

      Get prices at index i.



   .. py:method:: _get_observation(i = -1)
      :abstractmethod:


      Get the current observation from the environment.



   .. py:method:: reset(*, seed = None, options = None)

      Reset the environment to its initial state. Can be overridden by subclasses.



   .. py:method:: step(action)
      :abstractmethod:


      Execute one time step within the environment.



   .. py:method:: render()

      Render the environment state.



   .. py:method:: _reset_internal_states(timestamp = None)

      Reset internal state counters.