Merge pull request #7 from jmbhughes/1.0.0

1.0.0

.github/workflows/codecov.yaml → .github/workflows/ci.yaml

@@ -1,4 +1,4 @@
-name: codecov
+name: ci
 on: [push]
 jobs:
   run:
@@ -8,13 +8,13 @@ jobs:
         os: [ubuntu-latest]
     env:
       OS: ${{ matrix.os }}
-      PYTHON: '3.7'
+      PYTHON: '3.10.12'
     steps:
     - uses: actions/checkout@master
     - name: Setup Python
       uses: actions/setup-python@master
       with:
-        python-version: 3.7
+        python-version: "3.10.12"
     - name: Generate coverage report
       run: |
         pip install ".[test]"

.github/workflows/python-publish.yaml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build -s
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

crcf/forest.py

@@ -3,7 +3,6 @@
 import crcf.tree
 import crcf.rule
 import numpy as np
-import pickle
 
 
 class CombinationForest:
@@ -49,11 +48,8 @@ def save(self, path: str) -> None:
         -------
         None
         """
-        # TODO: change this to a more robust save method
-        if not path.lower().endswith('.pkl'):
-            raise RuntimeError("Save paths should end with .pkl")
-        with open(path, 'wb') as f:
-            pickle.dump(self, f)
+        raise NotImplementedError("Saving was removed for a pickle vulnerability.")
+
 
     @classmethod
     def load(cls, path: str) -> CombinationForest:
@@ -69,9 +65,7 @@ def load(cls, path: str) -> CombinationForest:
         CombinationForest
             the loaded tree
         """
-        with open(path, 'rb') as f:
-            forest = pickle.load(f)
-        return forest
+        raise NotImplementedError("Saving was removed for a pickle vulnerability.")
 
     def depth(self, x: np.ndarray,
               estimated: bool = True) -> np.ndarray:

crcf/tree.py

@@ -4,7 +4,6 @@
 from graphviz import Digraph
 from .rule import Rule, AxisAlignedRule, NonAxisAlignedRule
 from dataclasses import dataclass
-import pickle
 
 
 @dataclass(repr=False)
@@ -275,11 +274,7 @@ def save(self, path: str) -> None:
         -------
         None
         """
-        # TODO: change this to a more robust save method
-        if not path.lower().endswith('.pkl'):
-            raise RuntimeError("Save paths should end with .pkl")
-        with open(path, 'wb') as f:
-            pickle.dump(self, f)
+        raise NotImplementedError("Saving was removed for a pickle vulnerability.")
 
     @classmethod
     def load(cls, path: str) -> CombinationTree:
@@ -295,9 +290,7 @@ def load(cls, path: str) -> CombinationTree:
         CombinationTree
             the loaded tree
         """
-        with open(path, 'rb') as f:
-            tree = pickle.load(f)
-        return tree
+        raise NotImplementedError("Loading was removed for a pickle vulnerability.")
 
     def depth(self, x: np.ndarray,
               estimated: bool = True) -> float:
@@ -435,7 +428,7 @@ def score(self, x: np.ndarray,
         if normalize:
             disp = disp / (self.root.count - 1)
             depths = depths / self.root.count
-        return depth_weight * depths + disp_weight * disp
+        return depth_weight * 1/depths + disp_weight * disp
 
     def remove_by_node(self, node: Node) -> None:
         """Remove the specified node using RRCF rules
@@ -649,7 +642,7 @@ def score(self, x: np.ndarray, estimated: bool = False) -> np.ndarray:
 
 
 class RobustRandomCutTree(CombinationTree):
-    def __init__(self,  depth_limit: Optional[int] = None) -> None:
+    def __init__(self, depth_limit: Optional[int] = None) -> None:
         super().__init__(depth_limit=depth_limit, rule_kind=AxisAlignedRule, rule_mode="biased")
 
     def depth(self, x: np.ndarray,

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crcf"
-version = "0.0.4"
+version = "1.0.0"
 authors = [
     { name="J. Marcus Hughes", email="[email protected]"}
 ]