Source code for sktree.ensemble._multiview

from sklearn.utils._param_validation import StrOptions

from .._lib.sklearn.ensemble._forest import ForestClassifier
from ..tree import MultiViewDecisionTreeClassifier
from ..tree._neighbors import SimMatrixMixin


[docs] class MultiViewRandomForestClassifier(SimMatrixMixin, ForestClassifier): """ A multi-view axis-aligned random forest classifier. A multi-view random forest is a meta estimator similar to a random forest that fits a number of multi-view decision tree classifiers on various sub-samples of the dataset and uses averaging to improve the predictive accuracy and control over-fitting. Parameters ---------- n_estimators : int, default=100 The number of trees in the forest. criterion : {"gini", "entropy"}, default="gini" The function to measure the quality of a split. Supported criteria are "gini" for the Gini impurity and "entropy" for the information gain. Note: this parameter is tree-specific. max_depth : int, default=None The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples. min_samples_split : int or float, default=2 The minimum number of samples required to split an internal node: - If int, then consider `min_samples_split` as the minimum number. - If float, then `min_samples_split` is a fraction and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. min_samples_leaf : int or float, default=1 The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least ``min_samples_leaf`` training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression. - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a fraction and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. min_weight_fraction_leaf : float, default=0.0 The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided. max_features : {"sqrt", "log2", None}, int or float, default="sqrt" The number of features to consider when looking for the best split: - If int, then consider `max_features` features at each split. - If float, then `max_features` is a fraction and `round(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=sqrt(n_features)`. - If "sqrt", then `max_features=sqrt(n_features)`. - If "log2", then `max_features=log2(n_features)`. - If None, then `max_features=n_features`. Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than ``max_features`` features. max_leaf_nodes : int, default=None Grow trees with ``max_leaf_nodes`` in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes. min_impurity_decrease : float, default=0.0 A node will be split if this split induces a decrease of the impurity greater than or equal to this value. The weighted impurity decrease equation is the following:: N_t / N * (impurity - N_t_R / N_t * right_impurity - N_t_L / N_t * left_impurity) where ``N`` is the total number of samples, ``N_t`` is the number of samples at the current node, ``N_t_L`` is the number of samples in the left child, and ``N_t_R`` is the number of samples in the right child. ``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum, if ``sample_weight`` is passed. bootstrap : bool, default=True Whether bootstrap samples are used when building trees. If False, the whole dataset is used to build each tree. oob_score : bool, default=False Whether to use out-of-bag samples to estimate the generalization score. Only available if bootstrap=True. n_jobs : int, default=None The number of jobs to run in parallel. :meth:`fit`, :meth:`predict`, :meth:`decision_path` and :meth:`apply` are all parallelized over the trees. ``None`` means 1 unless in a `joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary <n_jobs>` for more details. random_state : int, RandomState instance or None, default=None Controls both the randomness of the bootstrapping of the samples used when building trees (if ``bootstrap=True``) and the sampling of the features to consider when looking for the best split at each node (if ``max_features < n_features``). See :term:`Glossary <random_state>` for details. verbose : int, default=0 Controls the verbosity when fitting and predicting. warm_start : bool, default=False When set to ``True``, reuse the solution of the previous call to fit and add more estimators to the ensemble, otherwise, just fit a whole new forest. See :term:`the Glossary <warm_start>`. class_weight : {"balanced", "balanced_subsample"}, dict or list of dicts, \ default=None Weights associated with classes in the form ``{class_label: weight}``. If not given, all classes are supposed to have weight one. For multi-output problems, a list of dicts can be provided in the same order as the columns of y. Note that for multioutput (including multilabel) weights should be defined for each class of every column in its own dict. For example, for four-class multilabel classification weights should be [{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of [{1:1}, {2:5}, {3:1}, {4:1}]. 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))`` The "balanced_subsample" mode is the same as "balanced" except that weights are computed based on the bootstrap sample for every tree grown. For multi-output, the weights of each column of y will be multiplied. Note that these weights will be multiplied with sample_weight (passed through the fit method) if sample_weight is specified. max_samples : int or float, default=None If bootstrap is True, the number of samples to draw from X to train each base estimator. - If None (default), then draw `X.shape[0]` samples. - If int, then draw `max_samples` samples. - If float, then draw `max_samples * X.shape[0]` samples. Thus, `max_samples` should be in the interval `(0.0, 1.0]`. feature_combinations : float, default=None The number of features to combine on average at each split of the decision trees. If ``None``, then will default to the minimum of ``(1.5, n_features)``. This controls the number of non-zeros is the projection matrix. Setting the value to 1.0 is equivalent to a traditional decision-tree. ``feature_combinations * max_features`` gives the number of expected non-zeros in the projection matrix of shape ``(max_features, n_features)``. Thus this value must always be less than ``n_features`` in order to be valid. feature_set_ends : array-like of int of shape (n_feature_sets,), default=None The indices of the end of each feature set. For example, if the first feature set is the first 10 features, and the second feature set is the next 20 features, then ``feature_set_ends = [10, 30]``. If ``None``, then this will assume that there is only one feature set. apply_max_features_per_feature_set : bool, default=False Whether to apply sampling per feature set, where ``max_features`` is applied to each feature-set. If ``False``, then sampling is applied over the entire feature space. Attributes ---------- estimators_ : list of sktree.tree.ObliqueDecisionTreeClassifier The collection of fitted sub-estimators. classes_ : ndarray of shape (n_classes,) or a list of such arrays The classes labels (single output problem), or a list of arrays of class labels (multi-output problem). n_classes_ : int or list The number of classes (single output problem), or a list containing the number of classes for each output (multi-output problem). n_features_ : int The number of features when ``fit`` is performed. n_features_in_ : int Number of features seen during :term:`fit`. feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. n_outputs_ : int The number of outputs when ``fit`` is performed. feature_importances_ : ndarray of shape (n_features,) The impurity-based feature importances. The higher, the more important the feature. The importance of a feature is computed as the (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance. Warning: impurity-based feature importances can be misleading for high cardinality features (many unique values). See :func:`sklearn.inspection.permutation_importance` as an alternative. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. This attribute exists only when ``oob_score`` is True. oob_decision_function_ : ndarray of shape (n_samples, n_classes) or \ (n_samples, n_classes, n_outputs) Decision function computed with out-of-bag estimate on the training set. If n_estimators is small it might be possible that a data point was never left out during the bootstrap. In this case, `oob_decision_function_` might contain NaN. This attribute exists only when ``oob_score`` is True. See Also -------- sktree.tree.ObliqueDecisionTreeClassifier : An oblique decision tree classifier. sklearn.ensemble.RandomForestClassifier : An axis-aligned decision forest classifier. """ tree_type = "oblique" _parameter_constraints: dict = { **ForestClassifier._parameter_constraints, **MultiViewDecisionTreeClassifier._parameter_constraints, "class_weight": [ StrOptions({"balanced_subsample", "balanced"}), dict, list, None, ], } _parameter_constraints.pop("splitter") def __init__( self, n_estimators=100, *, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="sqrt", max_leaf_nodes=None, min_impurity_decrease=0.0, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None, max_samples=None, feature_combinations=None, feature_set_ends=None, apply_max_features_per_feature_set=False, ): super().__init__( estimator=MultiViewDecisionTreeClassifier(), n_estimators=n_estimators, estimator_params=( "criterion", "max_depth", "min_samples_split", "min_samples_leaf", "min_weight_fraction_leaf", "max_features", "max_leaf_nodes", "min_impurity_decrease", "random_state", "feature_combinations", "feature_set_ends", "apply_max_features_per_feature_set", ), bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start, class_weight=class_weight, max_samples=max_samples, ) self.criterion = criterion self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.max_features = max_features self.feature_combinations = feature_combinations self.feature_set_ends = feature_set_ends self.apply_max_features_per_feature_set = apply_max_features_per_feature_set # unused by oblique forests self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_leaf_nodes = max_leaf_nodes self.min_impurity_decrease = min_impurity_decrease