Merge pull request #16 from selimfirat/develop

Release v0.3.0

Author: selimfirat

CHANGES.txt

@@ -1,2 +1,3 @@
 v<0.1.0>, <08/15/2020> -- Initial release.
-v<0.2.0> <06/10/2023> -- Upgraded some libraries like numpy,pandas and small refactorings.
+v<0.2.0> <06/10/2023> -- Upgraded some libraries like numpy,pandas and small refactorings.
+v<0.3.0>, <05/23/2025> -- Updated dependencies to latest versions, improved documentation, added quick start example in README. Added Inqmad model. Special thanks to @TechyNilesh @Joaggi @onixlas.

MANIFEST.in

@@ -0,0 +1,2 @@
+include README.rst
+include requirements.txt

README.rst

@@ -120,10 +120,10 @@ Alternatively, you can install the library directly using the source code in Git
 **Required Dependencies:**
 
 
-* Python 3.8
-* numpy==1.23.5
-* scikit-learn>=1.3.0
-* scipy==1.10.0
+* Python 3.10+
+* numpy==2.0.2
+* scikit-learn==1.5.2
+* scipy==1.13.1
 * pyod==1.1.0
 * combo==0.1.3
 
@@ -133,7 +133,37 @@ Alternatively, you can install the library directly using the source code in Git
 * rrcf==0.4.3 (Only required for  `pysad.models.robust_random_cut_forest.RobustRandomCutForest`)
 * PyNomaly==0.3.3 (Only required for  `pysad.models.loop.StreamLocalOutlierProbability`)
 * mmh3==2.5.1 (Only required for  `pysad.models.xstream.xStream`)
-* pandas==2.0.3 (Only required for  `pysad.utils.pandas_streamer.PandasStreamer`)
+* pandas==2.2.3 (Only required for  `pysad.utils.pandas_streamer.PandasStreamer`)
+* jax>=0.6.1 (Only required for  `pysad.models.inqmad.Inqmad`; required for NumPy 2.0+ compatibility)
+* jaxlib>=0.6.1 (Only required for  `pysad.models.inqmad.Inqmad`; required for NumPy 2.0+ compatibility)
+
+Examples
+========
+
+Quick Start
+^^^^^^^^^^^^^^^^^^
+
+Here's a simple example showing how to use PySAD for anomaly detection on streaming data:
+
+.. code-block:: python
+
+    # Import modules.
+    from pysad.evaluation import AUROCMetric
+    from pysad.models import LODA
+    from pysad.utils import Data
+
+
+    model = LODA()  # Init model
+    metric = AUROCMetric()  # Init area under receiver-operating- characteristics curve metric
+    streaming_data = Data().get_iterator("arrhythmia.mat")  # Get data streamer.
+
+    for x, y_true in streaming_data:  # Stream data.
+        anomaly_score = model.fit_score_partial(x)  # Fit the instance to model and score the instance.
+
+        metric.update(y_true, anomaly_score)  # Update the AUROC metric.
+
+    # Output the resulting AUROCMetric.
+    print(f"Area under ROC metric is {metric.get()}.")
 
 Quick Links
 ============

README_template.rst

@@ -7,6 +7,34 @@
 
 .. include:: docs/installation.rst
 
+Examples
+========
+
+Quick Start
+^^^^^^^^^^^^^^^^^^
+
+Here's a simple example showing how to use PySAD for anomaly detection on streaming data:
+
+.. code-block:: python
+
+    # Import modules.
+    from pysad.evaluation import AUROCMetric
+    from pysad.models import LODA
+    from pysad.utils import Data
+
+
+    model = LODA()  # Init model
+    metric = AUROCMetric()  # Init area under receiver-operating- characteristics curve metric
+    streaming_data = Data().get_iterator("arrhythmia.mat")  # Get data streamer.
+
+    for x, y_true in streaming_data:  # Stream data.
+        anomaly_score = model.fit_score_partial(x)  # Fit the instance to model and score the instance.
+
+        metric.update(y_true, anomaly_score)  # Update the AUROC metric.
+
+    # Output the resulting AUROCMetric.
+    print(f"Area under ROC metric is {metric.get()}.")
+
 .. include:: docs/quick_links.rst
 
 .. include:: docs/versioning.rst

_build_readme.py

@@ -1,14 +1,53 @@
+import os
+import re
+
+def process_literalinclude(path, language):
+    # Make the path relative to the current directory if it starts with ../
+    if path.startswith("../"):
+        path = path[3:]  # Remove the ../
+    
+    if os.path.exists(path):
+        with open(path, "r") as code_file:
+            code = code_file.read()
+            return f".. code-block:: {language}\n\n{code}\n\n"
+    else:
+        return f".. warning:: File {path} not found\n\n"
+
 res = ""
 with open("README_template.rst", "r") as f:
-    for line in f.readlines():
-        line = line.strip("\n").replace(".. include:: ", "")
-        if line.endswith(".rst"):
-            tf = open(line, "r").read()
-            res += tf.replace(".. literalinclude:: ../LICENSE", "").replace("<../LICENSE>", "<LICENSE>").replace(":class:", " ")
+    lines = f.readlines()
+    i = 0
+    while i < len(lines):
+        line = lines[i].strip("\n")
+        i += 1
+        
+        # Handle include directives
+        if line.startswith(".. include:: "):
+            include_path = line.replace(".. include:: ", "")
+            if include_path.endswith(".rst"):
+                with open(include_path, "r") as tf:
+                    content = tf.read()
+                    # Process literalinclude directives inside the included file
+                    content = re.sub(r'\.\. literalinclude:: (.*?)\n\s+:language: (.*?)\n', 
+                        lambda m: process_literalinclude(m.group(1), m.group(2)), content)
+                    res += content.replace(".. literalinclude:: ../LICENSE", "").replace("<../LICENSE>", "<LICENSE>").replace(":class:", " ")
+        # Handle literalinclude directives directly in the template
+        elif line.startswith(".. literalinclude:: "):
+            # Extract path and language
+            path_match = re.match(r'\.\. literalinclude:: (.*)', line)
+            if path_match:
+                include_path = path_match.group(1)
+                # Read the next line to get the language if available
+                language = "python"  # Default language
+                if i < len(lines) and lines[i].strip().startswith(":language:"):
+                    language = lines[i].strip().replace(":language:", "").strip()
+                    i += 1  # Skip the language line since we've processed it
+                
+                res += process_literalinclude(include_path, language)
         else:
             res += line + "\n"
 
-    print(res)
+print(res)
 
 with open("README.rst", "w+") as f:
     f.write(res)

azure-pipelines.yml

@@ -9,18 +9,15 @@ trigger:
 
 strategy:
   matrix:
-    linux38:
-      imageName: "ubuntu-latest"
-      python.version: '3.8'
-    linux39:
-      imageName: "ubuntu-latest"
-      python.version: '3.9'
     linux310:
       imageName: "ubuntu-latest"
       python.version: '3.10'
     linux311:
       imageName: "ubuntu-latest"
       python.version: '3.11'
+    linux312:
+      imageName: "ubuntu-latest"
+      python.version: '3.12'
 
   maxParallel: 9
 

deploy.sh

@@ -1,4 +1,4 @@
 #!/usr/bin/env bash
 rm -rf ./build/ ./dist/ ./pysad.egg-info/
-python setup.py sdist bdist_wheel
-python3 -m twine upload dist/*
+python3 -m build
+python3 -m twine upload dist/*

docs/api.rst

@@ -43,6 +43,7 @@ Individual Anomaly Models
     models.ExactStorm
     models.HalfSpaceTrees
     models.IForestASD
+    models.Inqmad
     models.KitNet
     models.KNNCAD
     models.LODA
@@ -169,14 +170,14 @@ Postprocessors
    :template: class.rst
    :toctree: generated
 
-    pysad.transform.postprocessing.AveragePostprocessor
-    pysad.transform.postprocessing.MaxPostprocessor
-    pysad.transform.postprocessing.MedianPostprocessor
-    pysad.transform.postprocessing.ZScorePostprocessor
-    pysad.transform.postprocessing.RunningAveragePostprocessor
-    pysad.transform.postprocessing.RunningMaxPostprocessor
-    pysad.transform.postprocessing.RunningMedianPostprocessor
-    pysad.transform.postprocessing.RunningZScorePostprocessor
+    transform.postprocessing.AveragePostprocessor
+    transform.postprocessing.MaxPostprocessor
+    transform.postprocessing.MedianPostprocessor
+    transform.postprocessing.ZScorePostprocessor
+    transform.postprocessing.RunningAveragePostprocessor
+    transform.postprocessing.RunningMaxPostprocessor
+    transform.postprocessing.RunningMedianPostprocessor
+    transform.postprocessing.RunningZScorePostprocessor
 
 
 Statistics

docs/conf.py

@@ -76,9 +76,8 @@
 
 html_theme_options = {
     'canonical_url': '',
-    'analytics_id': 'UA-XXXXXXX-1',  #  Provided by Google in your dashboard
     'logo_only': True,
-    'display_version': False,
+    'version_selector': False,
     'prev_next_buttons_location': 'bottom',
     'style_external_links': False,
     #'vcs_pageview_mode': '',
@@ -112,3 +111,5 @@
     # 'matplotlib': ('https://matplotlib.org/', None),
     #'sklearn': ('https://scikit-learn.org/stable', None)
 }
+
+bibtex_bibfiles = ['refs.bib']

docs/examples.rst

@@ -1,6 +1,14 @@
 Examples
 ========
 
+Quick Start
+^^^^^^^^^^^^^^^^^^
+
+Here's a simple example showing how to use PySAD for anomaly detection on streaming data:
+
+.. literalinclude:: ../examples/example_usage_short.py
+   :language: python
+
 
 Example Full Usage
 ^^^^^^^^^^^^^^^^^^