Merge pull request #312 from yzhao062/development

V0.8.9

.circleci/config.yml

@@ -97,7 +97,7 @@ jobs:
           command: |
             . venv/bin/activate
             pytest
-          no_output_timeout: 30m
+          no_output_timeout: 60m
 
       - store_artifacts:
           path: test-reports

CHANGES.txt

@@ -122,7 +122,10 @@ v<0.8.7>, <01/16/2021> -- Add ROD.
 v<0.8.7>, <02/18/2021> -- Dependency optimization.
 v<0.8.8>, <04/08/2021> -- COPOD optimization.
 v<0.8.8>, <04/08/2021> -- Add parallelization for COPOD.
-v<0.8.8>, <04/26/2021> -- fix XGBOD issue with xgboost 1.4.
+v<0.8.8>, <04/26/2021> -- Fix XGBOD issue with xgboost 1.4.
+v<0.8.9>, <05/17/2021> -- Turn on test for Python 3.5-3.8.
+v<0.8.9>, <06/10/2021> -- Add PyTorch AutoEncoder
+v<0.8.9>, <06/11/2021> -- Fix LMDD parameter (#307)
 
 
 

README.rst

@@ -222,8 +222,8 @@ be found at `Moving to require Python 3 <https://python3statement.org/>`_.
 
 **Warning 1**\ :
 PyOD has multiple neural network based models, e.g., AutoEncoders, which are
-implemented in Keras. However, PyOD does **NOT** install **keras** and/or
-**tensorflow** for you. This reduces the risk of interfering with your local copies.
+implemented in both PyTorch and Tensorflow. However, PyOD does **NOT** install DL libraries for you.
+This reduces the risk of interfering with your local copies.
 If you want to use neural-net based models, please make sure Keras and a backend library, e.g., TensorFlow, are installed.
 Instructions are provided: `neural-net FAQ <https://github.com/yzhao062/pyod/wiki/Setting-up-Keras-and-Tensorflow-for-Neural-net-Based-models>`_.
 Similarly, models depending on **xgboost**, e.g., XGBOD, would **NOT** enforce xgboost installation by default.

docs/conf.py

@@ -51,6 +51,7 @@
     'sphinx.ext.viewcode',
     'sphinxcontrib.bibtex',
     'sphinx.ext.napoleon',
+    'sphinx_rtd_theme',
 ]
 
 bibtex_bibfiles = ['zreferences.bib']
@@ -87,7 +88,9 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'default'
+# html_theme = 'default'
+
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the

docs/install.rst

@@ -53,8 +53,8 @@ Alternatively, you could clone and run setup.py file:
 .. warning::
 
     PyOD has multiple neural network based models, e.g., AutoEncoders, which are
-    implemented in Keras. However, PyOD does **NOT** install **keras** and/or
-    **tensorflow** for you. This reduces the risk of interfering with your local copies.
+    implemented in both PyTorch and Tensorflow. However, PyOD does **NOT** install DL libraries for you.
+    This reduces the risk of interfering with your local copies.
     If you want to use neural-net based models, please make sure Keras and a backend library, e.g., TensorFlow, are installed.
     Instructions are provided: `neural-net FAQ <https://github.com/yzhao062/pyod/wiki/Setting-up-Keras-and-Tensorflow-for-Neural-net-Based-models>`_.
     Similarly, models depending on **xgboost**, e.g., XGBOD, would **NOT** enforce xgboost installation by default.

docs/pyod.models.rst

@@ -20,6 +20,15 @@ pyod.models.auto\_encoder module
     :show-inheritance:
     :inherited-members:
 
+pyod.models.auto\_encoder\_torch module
+---------------------------------------
+
+.. automodule:: pyod.models.auto_encoder_torch
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :inherited-members:
+
 pyod.models.cblof module
 ------------------------
 
@@ -49,7 +58,7 @@ pyod.models.combination module
     :inherited-members:
 
 pyod.models.copod module
-----------------------
+------------------------
 
 .. automodule:: pyod.models.copod
     :members:
@@ -96,7 +105,7 @@ pyod.models.knn module
     :inherited-members:
 
 pyod.models.lmdd module
-----------------------
+-----------------------
 
 .. automodule:: pyod.models.lmdd
     :members:

docs/requirements.txt

@@ -10,8 +10,11 @@ pytest
 scipy>=0.19.1
 scikit_learn>=0.19.1
 six
+sphinx-rtd-theme
 sphinxcontrib-bibtex
 statsmodels
 suod
 tensorflow
+torch
 xgboost
+docutils==0.16 # need to lift this later see github for issue

examples/auto_encoder_torch_example.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+"""Example of using Autoencoder for outlier detection (pytorch)
+detection
+"""
+# Author: Yue Zhao <[email protected]>
+# 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.auto_encoder_torch import AutoEncoder
+from pyod.utils.data import generate_data
+from pyod.utils.data import evaluate_print
+
+
+if __name__ == "__main__":
+    contamination = 0.1  # percentage of outliers
+    n_train = 20000  # number of training points
+    n_test = 2000  # number of testing points
+    n_features = 300  # number of features
+
+    # Generate sample data
+    X_train, y_train, X_test, y_test = \
+        generate_data(n_train=n_train,
+                      n_test=n_test,
+                      n_features=n_features,
+                      contamination=contamination,
+                      random_state=42)
+
+    # train AutoEncoder detector
+    clf_name = 'AutoEncoder'
+    clf = AutoEncoder(epochs=10)
+    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)