Merge pull request #422 from yzhao062/development

v1.0.3
yzhao062 · Jul 5, 2022 · c2839e0 · c2839e0
2 parents 3a0a55a + 3cdc6de
commit c2839e0
Show file tree

Hide file tree

Showing 84 changed files with 766 additions and 143 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -162,3 +162,6 @@ v<1.0.1>, <04/27/2022> -- Add INNE (#396).
 v<1.0.1>, <05/13/2022> -- Urgent fix for iForest (#406).
 v<1.0.2>, <06/21/2022> -- Add GMM detector (#402).
 v<1.0.2>, <06/23/2022> -- Add ADBench Benchmark.
+v<1.0.3>, <06/27/2022> -- Change default generation to new behaviors (#409).
+v<1.0.3>, <07/04/2022> -- Add AnoGAN (#412).
+
diff --git a/README.rst b/README.rst
@@ -352,6 +352,7 @@ Neural Networks      Beta-VAE            Variational AutoEncoder (all customized
 Neural Networks      SO_GAAL             Single-Objective Generative Adversarial Active Learning                                                 2019   [#Liu2019Generative]_
 Neural Networks      MO_GAAL             Multiple-Objective Generative Adversarial Active Learning                                               2019   [#Liu2019Generative]_
 Neural Networks      DeepSVDD            Deep One-Class Classification                                                                           2018   [#Ruff2018Deep]_
+Neural Networks      AnoGAN              Anomaly Detection with Generative Adversarial Networks                                                  2017   [#Schlegl2017Unsupervised]_
 ===================  ==================  ======================================================================================================  =====  ========================================
 
 
@@ -620,6 +621,8 @@ Reference
 
 .. [#Ruff2018Deep] Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., Müller, E. and Kloft, M., 2018, July. Deep one-class classification. In *International conference on machine learning* (pp. 4393-4402). PMLR.
 
+.. [#Schlegl2017Unsupervised] Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U. and Langs, G., 2017, June. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International conference on information processing in medical imaging (pp. 146-157). Springer, Cham.
+
 .. [#Scholkopf2001Estimating] Scholkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J. and Williamson, R.C., 2001. Estimating the support of a high-dimensional distribution. *Neural Computation*, 13(7), pp.1443-1471.
 
 .. [#Shyu2003A] Shyu, M.L., Chen, S.C., Sarinnapakorn, K. and Chang, L., 2003. A novel anomaly detection scheme based on principal component classifier. *MIAMI UNIV CORAL GABLES FL DEPT OF ELECTRICAL AND COMPUTER ENGINEERING*.

diff --git a/docs/about.rst b/docs/about.rst
@@ -44,9 +44,19 @@ Roel Bouman (Ph.D. Student @ Radboud University):
 Rafał Bodziony (Data Scientist):
 
 - Joined in 2021 (implemented DeepSVDD)
-- `LinkedIn (Roel Bouman) <https://pl.linkedin.com/in/rafalbodziony>`_
+- `LinkedIn (Rafał Bodziony) <https://pl.linkedin.com/in/rafalbodziony>`_
 
 Dr Akira Tamamori (Associate Professor @ Aichi Institute of Technology):
 
 - Joined in 2022 (implemented multiple OD algorithms such as KDE, sampling, and more)
-- `Homepage (Dr Akira Tamamori) <https://researchmap.jp/tamamori?lang=en>`_
+- `Homepage (Dr Akira Tamamori) <https://researchmap.jp/tamamori?lang=en>`_
+
+Michiel Bongaerts (PhD student @ Erasmus Medical Centre Metabolomics & Genetics):
+
+- Joined in 2022 (implemented AnoGAN and more)
+- `GitHub (Michiel Bongaerts) <https://github.com/mbongaerts>`_
+
+Adam Goodge (PhD Researcher @ National University of Singapore):
+
+- Joined in 2022 (implemented LUNAR)
+- `LinkedIn (Adam Goodge) <https://www.linkedin.com/in/adam-goodge-33908691/>`_
diff --git a/docs/index.rst b/docs/index.rst
@@ -199,6 +199,7 @@ Neural Networks      Beta-VAE          Variational AutoEncoder (all customized l
 Neural Networks      SO_GAAL           Single-Objective Generative Adversarial Active Learning                                                 2019   :class:`pyod.models.so_gaal.SO_GAAL`                 :cite:`a-liu2019generative`
 Neural Networks      MO_GAAL           Multiple-Objective Generative Adversarial Active Learning                                               2019   :class:`pyod.models.mo_gaal.MO_GAAL`                 :cite:`a-liu2019generative`
 Neural Networks      DeepSVDD          Deep One-Class Classification                                                                           2018   :class:`pyod.models.deep_svdd.DeepSVDD`              :cite:`a-ruff2018deepsvdd`
+Neural Networks      AnoGAN            Anomaly Detection with Generative Adversarial Networks                                                  2017   :class:`pyod.models.anogan.AnoGAN`                   :cite:`a-schlegl2017unsupervised`
 ===================  ================  ======================================================================================================  =====  ===================================================  ======================================================
 
 

diff --git a/docs/pyod.models.rst b/docs/pyod.models.rst
@@ -11,6 +11,15 @@ pyod.models.abod module
     :show-inheritance:
     :inherited-members:
 
+pyod.models.anogan module
+-------------------------
+
+.. automodule:: pyod.models.anogan
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :inherited-members:
+
 pyod.models.auto\_encoder module
 --------------------------------
 

diff --git a/docs/zreferences.bib b/docs/zreferences.bib
@@ -424,4 +424,13 @@ @article{bandaragoda2018isolation
   pages={968--998},
   year={2018},
   publisher={Wiley Online Library}
+}
+
+@inproceedings{schlegl2017unsupervised,
+  title={Unsupervised anomaly detection with generative adversarial networks to guide marker discovery},
+  author={Schlegl, Thomas and Seeb{\"o}ck, Philipp and Waldstein, Sebastian M and Schmidt-Erfurth, Ursula and Langs, Georg},
+  booktitle={International conference on information processing in medical imaging},
+  pages={146--157},
+  year={2017},
+  organization={Springer}
 }
diff --git a/examples/abod_example.py b/examples/abod_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/anogan_example.py b/examples/anogan_example.py
@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+"""Example for Anomaly Detection with Generative Adversarial Networks  (AnoGAN)
+ Paper: https://arxiv.org/pdf/1703.05921.pdf
+ Note, that this is another implementation of AnoGAN as the one from https://github.com/fuchami/ANOGAN
+"""
+# Author: Michiel Bongaerts (but not author of the AnoGAN method)
+# 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.anogan import AnoGAN
+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, X_test, y_train, y_test = generate_data(
+        n_train=n_train,
+        n_test=n_test,
+        n_features=2,
+        contamination=contamination,
+        behaviour="new",
+        random_state=42,
+    )
+
+    # train AutoEncoder detector
+    clf_name = 'AnoGAN'
+    clf = AnoGAN(G_layers=[10, 20], D_layers=[20, 2],
+                 preprocessing=True, index_D_layer_for_recon_error=1,
+                 epochs=200, contamination=contamination, verbose=1)
+
+    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)
+
+    clf.plot_learning_curves(window_smoothening=30)
diff --git a/examples/auto_encoder_example.py b/examples/auto_encoder_example.py
@@ -26,7 +26,7 @@
     n_features = 300  # number of features
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=n_features,

diff --git a/examples/auto_encoder_torch_example.py b/examples/auto_encoder_torch_example.py
@@ -28,7 +28,7 @@
     n_features = 300  # number of features
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=n_features,

diff --git a/examples/cblof_example.py b/examples/cblof_example.py
@@ -27,7 +27,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/cd_example.py b/examples/cd_example.py
@@ -27,7 +27,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/cof_example.py b/examples/cof_example.py
@@ -28,7 +28,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/compare_all_models.py b/examples/compare_all_models.py
@@ -33,14 +33,10 @@
 from pyod.models.iforest import IForest
 from pyod.models.knn import KNN
 from pyod.models.lof import LOF
-from pyod.models.loci import LOCI
 from pyod.models.mcd import MCD
 from pyod.models.ocsvm import OCSVM
 from pyod.models.pca import PCA
-from pyod.models.sos import SOS
 from pyod.models.lscp import LSCP
-from pyod.models.cof import COF
-from pyod.models.sod import SOD
 
 # TODO: add neural networks, LOCI, SOS, COF, SOD
 

diff --git a/examples/copod_example.py b/examples/copod_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/copod_parallel_example.py b/examples/copod_parallel_example.py
@@ -27,10 +27,10 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
-                      n_features=10,
+                      n_features=2,
                       contamination=contamination,
                       random_state=42)
 

diff --git a/examples/deepsvdd_example.py b/examples/deepsvdd_example.py
@@ -24,10 +24,11 @@
     n_train = 20000  # number of training points
     n_test = 2000  # number of testing points
     n_features = 300  # number of features
-    use_ae = False # hyperparameter for use ae architecture instead of simple NN
-    random_state = 10 # if C is set to None use random_state
+    use_ae = False  # hyperparameter for use ae architecture instead of simple NN
+    random_state = 10  # if C is set to None use random_state
+
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=n_features,

diff --git a/examples/ecod_example.py b/examples/ecod_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/feature_bagging_example.py b/examples/feature_bagging_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/hbos_example.py b/examples/hbos_example.py
@@ -27,7 +27,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/iforest_example.py b/examples/iforest_example.py
@@ -27,7 +27,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/inne_example.py b/examples/inne_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/kde_example.py b/examples/kde_example.py
@@ -24,14 +24,12 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, X_test, y_train, y_test = generate_data(
-        n_train=n_train,
-        n_test=n_test,
-        n_features=2,
-        contamination=contamination,
-        behaviour="new",
-        random_state=42,
-    )
+    X_train, X_test, y_train, y_test = \
+        generate_data(n_train=n_train,
+                      n_test=n_test,
+                      n_features=2,
+                      contamination=contamination,
+                      random_state=42)
 
     # train kNN detector
     clf_name = "KDE"

diff --git a/examples/knn_example.py b/examples/knn_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/knn_mahalanobis_example.py b/examples/knn_mahalanobis_example.py
@@ -28,7 +28,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/lmdd_example.py b/examples/lmdd_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/loci_example.py b/examples/loci_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/loda_example.py b/examples/loda_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/lof_example.py b/examples/lof_example.py
@@ -26,7 +26,7 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
                       n_features=2,

diff --git a/examples/lscp_example.py b/examples/lscp_example.py
@@ -28,12 +28,12 @@
     n_test = 100  # number of testing points
 
     # Generate sample data
-    X_train, y_train, X_test, y_test = \
+    X_train, X_test, y_train, y_test = \
         generate_data(n_train=n_train,
                       n_test=n_test,
+                      n_features=2,
                       contamination=contamination,
                       random_state=42)
-    X_train, X_test = standardizer(X_train, X_test)
 
     # train lscp
     clf_name = 'LSCP'