Modify create_hnsw_index

.github/workflows/tests_workflow.yml

@@ -0,0 +1,27 @@
+name: tests_workflow
+
+# execute this workflow automatically when a we push to any branch
+on: [push]
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - name: Install dependencies
+        run: |
+          pip install pytest
+      - name: Install PARC
+        run: |
+          pip install .
+      - name: Run Python tests -x
+        run: |
+          pytest tests/
+        continue-on-error: false
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true

.gitignore

@@ -1,3 +1,5 @@
 env/
 */__pycache__
 *.egg-info
+.eggs/
+.DS_Store

README.md

@@ -76,7 +76,7 @@ plt.scatter(X[:, 0], X[:, 1], c=parc_labels, cmap='rainbow')
 plt.show()
 
 # Run umap on the HNSW knngraph already built in PARC (more time and memory efficient for large datasets)
-// Parc1.knn_struct = p1.make_knn_struct() // if you choose to visualize before running PARC clustering. then you need to include this line
+// Parc1.hnsw_index = p1.create_hnsw_index() // if you choose to visualize before running PARC clustering. then you need to include this line
 graph = Parc1.knngraph_full()
 X_umap = Parc1.run_umap_hnsw(X, graph)
 plt.scatter(X_umap[:, 0], X_umap[:, 1], c=Parc1.labels)

docs/Examples.rst

@@ -31,7 +31,7 @@ Examples
 	plt.show()
 
 	# Run umap on the HNSW knngraph already built in PARC (more time and memory efficient for large datasets)
-	# If you choose to visualize before running PARC clustering. then you need to include this line: Parc1.knn_struct = p1.make_knn_struct() 
+	# If you choose to visualize before running PARC clustering. then you need to include this line: Parc1.hnsw_index = p1.create_hnsw_index() 
 	graph = Parc1.knngraph_full()
 	X_umap = Parc1.run_umap_hnsw(X, graph)
 	plt.scatter(X_umap[:, 0], X_umap[:, 1], c=Parc1.labels)

parc/logger.py

@@ -0,0 +1,95 @@
+"""Custom colored logger.
+
+See:
+
+`StackOverflow <http://stackoverflow.com/a/24956305/408556>`__
+`python-colors GitHub <https://gist.github.com/dideler/3814182>`__
+
+"""
+
+import logging
+import sys
+
+MIN_LEVEL = logging.DEBUG
+MESSAGE = 25
+logging.addLevelName(MESSAGE, "MESSAGE")
+LOGGING_LEVEL = 25
+
+
+class LogFilter(logging.Filter):
+    """Filters (lets through) all messages with level < LEVEL"""
+    def __init__(self, level):
+        self.level = level
+
+    def filter(self, record):
+        # "<" instead of "<=": since logger.setLevel is inclusive, this should
+        # be exclusive
+        return record.levelno < self.level
+
+
+class Logger(logging.Logger):
+    def message(self, msg, *args, **kwargs):
+        if self.isEnabledFor(MESSAGE):
+            self._log(MESSAGE, msg, args, **kwargs)
+
+
+class ColoredFormatter(logging.Formatter):
+    def __init__(self, fmt_prefix, fmt_msg):
+        self.use_color = self.supports_color()
+        self.fmt_prefix = fmt_prefix
+        self.fmt_msg = fmt_msg
+        super().__init__(fmt=f"{fmt_prefix} {fmt_msg}")
+
+    def format(self, record: logging.LogRecord) -> str:
+        if record.levelno == logging.WARNING:
+            if self.use_color:
+                fmt = f"\x1b[93m{self.fmt_prefix}\x1b[0m {self.fmt_msg}"
+                formatter = logging.Formatter(fmt)
+                return formatter.format(record)
+            else:
+                return super().format(record)
+        elif record.levelno == logging.ERROR:
+            if self.use_color:
+                fmt = f"\x1b[91m{self.fmt_prefix}\x1b[0m {self.fmt_msg}"
+                formatter = logging.Formatter(fmt)
+                return formatter.format(record)
+            else:
+                return super().format(record)
+        elif record.levelno == 25 or record.levelno == logging.INFO:
+            if self.use_color:
+                fmt = f"\x1b[96m{self.fmt_prefix}\x1b[0m {self.fmt_msg}"
+                formatter = logging.Formatter(fmt)
+                return formatter.format(record)
+            else:
+                return super().format(record)
+
+    def supports_color(self) -> bool:
+        """Check if the system supports ANSI color formatting."""
+        return hasattr(sys.stdout, "isatty") and sys.stdout.isatty()
+
+
+def get_logger(module_name, level: int = LOGGING_LEVEL) -> Logger:
+    logging.setLoggerClass(Logger)
+    stdout_handler = logging.StreamHandler(sys.stdout)
+    stderr_handler = logging.StreamHandler(sys.stderr)
+    stdout_handler.addFilter(LogFilter(logging.WARNING))
+    stdout_handler.setLevel(level)
+    if level == 25:
+        formatter = ColoredFormatter(
+            fmt_prefix="[%(levelname)s]:",
+            fmt_msg="%(message)s"
+        )
+    else:
+        formatter = ColoredFormatter(
+            fmt_prefix="[%(levelname)s] %(name)s.%(funcName)s (line %(lineno)d):",
+            fmt_msg="%(message)s"
+        )
+    stdout_handler.setFormatter(formatter)
+    stderr_handler.setLevel(max(MIN_LEVEL, logging.WARNING))
+    # messages lower than WARNING go to stdout
+    # messages >= WARNING (and >= STDOUT_LOG_LEVEL) go to stderr
+    logger = logging.getLogger(module_name)
+    logger.propagate = False
+    logger.handlers = [stdout_handler, stderr_handler]
+    logger.setLevel(level)
+    return logger

parc/utils.py

@@ -0,0 +1,13 @@
+def get_mode(a_list: list[any]) -> any:
+    """Get the value which appears most often in the list (the mode).
+
+    If multiple items are maximal, the function returns the first one encountered
+    (not necessarily the first one in the list).
+
+    Args:
+        a_list: A list with values.
+
+    Returns:
+        The most frequent value in the list
+    """
+    return max(set(a_list), key=a_list.count)

pytest.ini

@@ -0,0 +1,4 @@
+[pytest]
+log_cli = true
+log_cli_level = 25
+addopts = -rP

requirements.txt

@@ -0,0 +1,8 @@
+pybind11
+numpy
+scipy
+pandas
+hnswlib
+igraph
+leidenalg>=0.7.0
+umap-learn

setup.py

@@ -1,25 +1,25 @@
 import setuptools
-
 from os import path
-this_directory = path.abspath(path.dirname(__file__))
-with open(path.join(this_directory, 'README.md'), encoding='utf-8') as f:
+
+PARC_DIR = path.abspath(path.dirname(__file__))
+
+with open(path.join(PARC_DIR, "README.md"), encoding="utf-8") as f:
     long_description = f.read()
 
 setuptools.setup(
-    name='parc',
-    version='0.40',  #May 28,2024
-    packages=['parc',],
-    license='MIT',
-    author_email='[email protected]',
-    url='https://github.com/ShobiStassen/PARC',
-    setup_requires=['numpy', 'pybind11'],
+    name="parc",
+    version="0.40",
+    packages=["parc"],
+    license="MIT",
+    author_email="[email protected]",
+    url="https://github.com/ShobiStassen/PARC",
+    setup_requires=["numpy", "pybind11"],
     install_requires=[
-        'pybind11', 'numpy', 'scipy', 'pandas', 'hnswlib', 'igraph',
-        'leidenalg>=0.7.0', 'umap-learn'
+        line.strip() for line in open("requirements.txt")
     ],
     extras_require={
         "dev": ["pytest", "scikit-learn"]
     },
     long_description=long_description,
-    long_description_content_type='text/markdown'
+    long_description_content_type="text/markdown"
 )