"""Forest of trees-based ensemble methods Those methods include random forests and extremely randomized trees. The module structure is the following: - The ``BaseForest`` base class implements a common ``fit`` method for all the estimators in the module. The ``fit`` method of the base ``Forest`` class calls the ``fit`` method of each sub-estimator on random samples (with replacement, a.k.a. bootstrap) of the training set. The init of the sub-estimator is further delegated to the ``BaseEnsemble`` constructor. - The ``ForestClassifier`` and ``ForestRegressor`` base classes further implement the prediction logic by computing an average of the predicted outcomes of the sub-estimators. - The ``RandomForestClassifier`` and ``RandomForestRegressor`` derived classes provide the user with concrete implementations of the forest ensemble method using classical, deterministic ``DecisionTreeClassifier`` and ``DecisionTreeRegressor`` as sub-estimator implementations. - The ``ExtraTreesClassifier`` and ``ExtraTreesRegressor`` derived classes provide the user with concrete implementations of the forest ensemble method using the extremely randomized trees ``ExtraTreeClassifier`` and ``ExtraTreeRegressor`` as sub-estimator implementations. Single and multi-output problems are both handled. """ # Authors: Gilles Louppe # Brian Holt # Joly Arnaud # Fares Hedayati # # License: BSD 3 clause from __future__ import division import warnings from warnings import warn from abc import ABCMeta, abstractmethod import numpy as np from scipy.sparse import issparse from scipy.sparse import hstack as sparse_hstack from ..base import ClassifierMixin, RegressorMixin from ..externals.joblib import Parallel, delayed from ..externals import six from ..feature_selection.from_model import _LearntSelectorMixin from ..metrics import r2_score from ..preprocessing import OneHotEncoder from ..tree import (DecisionTreeClassifier, DecisionTreeRegressor, ExtraTreeClassifier, ExtraTreeRegressor) from ..tree._tree import DTYPE, DOUBLE from ..utils import check_random_state, check_array, compute_sample_weight from ..exceptions import DataConversionWarning, NotFittedError from .base import BaseEnsemble, _partition_estimators from ..utils.fixes import bincount, parallel_helper from ..utils.multiclass import check_classification_targets __all__ = ["RandomForestClassifier", "RandomForestRegressor", "ExtraTreesClassifier", "ExtraTreesRegressor", "RandomTreesEmbedding"] MAX_INT = np.iinfo(np.int32).max def _generate_sample_indices(random_state, n_samples): """Private function used to _parallel_build_trees function.""" random_instance = check_random_state(random_state) sample_indices = random_instance.randint(0, n_samples, n_samples) return sample_indices def _generate_unsampled_indices(random_state, n_samples): """Private function used to forest._set_oob_score function.""" sample_indices = _generate_sample_indices(random_state, n_samples) sample_counts = bincount(sample_indices, minlength=n_samples) unsampled_mask = sample_counts == 0 indices_range = np.arange(n_samples) unsampled_indices = indices_range[unsampled_mask] return unsampled_indices def _parallel_build_trees(tree, forest, X, y, sample_weight, tree_idx, n_trees, verbose=0, class_weight=None): """Private function used to fit a single tree in parallel.""" if verbose > 1: print("building tree %d of %d" % (tree_idx + 1, n_trees)) if forest.bootstrap: n_samples = X.shape[0] if sample_weight is None: curr_sample_weight = np.ones((n_samples,), dtype=np.float64) else: curr_sample_weight = sample_weight.copy() indices = _generate_sample_indices(tree.random_state, n_samples) sample_counts = bincount(indices, minlength=n_samples) curr_sample_weight *= sample_counts if class_weight == 'subsample': with warnings.catch_warnings(): warnings.simplefilter('ignore', DeprecationWarning) curr_sample_weight *= compute_sample_weight('auto', y, indices) elif class_weight == 'balanced_subsample': curr_sample_weight *= compute_sample_weight('balanced', y, indices) tree.fit(X, y, sample_weight=curr_sample_weight, check_input=False) else: tree.fit(X, y, sample_weight=sample_weight, check_input=False) return tree class BaseForest(six.with_metaclass(ABCMeta, BaseEnsemble, _LearntSelectorMixin)): """Base class for forests of trees. Warning: This class should not be used directly. Use derived classes instead. """ @abstractmethod def __init__(self, base_estimator, n_estimators=10, estimator_params=tuple(), bootstrap=False, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False, class_weight=None): super(BaseForest, self).__init__( base_estimator=base_estimator, n_estimators=n_estimators, estimator_params=estimator_params) self.bootstrap = bootstrap self.oob_score = oob_score self.n_jobs = n_jobs self.random_state = random_state self.verbose = verbose self.warm_start = warm_start self.class_weight = class_weight def apply(self, X): """Apply trees in the forest to X, return leaf indices. Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- X_leaves : array_like, shape = [n_samples, n_estimators] For each datapoint x in X and for each tree in the forest, return the index of the leaf x ends up in. """ X = self._validate_X_predict(X) results = Parallel(n_jobs=self.n_jobs, verbose=self.verbose, backend="threading")( delayed(parallel_helper)(tree, 'apply', X, check_input=False) for tree in self.estimators_) return np.array(results).T def decision_path(self, X): """Return the decision path in the forest .. versionadded:: 0.18 Parameters ---------- X : array-like or sparse matrix, shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- indicator : sparse csr array, shape = [n_samples, n_nodes] Return a node indicator matrix where non zero elements indicates that the samples goes through the nodes. n_nodes_ptr : array of size (n_estimators + 1, ) The columns from indicator[n_nodes_ptr[i]:n_nodes_ptr[i+1]] gives the indicator value for the i-th estimator. """ X = self._validate_X_predict(X) indicators = Parallel(n_jobs=self.n_jobs, verbose=self.verbose, backend="threading")( delayed(parallel_helper)(tree, 'decision_path', X, check_input=False) for tree in self.estimators_) n_nodes = [0] n_nodes.extend([i.shape[1] for i in indicators]) n_nodes_ptr = np.array(n_nodes).cumsum() return sparse_hstack(indicators).tocsr(), n_nodes_ptr def fit(self, X, y, sample_weight=None): """Build a forest of trees from the training set (X, y). Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The training input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csc_matrix``. y : array-like, shape = [n_samples] or [n_samples, n_outputs] The target values (class labels in classification, real numbers in regression). sample_weight : array-like, shape = [n_samples] or None Sample weights. If None, then samples are equally weighted. Splits that would create child nodes with net zero or negative weight are ignored while searching for a split in each node. In the case of classification, splits are also ignored if they would result in any single class carrying a negative weight in either child node. Returns ------- self : object Returns self. """ # Validate or convert input data X = check_array(X, accept_sparse="csc", dtype=DTYPE) y = check_array(y, accept_sparse='csc', ensure_2d=False, dtype=None) if issparse(X): # Pre-sort indices to avoid that each individual tree of the # ensemble sorts the indices. X.sort_indices() # Remap output n_samples, self.n_features_ = X.shape y = np.atleast_1d(y) if y.ndim == 2 and y.shape[1] == 1: warn("A column-vector y was passed when a 1d array was" " expected. Please change the shape of y to " "(n_samples,), for example using ravel().", DataConversionWarning, stacklevel=2) if y.ndim == 1: # reshape is necessary to preserve the data contiguity against vs # [:, np.newaxis] that does not. y = np.reshape(y, (-1, 1)) self.n_outputs_ = y.shape[1] y, expanded_class_weight = self._validate_y_class_weight(y) if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous: y = np.ascontiguousarray(y, dtype=DOUBLE) if expanded_class_weight is not None: if sample_weight is not None: sample_weight = sample_weight * expanded_class_weight else: sample_weight = expanded_class_weight # Check parameters self._validate_estimator() if not self.bootstrap and self.oob_score: raise ValueError("Out of bag estimation only available" " if bootstrap=True") random_state = check_random_state(self.random_state) if not self.warm_start: # Free allocated memory, if any self.estimators_ = [] n_more_estimators = self.n_estimators - len(self.estimators_) if n_more_estimators < 0: raise ValueError('n_estimators=%d must be larger or equal to ' 'len(estimators_)=%d when warm_start==True' % (self.n_estimators, len(self.estimators_))) elif n_more_estimators == 0: warn("Warm-start fitting without increasing n_estimators does not " "fit new trees.") else: if self.warm_start and len(self.estimators_) > 0: # We draw from the random state to get the random state we # would have got if we hadn't used a warm_start. random_state.randint(MAX_INT, size=len(self.estimators_)) trees = [] for i in range(n_more_estimators): tree = self._make_estimator(append=False, random_state=random_state) trees.append(tree) # Parallel loop: we use the threading backend as the Cython code # for fitting the trees is internally releasing the Python GIL # making threading always more efficient than multiprocessing in # that case. trees = Parallel(n_jobs=self.n_jobs, verbose=self.verbose, backend="threading")( delayed(_parallel_build_trees)( t, self, X, y, sample_weight, i, len(trees), verbose=self.verbose, class_weight=self.class_weight) for i, t in enumerate(trees)) # Collect newly grown trees self.estimators_.extend(trees) if self.oob_score: self._set_oob_score(X, y) # Decapsulate classes_ attributes if hasattr(self, "classes_") and self.n_outputs_ == 1: self.n_classes_ = self.n_classes_[0] self.classes_ = self.classes_[0] return self @abstractmethod def _set_oob_score(self, X, y): """Calculate out of bag predictions and score.""" def _validate_y_class_weight(self, y): # Default implementation return y, None def _validate_X_predict(self, X): """Validate X whenever one tries to predict, apply, predict_proba""" if self.estimators_ is None or len(self.estimators_) == 0: raise NotFittedError("Estimator not fitted, " "call `fit` before exploiting the model.") return self.estimators_[0]._validate_X_predict(X, check_input=True) @property def feature_importances_(self): """Return the feature importances (the higher, the more important the feature). Returns ------- feature_importances_ : array, shape = [n_features] """ if self.estimators_ is None or len(self.estimators_) == 0: raise NotFittedError("Estimator not fitted, " "call `fit` before `feature_importances_`.") all_importances = Parallel(n_jobs=self.n_jobs, backend="threading")( delayed(getattr)(tree, 'feature_importances_') for tree in self.estimators_) return sum(all_importances) / len(self.estimators_) class ForestClassifier(six.with_metaclass(ABCMeta, BaseForest, ClassifierMixin)): """Base class for forest of trees-based classifiers. Warning: This class should not be used directly. Use derived classes instead. """ @abstractmethod def __init__(self, base_estimator, n_estimators=10, estimator_params=tuple(), bootstrap=False, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False, class_weight=None): super(ForestClassifier, self).__init__( base_estimator, n_estimators=n_estimators, estimator_params=estimator_params, bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start, class_weight=class_weight) def _set_oob_score(self, X, y): """Compute out-of-bag score""" X = check_array(X, dtype=DTYPE, accept_sparse='csr') n_classes_ = self.n_classes_ n_samples = y.shape[0] oob_decision_function = [] oob_score = 0.0 predictions = [] for k in range(self.n_outputs_): predictions.append(np.zeros((n_samples, n_classes_[k]))) for estimator in self.estimators_: unsampled_indices = _generate_unsampled_indices( estimator.random_state, n_samples) p_estimator = estimator.predict_proba(X[unsampled_indices, :], check_input=False) if self.n_outputs_ == 1: p_estimator = [p_estimator] for k in range(self.n_outputs_): predictions[k][unsampled_indices, :] += p_estimator[k] for k in range(self.n_outputs_): if (predictions[k].sum(axis=1) == 0).any(): warn("Some inputs do not have OOB scores. " "This probably means too few trees were used " "to compute any reliable oob estimates.") decision = (predictions[k] / predictions[k].sum(axis=1)[:, np.newaxis]) oob_decision_function.append(decision) oob_score += np.mean(y[:, k] == np.argmax(predictions[k], axis=1), axis=0) if self.n_outputs_ == 1: self.oob_decision_function_ = oob_decision_function[0] else: self.oob_decision_function_ = oob_decision_function self.oob_score_ = oob_score / self.n_outputs_ def _validate_y_class_weight(self, y): check_classification_targets(y) y = np.copy(y) expanded_class_weight = None if self.class_weight is not None: y_original = np.copy(y) self.classes_ = [] self.n_classes_ = [] y_store_unique_indices = np.zeros(y.shape, dtype=np.int) for k in range(self.n_outputs_): classes_k, y_store_unique_indices[:, k] = np.unique(y[:, k], return_inverse=True) self.classes_.append(classes_k) self.n_classes_.append(classes_k.shape[0]) y = y_store_unique_indices if self.class_weight is not None: valid_presets = ('auto', 'balanced', 'subsample', 'balanced_subsample') if isinstance(self.class_weight, six.string_types): if self.class_weight not in valid_presets: raise ValueError('Valid presets for class_weight include ' '"balanced" and "balanced_subsample". Given "%s".' % self.class_weight) if self.class_weight == "subsample": warn("class_weight='subsample' is deprecated in 0.17 and" "will be removed in 0.19. It was replaced by " "class_weight='balanced_subsample' using the balanced" "strategy.", DeprecationWarning) if self.warm_start: warn('class_weight presets "balanced" or "balanced_subsample" are ' 'not recommended for warm_start if the fitted data ' 'differs from the full dataset. In order to use ' '"balanced" weights, use compute_class_weight("balanced", ' 'classes, y). In place of y you can use a large ' 'enough sample of the full training set target to ' 'properly estimate the class frequency ' 'distributions. Pass the resulting weights as the ' 'class_weight parameter.') if (self.class_weight not in ['subsample', 'balanced_subsample'] or not self.bootstrap): if self.class_weight == 'subsample': class_weight = 'auto' elif self.class_weight == "balanced_subsample": class_weight = "balanced" else: class_weight = self.class_weight with warnings.catch_warnings(): if class_weight == "auto": warnings.simplefilter('ignore', DeprecationWarning) expanded_class_weight = compute_sample_weight(class_weight, y_original) return y, expanded_class_weight def predict(self, X): """Predict class for X. The predicted class of an input sample is a vote by the trees in the forest, weighted by their probability estimates. That is, the predicted class is the one with highest mean probability estimate across the trees. Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- y : array of shape = [n_samples] or [n_samples, n_outputs] The predicted classes. """ proba = self.predict_proba(X) if self.n_outputs_ == 1: return self.classes_.take(np.argmax(proba, axis=1), axis=0) else: n_samples = proba[0].shape[0] predictions = np.zeros((n_samples, self.n_outputs_)) for k in range(self.n_outputs_): predictions[:, k] = self.classes_[k].take(np.argmax(proba[k], axis=1), axis=0) return predictions def predict_proba(self, X): """Predict class probabilities for X. The predicted class probabilities of an input sample are computed as the mean predicted class probabilities of the trees in the forest. The class probability of a single tree is the fraction of samples of the same class in a leaf. Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- p : array of shape = [n_samples, n_classes], or a list of n_outputs such arrays if n_outputs > 1. The class probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. """ # Check data X = self._validate_X_predict(X) # Assign chunk of trees to jobs n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs) # Parallel loop all_proba = Parallel(n_jobs=n_jobs, verbose=self.verbose, backend="threading")( delayed(parallel_helper)(e, 'predict_proba', X, check_input=False) for e in self.estimators_) # Reduce proba = all_proba[0] if self.n_outputs_ == 1: for j in range(1, len(all_proba)): proba += all_proba[j] proba /= len(self.estimators_) else: for j in range(1, len(all_proba)): for k in range(self.n_outputs_): proba[k] += all_proba[j][k] for k in range(self.n_outputs_): proba[k] /= self.n_estimators return proba def predict_log_proba(self, X): """Predict class log-probabilities for X. The predicted class log-probabilities of an input sample is computed as the log of the mean predicted class probabilities of the trees in the forest. Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- p : array of shape = [n_samples, n_classes], or a list of n_outputs such arrays if n_outputs > 1. The class probabilities of the input samples. The order of the classes corresponds to that in the attribute `classes_`. """ proba = self.predict_proba(X) if self.n_outputs_ == 1: return np.log(proba) else: for k in range(self.n_outputs_): proba[k] = np.log(proba[k]) return proba class ForestRegressor(six.with_metaclass(ABCMeta, BaseForest, RegressorMixin)): """Base class for forest of trees-based regressors. Warning: This class should not be used directly. Use derived classes instead. """ @abstractmethod def __init__(self, base_estimator, n_estimators=10, estimator_params=tuple(), bootstrap=False, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False): super(ForestRegressor, self).__init__( base_estimator, n_estimators=n_estimators, estimator_params=estimator_params, bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start) def predict(self, X): """Predict regression target for X. The predicted regression target of an input sample is computed as the mean predicted regression targets of the trees in the forest. Parameters ---------- X : array-like or sparse matrix of shape = [n_samples, n_features] The input samples. Internally, its dtype will be converted to ``dtype=np.float32``. If a sparse matrix is provided, it will be converted into a sparse ``csr_matrix``. Returns ------- y : array of shape = [n_samples] or [n_samples, n_outputs] The predicted values. """ # Check data X = self._validate_X_predict(X) # Assign chunk of trees to jobs n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs) # Parallel loop all_y_hat = Parallel(n_jobs=n_jobs, verbose=self.verbose, backend="threading")( delayed(parallel_helper)(e, 'predict', X, check_input=False) for e in self.estimators_) # Reduce y_hat = sum(all_y_hat) / len(self.estimators_) return y_hat def _set_oob_score(self, X, y): """Compute out-of-bag scores""" X = check_array(X, dtype=DTYPE, accept_sparse='csr') n_samples = y.shape[0] predictions = np.zeros((n_samples, self.n_outputs_)) n_predictions = np.zeros((n_samples, self.n_outputs_)) for estimator in self.estimators_: unsampled_indices = _generate_unsampled_indices( estimator.random_state, n_samples) p_estimator = estimator.predict( X[unsampled_indices, :], check_input=False) if self.n_outputs_ == 1: p_estimator = p_estimator[:, np.newaxis] predictions[unsampled_indices, :] += p_estimator n_predictions[unsampled_indices, :] += 1 if (n_predictions == 0).any(): warn("Some inputs do not have OOB scores. " "This probably means too few trees were used " "to compute any reliable oob estimates.") n_predictions[n_predictions == 0] = 1 predictions /= n_predictions self.oob_prediction_ = predictions if self.n_outputs_ == 1: self.oob_prediction_ = \ self.oob_prediction_.reshape((n_samples, )) self.oob_score_ = 0.0 for k in range(self.n_outputs_): self.oob_score_ += r2_score(y[:, k], predictions[:, k]) self.oob_score_ /= self.n_outputs_ class RandomForestClassifier(ForestClassifier): """A random forest classifier. A random forest is a meta estimator that fits a number of decision tree classifiers on various sub-samples of the dataset and use averaging to improve the predictive accuracy and control over-fitting. The sub-sample size is always the same as the original input sample size but the samples are drawn with replacement if `bootstrap=True` (default). Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. criterion : string, optional (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_features : int, float, string or None, optional (default="auto") 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 percentage and `int(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)` (same as "auto"). - 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_depth : integer or None, optional (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, float, optional (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 percentage and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for percentages. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node: - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a percentage and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for percentages. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the input samples required to be at a leaf node. max_leaf_nodes : int or None, optional (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_split : float, optional (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. versionadded:: 0.18 bootstrap : boolean, optional (default=True) Whether bootstrap samples are used when building trees. oob_score : bool (default=False) Whether to use out-of-bag samples to estimate the generalization accuracy. n_jobs : integer, optional (default=1) The number of jobs to run in parallel for both `fit` and `predict`. If -1, then the number of jobs is set to the number of cores. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity of the tree building process. warm_start : bool, optional (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. class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional (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. 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. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. classes_ : array 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_outputs_ : int The number of outputs when ``fit`` is performed. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_decision_function_ : array of shape = [n_samples, n_classes] 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. References ---------- .. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001. See also -------- DecisionTreeClassifier, ExtraTreesClassifier """ def __init__(self, n_estimators=10, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0., max_features="auto", max_leaf_nodes=None, min_impurity_split=1e-7, bootstrap=True, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False, class_weight=None): super(RandomForestClassifier, self).__init__( base_estimator=DecisionTreeClassifier(), 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_split", "random_state"), bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start, class_weight=class_weight) self.criterion = criterion self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_features = max_features self.max_leaf_nodes = max_leaf_nodes self.min_impurity_split = min_impurity_split class RandomForestRegressor(ForestRegressor): """A random forest regressor. A random forest is a meta estimator that fits a number of classifying decision trees on various sub-samples of the dataset and use averaging to improve the predictive accuracy and control over-fitting. The sub-sample size is always the same as the original input sample size but the samples are drawn with replacement if `bootstrap=True` (default). Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. criterion : string, optional (default="mse") The function to measure the quality of a split. Supported criteria are "mse" for the mean squared error, which is equal to variance reduction as feature selection criterion, and "mae" for the mean absolute error. .. versionadded:: 0.18 Mean Absolute Error (MAE) criterion. max_features : int, float, string or None, optional (default="auto") 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 percentage and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=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_depth : integer or None, optional (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, float, optional (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 percentage and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for percentages. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node: - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a percentage and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for percentages. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the input samples required to be at a leaf node. max_leaf_nodes : int or None, optional (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_split : float, optional (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. versionadded:: 0.18 bootstrap : boolean, optional (default=True) Whether bootstrap samples are used when building trees. oob_score : bool, optional (default=False) whether to use out-of-bag samples to estimate the R^2 on unseen data. n_jobs : integer, optional (default=1) The number of jobs to run in parallel for both `fit` and `predict`. If -1, then the number of jobs is set to the number of cores. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity of the tree building process. warm_start : bool, optional (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. Attributes ---------- estimators_ : list of DecisionTreeRegressor The collection of fitted sub-estimators. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features when ``fit`` is performed. n_outputs_ : int The number of outputs when ``fit`` is performed. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_prediction_ : array of shape = [n_samples] Prediction computed with out-of-bag estimate on the training set. References ---------- .. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32, 2001. See also -------- DecisionTreeRegressor, ExtraTreesRegressor """ def __init__(self, n_estimators=10, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0., max_features="auto", max_leaf_nodes=None, min_impurity_split=1e-7, bootstrap=True, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False): super(RandomForestRegressor, self).__init__( base_estimator=DecisionTreeRegressor(), 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_split", "random_state"), bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start) self.criterion = criterion self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_features = max_features self.max_leaf_nodes = max_leaf_nodes self.min_impurity_split = min_impurity_split class ExtraTreesClassifier(ForestClassifier): """An extra-trees classifier. This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset and use averaging to improve the predictive accuracy and control over-fitting. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. criterion : string, optional (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. max_features : int, float, string or None, optional (default="auto") 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 percentage and `int(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_depth : integer or None, optional (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, float, optional (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 percentage and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for percentages. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node: - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a percentage and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for percentages. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the input samples required to be at a leaf node. max_leaf_nodes : int or None, optional (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_split : float, optional (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. versionadded:: 0.18 bootstrap : boolean, optional (default=False) Whether bootstrap samples are used when building trees. oob_score : bool, optional (default=False) Whether to use out-of-bag samples to estimate the generalization accuracy. n_jobs : integer, optional (default=1) The number of jobs to run in parallel for both `fit` and `predict`. If -1, then the number of jobs is set to the number of cores. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity of the tree building process. warm_start : bool, optional (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. class_weight : dict, list of dicts, "balanced", "balanced_subsample" or None, optional (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. 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. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. classes_ : array 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). feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features when ``fit`` is performed. n_outputs_ : int The number of outputs when ``fit`` is performed. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_decision_function_ : array of shape = [n_samples, n_classes] 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. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. See also -------- sklearn.tree.ExtraTreeClassifier : Base classifier for this ensemble. RandomForestClassifier : Ensemble Classifier based on trees with optimal splits. """ def __init__(self, n_estimators=10, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0., max_features="auto", max_leaf_nodes=None, min_impurity_split=1e-7, bootstrap=False, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False, class_weight=None): super(ExtraTreesClassifier, self).__init__( base_estimator=ExtraTreeClassifier(), 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_split", "random_state"), bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start, class_weight=class_weight) self.criterion = criterion self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_features = max_features self.max_leaf_nodes = max_leaf_nodes self.min_impurity_split = min_impurity_split class ExtraTreesRegressor(ForestRegressor): """An extra-trees regressor. This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset and use averaging to improve the predictive accuracy and control over-fitting. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) The number of trees in the forest. criterion : string, optional (default="mse") The function to measure the quality of a split. Supported criteria are "mse" for the mean squared error, which is equal to variance reduction as feature selection criterion, and "mae" for the mean absolute error. .. versionadded:: 0.18 Mean Absolute Error (MAE) criterion. max_features : int, float, string or None, optional (default="auto") 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 percentage and `int(max_features * n_features)` features are considered at each split. - If "auto", then `max_features=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_depth : integer or None, optional (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, float, optional (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 percentage and `ceil(min_samples_split * n_samples)` are the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for percentages. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node: - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a percentage and `ceil(min_samples_leaf * n_samples)` are the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for percentages. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the input samples required to be at a leaf node. max_leaf_nodes : int or None, optional (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_split : float, optional (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. versionadded:: 0.18 bootstrap : boolean, optional (default=False) Whether bootstrap samples are used when building trees. oob_score : bool, optional (default=False) Whether to use out-of-bag samples to estimate the R^2 on unseen data. n_jobs : integer, optional (default=1) The number of jobs to run in parallel for both `fit` and `predict`. If -1, then the number of jobs is set to the number of cores. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity of the tree building process. warm_start : bool, optional (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. Attributes ---------- estimators_ : list of DecisionTreeRegressor The collection of fitted sub-estimators. feature_importances_ : array of shape = [n_features] The feature importances (the higher, the more important the feature). n_features_ : int The number of features. n_outputs_ : int The number of outputs. oob_score_ : float Score of the training dataset obtained using an out-of-bag estimate. oob_prediction_ : array of shape = [n_samples] Prediction computed with out-of-bag estimate on the training set. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. See also -------- sklearn.tree.ExtraTreeRegressor: Base estimator for this ensemble. RandomForestRegressor: Ensemble regressor using trees with optimal splits. """ def __init__(self, n_estimators=10, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0., max_features="auto", max_leaf_nodes=None, min_impurity_split=1e-7, bootstrap=False, oob_score=False, n_jobs=1, random_state=None, verbose=0, warm_start=False): super(ExtraTreesRegressor, self).__init__( base_estimator=ExtraTreeRegressor(), 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_split", "random_state"), bootstrap=bootstrap, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start) self.criterion = criterion self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_features = max_features self.max_leaf_nodes = max_leaf_nodes self.min_impurity_split = min_impurity_split class RandomTreesEmbedding(BaseForest): """An ensemble of totally random trees. An unsupervised transformation of a dataset to a high-dimensional sparse representation. A datapoint is coded according to which leaf of each tree it is sorted into. Using a one-hot encoding of the leaves, this leads to a binary coding with as many ones as there are trees in the forest. The dimensionality of the resulting representation is ``n_out <= n_estimators * max_leaf_nodes``. If ``max_leaf_nodes == None``, the number of leaf nodes is at most ``n_estimators * 2 ** max_depth``. Read more in the :ref:`User Guide `. Parameters ---------- n_estimators : integer, optional (default=10) Number of trees in the forest. max_depth : integer, optional (default=5) The maximum depth of each 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, float, optional (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 percentage and `ceil(min_samples_split * n_samples)` is the minimum number of samples for each split. .. versionchanged:: 0.18 Added float values for percentages. min_samples_leaf : int, float, optional (default=1) The minimum number of samples required to be at a leaf node: - If int, then consider `min_samples_leaf` as the minimum number. - If float, then `min_samples_leaf` is a percentage and `ceil(min_samples_leaf * n_samples)` is the minimum number of samples for each node. .. versionchanged:: 0.18 Added float values for percentages. min_weight_fraction_leaf : float, optional (default=0.) The minimum weighted fraction of the input samples required to be at a leaf node. max_leaf_nodes : int or None, optional (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_split : float, optional (default=1e-7) Threshold for early stopping in tree growth. A node will split if its impurity is above the threshold, otherwise it is a leaf. .. versionadded:: 0.18 sparse_output : bool, optional (default=True) Whether or not to return a sparse CSR matrix, as default behavior, or to return a dense array compatible with dense pipeline operators. n_jobs : integer, optional (default=1) The number of jobs to run in parallel for both `fit` and `predict`. If -1, then the number of jobs is set to the number of cores. random_state : int, RandomState instance or None, optional (default=None) If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by `np.random`. verbose : int, optional (default=0) Controls the verbosity of the tree building process. warm_start : bool, optional (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. Attributes ---------- estimators_ : list of DecisionTreeClassifier The collection of fitted sub-estimators. References ---------- .. [1] P. Geurts, D. Ernst., and L. Wehenkel, "Extremely randomized trees", Machine Learning, 63(1), 3-42, 2006. .. [2] Moosmann, F. and Triggs, B. and Jurie, F. "Fast discriminative visual codebooks using randomized clustering forests" NIPS 2007 """ def __init__(self, n_estimators=10, max_depth=5, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0., max_leaf_nodes=None, min_impurity_split=1e-7, sparse_output=True, n_jobs=1, random_state=None, verbose=0, warm_start=False): super(RandomTreesEmbedding, self).__init__( base_estimator=ExtraTreeRegressor(), 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_split", "random_state"), bootstrap=False, oob_score=False, n_jobs=n_jobs, random_state=random_state, verbose=verbose, warm_start=warm_start) self.criterion = 'mse' self.max_depth = max_depth self.min_samples_split = min_samples_split self.min_samples_leaf = min_samples_leaf self.min_weight_fraction_leaf = min_weight_fraction_leaf self.max_features = 1 self.max_leaf_nodes = max_leaf_nodes self.min_impurity_split = min_impurity_split self.sparse_output = sparse_output def _set_oob_score(self, X, y): raise NotImplementedError("OOB score not supported by tree embedding") def fit(self, X, y=None, sample_weight=None): """Fit estimator. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) The input samples. Use ``dtype=np.float32`` for maximum efficiency. Sparse matrices are also supported, use sparse ``csc_matrix`` for maximum efficiency. Returns ------- self : object Returns self. """ self.fit_transform(X, y, sample_weight=sample_weight) return self def fit_transform(self, X, y=None, sample_weight=None): """Fit estimator and transform dataset. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) Input data used to build forests. Use ``dtype=np.float32`` for maximum efficiency. Returns ------- X_transformed : sparse matrix, shape=(n_samples, n_out) Transformed dataset. """ # ensure_2d=False because there are actually unit test checking we fail # for 1d. X = check_array(X, accept_sparse=['csc'], ensure_2d=False) if issparse(X): # Pre-sort indices to avoid that each individual tree of the # ensemble sorts the indices. X.sort_indices() rnd = check_random_state(self.random_state) y = rnd.uniform(size=X.shape[0]) super(RandomTreesEmbedding, self).fit(X, y, sample_weight=sample_weight) self.one_hot_encoder_ = OneHotEncoder(sparse=self.sparse_output) return self.one_hot_encoder_.fit_transform(self.apply(X)) def transform(self, X): """Transform dataset. Parameters ---------- X : array-like or sparse matrix, shape=(n_samples, n_features) Input data to be transformed. Use ``dtype=np.float32`` for maximum efficiency. Sparse matrices are also supported, use sparse ``csr_matrix`` for maximum efficiency. Returns ------- X_transformed : sparse matrix, shape=(n_samples, n_out) Transformed dataset. """ return self.one_hot_encoder_.transform(self.apply(X))