Merge pull request #407 from yzhao062/development

V1.0.1

.gitignore

@@ -3,3 +3,5 @@ pyod.egg-info/
 .cache/
 .pytest_cache
 __pycache__
+.idea/
+.vscode/

CHANGES.txt

@@ -158,4 +158,6 @@ v<1.0.0>, <04/04/2022> -- Add KDE detector (#382).
 v<1.0.0>, <04/06/2022> -- Disable the bias term in DeepSVDD (#385).
 v<1.0.0>, <04/21/2022> -- Fix a set of issues of autoencoders (#313, #390, #391).
 v<1.0.0>, <04/23/2022> -- Add sampling based detector (#384).
+v<1.0.1>, <04/27/2022> -- Add INNE (#396).
+v<1.0.1>, <05/13/2022> -- Urgent fix for iForest (#406).
 

README.rst

@@ -172,9 +172,9 @@ Alternatively, you could clone and run setup.py file:
 * Python 3.6+
 * combo>=0.1.3
 * joblib
-* numpy>=1.13
-* numba>=0.35
-* scipy>=1.3.1
+* numpy>=1.19
+* numba>=0.51
+* scipy>=1.5.1
 * scikit_learn>=0.20.0
 * six
 * statsmodels
@@ -324,6 +324,7 @@ Proximity-Based      MedKNN              Median kNN (use the median distance to
 Proximity-Based      SOD                 Subspace Outlier Detection                                                                              2009   [#Kriegel2009Outlier]_
 Proximity-Based      ROD                 Rotation-based Outlier Detection                                                                        2020   [#Almardeny2020A]_
 Outlier Ensembles    IForest             Isolation Forest                                                                                        2008   [#Liu2008Isolation]_
+Outlier Ensembles    INNE                Isolation-based Anomaly Detection Using Nearest-Neighbor Ensembles                                      2018   [#Bandaragoda2018Isolation]_
 Outlier Ensembles    FB                  Feature Bagging                                                                                         2005   [#Lazarevic2005Feature]_
 Outlier Ensembles    LSCP                LSCP: Locally Selective Combination of Parallel Outlier Ensembles                                       2019   [#Zhao2019LSCP]_
 Outlier Ensembles    XGBOD               Extreme Boosting Based Outlier Detection **(Supervised)**                                               2018   [#Zhao2018XGBOD]_
@@ -343,11 +344,12 @@ Neural Networks      DeepSVDD            Deep One-Class Classification
 ===================  ================  =====================================================================================================  =====  ========================================
 Type                 Abbr              Algorithm                                                                                              Year   Ref
 ===================  ================  =====================================================================================================  =====  ========================================
-Outlier Ensembles                      Feature Bagging                                                                                        2005   [#Lazarevic2005Feature]_
+Outlier Ensembles    FB                Feature Bagging                                                                                        2005   [#Lazarevic2005Feature]_
 Outlier Ensembles    LSCP              LSCP: Locally Selective Combination of Parallel Outlier Ensembles                                      2019   [#Zhao2019LSCP]_
 Outlier Ensembles    XGBOD             Extreme Boosting Based Outlier Detection **(Supervised)**                                              2018   [#Zhao2018XGBOD]_
 Outlier Ensembles    LODA              Lightweight On-line Detector of Anomalies                                                              2016   [#Pevny2016Loda]_
 Outlier Ensembles    SUOD              SUOD: Accelerating Large-scale Unsupervised Heterogeneous Outlier Detection **(Acceleration)**         2021   [#Zhao2021SUOD]_
+Outlier Ensembles    INNE              Isolation-based Anomaly Detection Using Nearest-Neighbor Ensembles                                     2018   [#Bandaragoda2018Isolation]_
 Combination          Average           Simple combination by averaging the scores                                                             2015   [#Aggarwal2015Theoretical]_
 Combination          Weighted Average  Simple combination by averaging the scores with detector weights                                       2015   [#Aggarwal2015Theoretical]_
 Combination          Maximization      Simple combination by taking the maximum scores                                                        2015   [#Aggarwal2015Theoretical]_
@@ -539,6 +541,8 @@ Reference
 
 .. [#Arning1996A] Arning, A., Agrawal, R. and Raghavan, P., 1996, August. A Linear Method for Deviation Detection in Large Databases. In *KDD* (Vol. 1141, No. 50, pp. 972-981).
 
+.. [#Bandaragoda2018Isolation] Bandaragoda, T. R., Ting, K. M., Albrecht, D., Liu, F. T., Zhu, Y., and Wells, J. R., 2018, Isolation-based anomaly detection using nearest-neighbor ensembles. *Computational Intelligence*\ , 34(4), pp. 968-998.
+
 .. [#Breunig2000LOF] Breunig, M.M., Kriegel, H.P., Ng, R.T. and Sander, J., 2000, May. LOF: identifying density-based local outliers. *ACM Sigmod Record*\ , 29(2), pp. 93-104.
 
 .. [#Burgess2018Understanding] Burgess, Christopher P., et al. "Understanding disentangling in beta-VAE." arXiv preprint arXiv:1804.03599 (2018).

docs/index.rst

@@ -169,6 +169,7 @@ Proximity-Based      MedKNN            Median kNN (use the median distance to k
 Proximity-Based      SOD               Subspace Outlier Detection                                                                              2009   :class:`pyod.models.sod.SOD`                         :cite:`a-kriegel2009outlier`
 Proximity-Based      ROD               Rotation-based Outlier Detection                                                                        2020   :class:`pyod.models.rod.ROD`                         :cite:`a-almardeny2020novel`
 Outlier Ensembles    IForest           Isolation Forest                                                                                        2008   :class:`pyod.models.iforest.IForest`                 :cite:`a-liu2008isolation,a-liu2012isolation`
+Outlier Ensembles    INNE              Isolation-based Anomaly Detection Using Nearest-Neighbor Ensembles                                      2018   :class:`pyod.models.inne.INNE`                       :cite:`a-bandaragoda2018isolation`
 Outlier Ensembles    FB                Feature Bagging                                                                                         2005   :class:`pyod.models.feature_bagging.FeatureBagging`  :cite:`a-lazarevic2005feature`
 Outlier Ensembles    LSCP              LSCP: Locally Selective Combination of Parallel Outlier Ensembles                                       2019   :class:`pyod.models.lscp.LSCP`                       :cite:`a-zhao2019lscp`
 Outlier Ensembles    XGBOD             Extreme Boosting Based Outlier Detection **(Supervised)**                                               2018   :class:`pyod.models.xgbod.XGBOD`                     :cite:`a-zhao2018xgbod`

docs/install.rst

@@ -28,9 +28,9 @@ Alternatively, you could clone and run setup.py file:
 * Python 3.6+
 * combo>=0.1.3
 * joblib
-* numpy>=1.13
-* numba>=0.35
-* scipy>=1.3.1
+* numpy>=1.19
+* numba>=0.51
+* scipy>=1.5.1
 * scikit_learn>=0.20.0
 * six
 * statsmodels

docs/pyod.models.rst

@@ -125,6 +125,16 @@ pyod.models.iforest module
     :show-inheritance:
     :inherited-members:
 
+pyod.models.inne module
+-----------------------
+
+.. automodule:: pyod.models.inne
+    :members:
+    :exclude-members:
+    :undoc-members:
+    :show-inheritance:
+    :inherited-members:
+
 pyod.models.kde module
 ----------------------
 

docs/requirements.txt

@@ -4,10 +4,10 @@ joblib
 keras
 matplotlib
 nose
-numpy>=1.13
+numpy>=1.19
 numba==0.53 # need to lift this later see github for issue
 pytest
-scipy>=1.3.1
+scipy>=1.5.1
 scikit_learn>=0.20.0
 six
 sphinx-rtd-theme

docs/zreferences.bib

@@ -413,4 +413,15 @@ @article{sugiyama2013rapid
   journal={Advances in neural information processing systems},
   volume={26},
   year={2013}
+}
+
+@article{bandaragoda2018isolation,
+  title={Isolation-based anomaly detection using nearest-neighbor ensembles},
+  author={Bandaragoda, Tharindu R and Ting, Kai Ming and Albrecht, David and Liu, Fei Tony and Zhu, Ye and Wells, Jonathan R},
+  journal={Computational Intelligence},
+  volume={34},
+  number={4},
+  pages={968--998},
+  year={2018},
+  publisher={Wiley Online Library}
 }

examples/inne_example.py

@@ -0,0 +1,57 @@
+"""Example of using INNE for outlier detection
+"""
+# Author: Xin Han <xinhan197@gmail.com>
+# License: BSD 2 clause
+
+from __future__ import division
+from __future__ import print_function
+
+import os
+import sys
+
+# temporary solution for relative imports in case pyod is not installed
+# if pyod is installed, no need to use the following line
+sys.path.append(
+    os.path.abspath(os.path.join(os.path.dirname("__file__"), '..')))
+
+from pyod.models.inne import INNE
+from pyod.utils.data import generate_data
+
+from pyod.utils.data import evaluate_print
+from pyod.utils.example import visualize
+
+if __name__ == "__main__":
+    contamination = 0.1  # percentage of outliers
+    n_train = 200  # number of training points
+    n_test = 100  # number of testing points
+
+    # Generate sample data
+    X_train, y_train, X_test, y_test = \
+        generate_data(n_train=n_train,
+                      n_test=n_test,
+                      n_features=2,
+                      contamination=contamination,
+                      random_state=42)
+
+    # train INNE detector
+    clf_name = 'INNE'
+    clf = INNE(contamination=contamination, max_samples=4)
+    clf.fit(X_train)
+
+    # get the prediction labels and outlier scores of the training data
+    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
+    y_train_scores = clf.decision_scores_  # raw outlier scores
+
+    # get the prediction on the test data
+    y_test_pred = clf.predict(X_test)  # outlier labels (0 or 1)
+    y_test_scores = clf.decision_function(X_test)  # outlier scores
+
+    # evaluate and print the results
+    print("\nOn Training Data:")
+    evaluate_print(clf_name, y_train, y_train_scores)
+    print("\nOn Test Data:")
+    evaluate_print(clf_name, y_test, y_test_scores)
+
+    # visualize the results
+    visualize(clf_name, X_train, y_train, X_test, y_test, y_train_pred,
+              y_test_pred, show_figure=True, save_figure=False)

pyod/models/iforest.py

@@ -10,7 +10,6 @@
 import numpy as np
 from joblib import Parallel
 from joblib.parallel import delayed
-from sklearn.utils.fixes import _joblib_parallel_args
 
 from sklearn.ensemble import IsolationForest
 from sklearn.utils.validation import check_is_fitted
@@ -306,8 +305,7 @@ def feature_importances_(self):
         """
         check_is_fitted(self)
         all_importances = Parallel(
-            n_jobs=self.n_jobs, **_joblib_parallel_args(prefer="threads")
-        )(
+            n_jobs=self.n_jobs)(
             delayed(getattr)(tree, "feature_importances_")
             for tree in self.detector_.estimators_
             if tree.tree_.node_count > 1