ordinalgbt.lgb
==============

.. py:module:: ordinalgbt.lgb

.. autoapi-nested-parse::

   Ordinal classifier lightgbm implementation



Classes
-------

.. autoapisummary::

   ordinalgbt.lgb.LGBMOrdinal


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

.. py:class:: LGBMOrdinal(boosting_type: str = 'gbdt', num_leaves: int = 31, max_depth: int = -1, learning_rate: float = 0.1, n_estimators: int = 100, subsample_for_bin: int = 200000, objective='immediate-thresholds', class_weight=None, min_split_gain: float = 0.0, min_child_weight: float = 0.001, min_child_samples: int = 20, subsample: float = 1.0, subsample_freq: int = 0, colsample_bytree: float = 1.0, reg_alpha: float = 0.0, reg_lambda: float = 0.0, random_state=None, n_jobs: int = -1, silent='warn', importance_type: str = 'split', **kwargs)

   Bases: :py:obj:`lightgbm.LGBMRegressor`


   .. py:method:: _initialise_theta()


   .. py:method:: _lgb_loss_factory()


   .. py:method:: _alpha_loss_factory(y_true, y_preds)
      :staticmethod:


      Creates loss parametrised by alpha



   .. py:method:: _optimise_alpha(y_true, y_preds)

      Takes loss parametrised by alpha and optimises it.
      Can optionally take in gradient.



   .. py:method:: _initialise_objective(y)

      initialises the objective by creating the loss and setting the class
      attributes



   .. py:method:: _output_to_probability(output)


   .. py:method:: _hot_start(X, y, hot_start_iterations=5, **kwargs)

      TODO



   .. py:method:: fit(X, y, hot_start_iterations=5, sample_weight=None, init_score=None, eval_set=None, eval_names=None, eval_sample_weight=None, eval_init_score=None, eval_metric=None, early_stopping_rounds=None, verbose='warn', feature_name='auto', categorical_feature='auto', callbacks=None, init_model=None) -> LGBMOrdinal

      Docstring is inherited from the LGBMModel.



   .. py:method:: _fit(X, y, sample_weight=None, init_score=None, eval_set=None, eval_names=None, eval_sample_weight=None, eval_init_score=None, eval_metric=None, early_stopping_rounds=None, verbose='warn', feature_name='auto', categorical_feature='auto', callbacks=None, init_model=None) -> LGBMOrdinal

      Docstring is inherited from the LGBMModel.



   .. py:method:: predict(X, start_iteration=0, num_iteration=None, pred_leaf=False, pred_contrib=False, **kwargs)


   .. py:method:: predict_proba(X, raw_score=False, start_iteration=0, num_iteration=None, pred_leaf=False, pred_contrib=False, **kwargs)