from sklearn.ensemble._iforest import IsolationForest
from sktree.tree import ExtraObliqueDecisionTreeRegressor
[docs]
class ExtendedIsolationForest(IsolationForest):
"""
Extended Isolation Forest Algorithm.
Return the anomaly score of each sample using the ExtendedIsolationForest algorithm
The ExtendedIsolationForest 'isolates' observations by randomly selecting a
sparse linear combination of features and then randomly selecting a split
value between the maximum and minimum values of the selected feature. The
main difference from the IsolationForest algorithm is how the splits are
computed.
Read more in the :ref:`User Guide <isolation_forest>`.
Parameters
----------
n_estimators : int, default=100
The number of base estimators in the ensemble.
max_samples : "auto", int or float, default="auto"
The number of samples to draw from X to train each base estimator.
- If int, then draw `max_samples` samples.
- If float, then draw `max_samples * X.shape[0]` samples.
- If "auto", then `max_samples=min(256, n_samples)`.
If max_samples is larger than the number of samples provided,
all samples will be used for all trees (no sampling).
contamination : 'auto' or float, default='auto'
The amount of contamination of the data set, i.e. the proportion
of outliers in the data set. Used when fitting to define the threshold
on the scores of the samples.
- If 'auto', the threshold is determined as in the
original paper.
- If float, the contamination should be in the range (0, 0.5].
max_features : int or float, default=1.0
The number of features to draw from X to train each base estimator.
- If int, then draw `max_features` features.
- If float, then draw `max(1, int(max_features * n_features_in_))` features.
Note: using a float number less than 1.0 or integer less than number of
features will enable feature subsampling and leads to a longer runtime.
bootstrap : bool, default=False
If True, individual trees are fit on random subsets of the training
data sampled with replacement. If False, sampling without replacement
is performed.
feature_combinations : int, default=2
The number of features to on average combine to consider at each split.
For more information, see `ExtraObliqueDecisionTreeRegressor`.
n_jobs : int, default=None
The number of jobs to run in parallel for both :meth:`fit` and
:meth:`predict`. ``None`` means 1 unless in a
:obj:`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 the pseudo-randomness of the selection of the feature
and split values for each branching step and each tree in the forest.
Pass an int for reproducible results across multiple function calls.
See :term:`Glossary <random_state>`.
verbose : int, default=0
Controls the verbosity of the tree building process.
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>`.
.. versionadded:: 0.21
Attributes
----------
estimator_ : :class:`~sklearn.tree.ExtraTreeRegressor` instance
The child estimator template used to create the collection of
fitted sub-estimators.
.. versionadded:: 1.2
`base_estimator_` was renamed to `estimator_`.
base_estimator_ : ExtraTreeRegressor instance
The child estimator template used to create the collection of
fitted sub-estimators.
.. deprecated:: 1.2
`base_estimator_` is deprecated and will be removed in 1.4.
Use `estimator_` instead.
estimators_ : list of ExtraTreeRegressor instances
The collection of fitted sub-estimators.
estimators_features_ : list of ndarray
The subset of drawn features for each base estimator.
estimators_samples_ : list of ndarray
The subset of drawn samples (i.e., the in-bag samples) for each base
estimator.
max_samples_ : int
The actual number of samples.
offset_ : float
Offset used to define the decision function from the raw scores. We
have the relation: ``decision_function = score_samples - offset_``.
``offset_`` is defined as follows. When the contamination parameter is
set to "auto", the offset is equal to -0.5 as the scores of inliers are
close to 0 and the scores of outliers are close to -1. When a
contamination parameter different than "auto" is provided, the offset
is defined in such a way we obtain the expected number of outliers
(samples with decision function < 0) in training.
.. versionadded:: 0.20
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
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.
.. versionadded:: 1.0
See Also
--------
sklearn.covariance.EllipticEnvelope : An object for detecting outliers in a
Gaussian distributed dataset.
sklearn.svm.OneClassSVM : Unsupervised Outlier Detection.
Estimate the support of a high-dimensional distribution.
The implementation is based on libsvm.
sklearn.neighbors.LocalOutlierFactor : Unsupervised Outlier Detection
using Local Outlier Factor (LOF).
Notes
-----
The implementation is based on an ensemble of ExtraTreeRegressor. The
maximum depth of each tree is set to ``ceil(log_2(n))`` where
:math:`n` is the number of samples used to build the tree
(see (Liu et al., 2008) for more details).
References
----------
.. [1] Liu, Fei Tony, Ting, Kai Ming and Zhou, Zhi-Hua. "Isolation forest."
Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on.
.. [2] Liu, Fei Tony, Ting, Kai Ming and Zhou, Zhi-Hua. "Isolation-based
anomaly detection." ACM Transactions on Knowledge Discovery from
Data (TKDD) 6.1 (2012): 3.
Examples
--------
>>> from sktree.ensemble import ExtendedIsolationForest
>>> X = [[-1.1], [0.3], [0.5], [100]]
>>> clf = ExtendedIsolationForest(random_state=0).fit(X)
>>> clf.predict([[0.1], [0], [90]])
array([ 1, 1, -1])
"""
def __init__(
self,
*,
n_estimators=100,
max_samples="auto",
contamination="auto",
max_features=1.0,
bootstrap=False,
feature_combinations=None,
n_jobs=None,
random_state=None,
verbose=0,
warm_start=False,
):
super(IsolationForest, self).__init__(
estimator=ExtraObliqueDecisionTreeRegressor(
feature_combinations=feature_combinations,
max_features=1,
splitter="random",
random_state=random_state,
),
# here above max_features has no links with self.max_features
bootstrap=bootstrap,
bootstrap_features=False,
n_estimators=n_estimators,
max_samples=max_samples,
max_features=max_features,
warm_start=warm_start,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
)
self.feature_combinations = feature_combinations
self.contamination = contamination