Merge pull request #480 from WenjieDu/dev

Add pyproject.toml, gather dependency files, and fix flake8 with toml config file

.github/workflows/linting.yml

@@ -23,8 +23,8 @@ jobs:
 
             - name: Install Flake8
               run: |
-                pip install flake8
+                pip install flake8 flake8-pyproject
 
             - name: Run linting
               run: |
-                flake8 .
+                flake8 .

.github/workflows/publish_to_PyPI.yml

@@ -39,7 +39,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install build wheel
-        pip install -r requirements.txt
+        pip install -r requirements/requirements.txt
 
     - name: Fetch the test environment details
       run: |

.github/workflows/testing_ci.yml

@@ -34,26 +34,29 @@ jobs:
                 check-latest: true
                 cache: pip
                 cache-dependency-path: |
-                  setup.cfg
+                  requirements/requirements.txt
+                  requirements/requirements_dev.txt
 
             - name: Install PyTorch ${{ matrix.pytorch-version }}+cpu
               # we have to install torch in advance because torch_sparse needs it for compilation,
               # refer to https://github.com/rusty1s/pytorch_sparse/issues/156#issuecomment-1304869772 for details
               run: |
                   which python
                   which pip
-                  pip install numpy==1.24 torch==${{ matrix.pytorch-version }} -f https://download.pytorch.org/whl/cpu
+                  pip install torch==${{ matrix.pytorch-version }} -f https://download.pytorch.org/whl/cpu
                   python -c "import torch; print('PyTorch:', torch.__version__)"
 
             - name: Install other dependencies
               run: |
-                  pip install -r requirements.txt
+                  pip install -r requirements/requirements.txt
+                  pip install numpy==1.24  # many libs not compatible with numpy 2.0. Note 3.12 requests for numpy>=2.0
+                  pip install pandas==1.5  # fix pandas version to avoid installing pandas 2.0, the same reason with numpy
 
             - name: Test building package
               # we need to know if the package can be built successfully without optional dependencies
               run: |
                   pip install build wheel
-                  python -m build --no-isolation
+                  python -m build
 
             - name: Continue to install torch-geometric dependencies
               run: |

.readthedocs.yaml

@@ -23,7 +23,7 @@ build:
             - python -m pip install --upgrade pip
             - pip install torch==1.13.1 -f https://download.pytorch.org/whl/cpu
             - pip install torch-geometric==2.3.1 torch-scatter==2.1.1 torch-sparse==0.6.17 -f "https://data.pyg.org/whl/torch-1.13.1+cpu.html"
-            - pip install -r requirements.txt
+            - pip install -r requirements/requirements.txt
             - pip install pypots
             - pip install sphinx==6.2.1 docutils==0.19 sphinxcontrib-bibtex==2.1.4 sphinxcontrib-gtagjs sphinx-autodoc-typehints furo==2023.07.26
             - git clone https://github.com/WenjieDu/TSDB TSDB_repo --depth 1 && pip install ./TSDB_repo

pypots/__init__.py

@@ -6,26 +6,16 @@
 # License: BSD-3-Clause
 
 
-# PyPOTS version
-#
-# PEP0440 compatible formatted version, see:
-# https://www.python.org/dev/peps/pep-0440/
-# Generic release markers:
-# X.Y
-# X.Y.Z # For bugfix releases
-#
-# Admissible pre-release markers:
-# X.YaN # Alpha release
-# X.YbN # Beta release
-# X.YrcN # Release Candidate
-# X.Y # Final release
-#
-# Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
-# 'X.Y.dev0' is the canonical version of 'X.Y.dev'
-__version__ = "0.7"
-
-
-from . import imputation, classification, clustering, forecasting, optim, data, utils
+from . import (
+    imputation,
+    classification,
+    clustering,
+    forecasting,
+    optim,
+    data,
+    utils,
+)
+from .version import __version__
 
 __all__ = [
     "imputation",

pypots/version.py

@@ -0,0 +1,25 @@
+"""
+
+"""
+
+# Created by Wenjie Du <[email protected]>
+# License: BSD-3-Clause
+
+
+# PyPOTS version
+#
+# PEP0440 compatible formatted version, see:
+# https://www.python.org/dev/peps/pep-0440/
+# Generic release markers:
+# X.Y
+# X.Y.Z # For bugfix releases
+#
+# Admissible pre-release markers:
+# X.YaN # Alpha release
+# X.YbN # Beta release
+# X.YrcN # Release Candidate
+# X.Y # Final release
+#
+# Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
+# 'X.Y.dev0' is the canonical version of 'X.Y.dev'
+__version__ = "0.7"

pyproject.toml

@@ -0,0 +1,91 @@
+[build-system]
+requires = ["setuptools>=71"]
+
+[project]
+name = "pypots"
+description = "A Python Toolbox for Machine Learning on Partially-Observed Time Series"
+authors = [{ name = "Wenjie Du", email = "[email protected]" }]
+dynamic = ["version", "readme", "dependencies", "optional-dependencies"]
+license = { file = "LICENSE" }
+requires-python = ">=3.8"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Healthcare Industry",
+    "License :: OSI Approved :: BSD License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Application Frameworks",
+]
+keywords = [
+    "data science",
+    "data mining",
+    "neural networks",
+    "machine learning",
+    "deep learning",
+    "artificial intelligence",
+    "time-series analysis",
+    "time series",
+    "imputation",
+    "interpolation",
+    "classification",
+    "clustering",
+    "forecasting",
+    "partially observed",
+    "irregular sampled",
+    "partially-observed time series",
+    "incomplete time series",
+    "missing data",
+    "missing values",
+]
+
+[project.scripts]
+pypots-cli = "pypots.cli.pypots_cli:main"
+
+[project.urls]
+Source = "https://github.com/WenjieDu/PyPOTS"
+Homepage = "https://pypots.com"
+Documentation = "https://docs.pypots.com"
+"Bug Tracker" = "https://github.com/WenjieDu/PyPOTS/issues"
+Download = "https://github.com/WenjieDu/PyPOTS/archive/main.zip"
+
+[tool.setuptools.packages.find]
+exclude = [
+    "*template",
+    "*README.md",
+    "docs*",
+    "test*",
+    "requirements*",
+]
+
+[tool.setuptools.dynamic]
+version = { attr = "pypots.version.__version__" }
+readme = { file = "README.md", content-type = "text/markdown" }
+dependencies = { file = "requirements/requirements.txt" }
+optional-dependencies.dev = { file = "requirements/requirements_dev.txt" }
+
+[tool.flake8]
+# People may argue that coding style is personal. This may be true if the project is personal and one works like a
+# hermit, but to PyPOTS and its community, the answer is NO.
+# We use Black and Flake8 to lint code style and keep the style consistent across all commits and pull requests.
+# Black only reformats the code, and Flake8 is necessary for checking for some other issues not covered by Black.
+
+# The Black line length is default as 88, while the default of Flake8 is 79. However, considering our monitors are
+# much more advanced nowadays, I extend the maximum line length to 120, like other project e.g. transformers. People
+# who prefer the default setting can keep using 88 or 79 while coding. Please ensure your code lines not exceeding 120.
+max-line-length = 120
+# why ignore E203? Refer to https://github.com/PyCQA/pycodestyle/issues/373
+extend-ignore = """
+    E203
+"""
+# ignore some errors that are not important in template files
+exclude = [
+    "*/template"
+]

environment-dev.yml → requirements/conda_env.yml

@@ -1,4 +1,4 @@
-name: pypots-dev
+name: pypots
 
 channels:
     - conda-forge
@@ -16,11 +16,12 @@ dependencies:
     - conda-forge::python
     - conda-forge::einops
     - conda-forge::pandas
+    - conda-forge::seaborn
     - conda-forge::matplotlib
     - conda-forge::tensorboard
     - conda-forge::scikit-learn
-    - conda-forge::tsdb >=0.4
     - conda-forge::pygrinder >=0.6
+    - conda-forge::tsdb >=0.6
     - conda-forge::benchpots >=0.2
     - pytorch::pytorch >=1.10.0
     ## Below we install the latest pypots because we need pypots-cli in it for development.
@@ -49,7 +50,7 @@ dependencies:
     - conda-forge::jupyterlab
 
     - pip:
+        # building
+        - build
         # doc
         - sphinxcontrib-gtagjs
-        # hyperparameter tuning
-        - nni

tests/environment_for_conda_test.yml → requirements/environment_for_conda_test.yml

@@ -16,10 +16,11 @@ dependencies:
     - conda-forge::numpy
     - conda-forge::einops
     - conda-forge::pandas
+    - conda-forge::seaborn
     - conda-forge::matplotlib
     - conda-forge::tensorboard
     - conda-forge::scikit-learn
-    - conda-forge::tsdb >=0.4
+    - conda-forge::tsdb >=0.6
     - conda-forge::pygrinder >=0.6
     - conda-forge::benchpots >=0.2
     - conda-forge::protobuf <=4.21.12
@@ -46,5 +47,5 @@ dependencies:
     - conda-forge::flake8
 
     - pip:
-          # doc
-          - sphinxcontrib-gtagjs
+        # doc
+        - sphinxcontrib-gtagjs

requirements/requirements.txt

@@ -0,0 +1,14 @@
+h5py
+numpy
+scipy
+sympy
+einops
+pandas
+seaborn
+matplotlib
+tensorboard
+scikit-learn
+torch>=1.10.0
+tsdb>=0.6
+pygrinder>=0.6
+benchpots>=0.2

requirements/requirements_dev.txt

@@ -0,0 +1,16 @@
+build
+torch-sparse
+torch-scatter
+torch-geometric
+pre-commit
+jupyterlab
+black
+flake8
+flake8-pyproject
+pytest-cov
+pytest-xdist
+furo
+sphinx
+sphinxcontrib-bibtex
+sphinxcontrib-gtagjs
+sphinx-autodoc-typehints