Method __init__

python-package/lightgbmmt/sklearn.py:172–329

r"""Construct a gradient boosting model. Parameters ---------- boosting_type : string, optional (default='gbdt') 'gbdt', traditional Gradient Boosting Decision Tree. 'dart', Dropouts meet Multiple Additive Regression Trees. 'goss', Gradien

(self, boosting_type='gbdt', num_leaves=31, max_depth=-1,
                 learning_rate=0.1, n_estimators=100,
                 subsample_for_bin=200000, objective=None, class_weight=None,
                 min_split_gain=0., min_child_weight=1e-3, min_child_samples=20,
                 subsample=1., subsample_freq=0, colsample_bytree=1.,
                 reg_alpha=0., reg_lambda=0., random_state=None,
                 n_jobs=-1, silent=True, importance_type='split', **kwargs)

    """Implementation of the scikit-learn API for LightGBM."""

    def __init__(self, boosting_type='gbdt', num_leaves=31, max_depth=-1,
                 learning_rate=0.1, n_estimators=100,
                 subsample_for_bin=200000, objective=None, class_weight=None,
                 min_split_gain=0., min_child_weight=1e-3, min_child_samples=20,
                 subsample=1., subsample_freq=0, colsample_bytree=1.,
                 reg_alpha=0., reg_lambda=0., random_state=None,
                 n_jobs=-1, silent=True, importance_type='split', **kwargs):
        r"""Construct a gradient boosting model.

        Parameters
        ----------
        boosting_type : string, optional (default='gbdt')
            'gbdt', traditional Gradient Boosting Decision Tree.
            'dart', Dropouts meet Multiple Additive Regression Trees.
            'goss', Gradient-based One-Side Sampling.
            'rf', Random Forest.
        num_leaves : int, optional (default=31)
            Maximum tree leaves for base learners.
        max_depth : int, optional (default=-1)
            Maximum tree depth for base learners, <=0 means no limit.
        learning_rate : float, optional (default=0.1)
            Boosting learning rate.
            You can use ``callbacks`` parameter of ``fit`` method to shrink/adapt learning rate
            in training using ``reset_parameter`` callback.
            Note, that this will ignore the ``learning_rate`` argument in training.
        n_estimators : int, optional (default=100)
            Number of boosted trees to fit.
        subsample_for_bin : int, optional (default=200000)
            Number of samples for constructing bins.
        objective : string, callable or None, optional (default=None)
            Specify the learning task and the corresponding learning objective or
            a custom objective function to be used (see note below).
            Default: 'regression' for LGBMRegressor, 'binary' or 'multiclass' for LGBMClassifier, 'lambdarank' for LGBMRanker.
        class_weight : dict, 'balanced' or None, optional (default=None)
            Weights associated with classes in the form ``{class_label: weight}``.
            Use this parameter only for multi-class classification task;
            for binary classification task you may use ``is_unbalance`` or ``scale_pos_weight`` parameters.
            Note, that the usage of all these parameters will result in poor estimates of the individual class probabilities.
            You may want to consider performing probability calibration
            (https://scikit-learn.org/stable/modules/calibration.html) of your model.
            The 'balanced' mode uses the values of y to automatically adjust weights
            inversely proportional to class frequencies in the input data as ``n_samples / (n_classes * np.bincount(y))``.
            If None, all classes are supposed to have weight one.
            Note, that these weights will be multiplied with ``sample_weight`` (passed through the ``fit`` method)
            if ``sample_weight`` is specified.
        min_split_gain : float, optional (default=0.)
            Minimum loss reduction required to make a further partition on a leaf node of the tree.
        min_child_weight : float, optional (default=1e-3)
            Minimum sum of instance weight (hessian) needed in a child (leaf).
        min_child_samples : int, optional (default=20)
            Minimum number of data needed in a child (leaf).
        subsample : float, optional (default=1.)
            Subsample ratio of the training instance.
        subsample_freq : int, optional (default=0)
            Frequence of subsample, <=0 means no enable.
        colsample_bytree : float, optional (default=1.)
            Subsample ratio of columns when constructing each tree.
        reg_alpha : float, optional (default=0.)