documentation and test improvement

.circleci/config.yml

@@ -8,6 +8,7 @@ workflows:
   test:
     jobs:
       - test-3.6
+      - test-3.7
 jobs:
   test-3.6:
     docker:
@@ -22,7 +23,7 @@ jobs:
       # Download and cache dependencies
       - restore_cache:
           keys:
-          - v1-py3-dependencies-{{ checksum "requirements_ci.txt" }}
+          - v1-py3-dependencies-{{ checksum "requirements.txt" }}
           # fallback to using the latest cache if no exact match is found
           - v1-py3-dependencies-
 
@@ -54,3 +55,50 @@ jobs:
       - store_artifacts:
           path: test-reports
           destination: test-reports
+
+  test-3.7:
+    docker:
+      - image: circleci/python:3.7-stretch
+
+    working_directory: ~/repo
+
+    steps:
+      - checkout
+      - run: sudo chown -R circleci:circleci /usr/local/bin
+
+      # Download and cache dependencies
+      - restore_cache:
+          keys:
+            - v1-py3-dependencies-{{ checksum "requirements.txt" }}
+            # fallback to using the latest cache if no exact match is found
+            - v1-py3-dependencies-
+
+      - run:
+          name: install dependencies
+          command: |
+            python3 -m venv venv
+            . venv/bin/activate
+            pip install --upgrade pip
+            pip install -r requirements.txt
+            pip install pandas
+            pip install pytest
+            pip install pytest-cov
+
+
+      - save_cache:
+          paths:
+            - ./venv
+          key: v1-py3-dependencies-{{ checksum "requirements.txt" }}
+
+
+      # run tests!
+      - run:
+          name: run tests
+          command: |
+            . venv/bin/activate
+            pytest
+
+      - store_artifacts:
+          path: test-reports
+          destination: test-reports
+

CHANGES.txt

@@ -13,4 +13,5 @@ v<0.0.5>, <12/15/2020> -- Unit test updatde.
 v<0.0.5>, <12/27/2020> -- Refactor for sklearn 0.24.
 v<0.0.6>, <01/14/2021> -- Fix n_jobs issue and code refactor.
 v<0.0.6>, <01/14/2021> -- Add model save and load functionality.
-v<0.0.7>, <08/29/2021> -- Update to be integrated in PyOD.
+v<0.0.7>, <08/29/2021> -- Update to be integrated in PyOD.
+v<0.0.7>, <08/29/2021> -- Documentation and test improvement.

README.rst

@@ -39,8 +39,8 @@ SUOD: Accelerating Large-scare Unsupervised Heterogeneous Outlier Detection
 **Build Status & Coverage & Maintainability & License**
 
 
-.. image:: https://travis-ci.org/yzhao062/suod.svg?branch=master
-   :target: https://travis-ci.org/yzhao062/suod
+.. image::  https://app.travis-ci.com/yzhao062/SUOD.svg?branch=master
+   :target: https://app.travis-ci.com/yzhao062/SUOD
    :alt: Build Status
 
 
@@ -65,6 +65,29 @@ SUOD: Accelerating Large-scare Unsupervised Heterogeneous Outlier Detection
 
 ----
 
+**News**: SUOD is now integrated into `PyOD <https://github.com/yzhao062/pyod>`_.
+It can be easily invoked in PyOD by following the `SUOD example <https://github.com/yzhao062/pyod/blob/master/examples/suod_example.py>`_.
+In a nutshell, we could easily initialize a few outlier detectors and then use SUOD for collective training and prediction!
+
+.. code-block:: python
+
+    from pyod.models.suod import SUOD
+
+    # initialized a group of outlier detectors for acceleration
+    detector_list = [LOF(n_neighbors=15), LOF(n_neighbors=20),
+                     LOF(n_neighbors=25), LOF(n_neighbors=35),
+                     COPOD(), IForest(n_estimators=100),
+                     IForest(n_estimators=200)]
+
+    # decide the number of parallel process, and the combination method
+    # then clf can be used as any outlier detection model
+    clf = SUOD(base_estimators=detector_list, n_jobs=2, combination='average',
+               verbose=False)
+
+
+----
+
+
 **Background**: Outlier detection (OD) is a key data mining task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection.
 Due to the lack of ground truth labels, practitioners often have to build a large number of unsupervised models that are heterogeneous (i.e., different algorithms and hyperparameters) for further combination and analysis with ensemble learning, rather than relying on a single model.
 However, **this yields severe scalability issues on high-dimensional, large datasets**.

docs/index.rst

@@ -70,6 +70,28 @@ Welcome to SUOD's documentation!
    :alt: License
 
 
+----
+
+**News**: SUOD is now integrated into `PyOD <https://github.com/yzhao062/pyod>`_.
+It can be easily invoked in PyOD by following the `SUOD example <https://github.com/yzhao062/pyod/blob/master/examples/suod_example.py>`_.
+In a nutshell, we could easily initialize a few outlier detectors and then use SUOD for collective training and prediction!
+
+.. code-block:: python
+
+    from pyod.models.suod import SUOD
+
+    # initialized a group of outlier detectors for acceleration
+    detector_list = [LOF(n_neighbors=15), LOF(n_neighbors=20),
+                     LOF(n_neighbors=25), LOF(n_neighbors=35),
+                     COPOD(), IForest(n_estimators=100),
+                     IForest(n_estimators=200)]
+
+    # decide the number of parallel process, and the combination method
+    # then clf can be used as any outlier detection model
+    clf = SUOD(base_estimators=detector_list, n_jobs=2, combination='average',
+               verbose=False)
+
+
 ----
 
 **Background**: Outlier detection (OD) is a key data mining task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection.

docs/requirements.txt

@@ -1,7 +1,9 @@
+combo
 joblib
 matplotlib
 numpy>=1.13
 scipy>=0.19.1
 scikit_learn>=0.19.1
 pyod>=0.7.5
-sphinxcontrib-bibtex
+sphinxcontrib-bibtex
+docutils==0.16 # need to lift this later see github for issue

requirements.txt

@@ -1,3 +1,4 @@
+combo
 joblib>=0.14.1
 matplotlib
 numpy>=1.13