chore: update package config

.github/workflows/pull-request.yml

@@ -52,9 +52,7 @@ jobs:
     - name: Install pip dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install -r requirements.txt
-        python -m pip install -r requirements-dev.txt
-        python -m pip install -r requirements-test.txt
+        python -m pip install ".[dev,test]"
 
     - name: Install the package
       run: make install
@@ -103,10 +101,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install -r requirements.txt
-        python -m pip install -r requirements-dev.txt
-        python -m pip install -r requirements-test.txt
-        python -m pip install -r requirements-docs.txt
+        python -m pip install ".[dev,test,docs]"
 
     - name: Install the package
       run: make install

.github/workflows/release-deprecated.yml

@@ -34,9 +34,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install -r requirements.txt
-        python -m pip install -r requirements-dev.txt
-        python -m pip install -r requirements-test.txt
+        python -m pip install ".[dev,test]"
 
     - name: Install
       run: make install

.github/workflows/release.yml

@@ -35,9 +35,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install -r requirements.txt
-        python -m pip install -r requirements-dev.txt
-        python -m pip install -r requirements-test.txt
+        python -m pip install ".[dev,test]"
 
     - name: Install
       run: make install

.github/workflows/tests.yml

@@ -81,8 +81,7 @@ jobs:
           ${{ runner.os }}-${{ matrix.pandas }}-pip-
     - run: |
         pip install --upgrade pip setuptools wheel
-        pip install -r requirements.txt "${{ matrix.pandas }}" "${{ matrix.numpy }}"
-        pip install -r requirements-test.txt
+        pip install ".[test]" "${{ matrix.pandas }}" "${{ matrix.numpy }}"
     - run: echo "YDATA_PROFILING_NO_ANALYTICS=False" >> $GITHUB_ENV
     - run: make install
 
@@ -130,8 +129,7 @@ jobs:
           ${{ runner.os }}-${{ matrix.pandas }}-pip-
     - run: |
         pip install --upgrade pip setuptools wheel
-        pip install -r requirements.txt "${{ matrix.pandas }}" "${{ matrix.numpy }}"
-        pip install -r requirements-test.txt
+        pip install ".[test]" "${{ matrix.pandas }}" "${{ matrix.numpy }}"
         echo "YDATA_PROFILING_NO_ANALYTICS=False" >> $GITHUB_ENV
     - run: make install
 
@@ -146,8 +144,7 @@ jobs:
           ${{ runner.os }}-${{ matrix.pandas }}-pip-
     - run: |
         pip install --upgrade pip setuptools wheel
-        pip install -r requirements.txt "${{ matrix.pandas }}" "${{ matrix.numpy }}"
-        pip install -r requirements-test.txt
+        pip install ".[test]" "${{ matrix.pandas }}" "${{ matrix.numpy }}"
     - run: make install
     - run: make test_cov
     - run: codecov -F py${{ matrix.python-version }}-${{ matrix.os }}-${{ matrix.pandas }}-${{ matrix.numpy }}
@@ -205,14 +202,13 @@ jobs:
       - run: |
           pip install --upgrade pip setuptools wheel
           pip install pytest-spark>=0.6.0 pyarrow==1.0.1 pyspark=="${{ matrix.spark }}"
-          pip install -r requirements.txt
-          pip install -r requirements-test.txt
+          pip install ".[test]"
           pip install "${{ matrix.pandas }}" "${{ matrix.numpy }}"
       - if: ${{ matrix.spark != '3.0.1' }}
         run: echo "ARROW_PRE_0_15_IPC_FORMAT=1" >> $GITHUB_ENV
       - run: echo "SPARK_LOCAL_IP=127.0.0.1" >> $GITHUB_ENV
       - run: make install
       - run: make install-spark-ci
-      - run: pip install -r requirements-spark.txt # Make sure the proper version of pandas is install after everything
+      - run: pip install ".[spark]" # Make sure the proper version of pandas is install after everything
       - run: make test_spark
 

Makefile

@@ -29,10 +29,10 @@ package:
 	twine check dist/*
 
 install:
-	pip install -e .[notebook]
+	pip install -e ".[notebook]"
 
 install-docs: install ### Installs regular and docs dependencies
-	pip install -r requirements-docs.txt
+	pip install -e ".[docs]"
 
 install-spark-ci:
 	sudo apt-get update

docs/support-contribution/contribution_guidelines.md

@@ -33,7 +33,7 @@ To activate the local mechanisms (created using pre-commit hooks), run the
 following commands:
 
 ``` console
-pip install -r requirements-dev.txt
+pip install ".[dev]"
 pre-commit install --hook-type commit-msg --hook-type pre-commit
 ```
 

pyproject.toml

@@ -0,0 +1,135 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ydata-profiling"
+authors = [
+    {name = "YData Labs Inc", email = "[email protected]"},
+]
+description="Generate profile report for pandas DataFrame"
+readme = "README.md"
+requires-python=">=3.7, <3.13"
+keywords=["pandas", "data-science", "data-analysis", "python", "jupyter", "ipython"]
+license = {text = "MIT"}
+classifiers=[
+    "Development Status :: 5 - Production/Stable",
+    "Topic :: Software Development :: Build Tools",
+    "License :: OSI Approved :: MIT License",
+    "Environment :: Console",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Financial and Insurance Industry",
+    "Intended Audience :: Healthcare Industry",
+    "Topic :: Scientific/Engineering",
+    "Framework :: IPython",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+
+dependencies = [
+    "scipy>=1.4.1, <1.14",
+    "pandas>1.1, <3.0, !=1.4.0",
+    "matplotlib>=3.5, <=3.10",
+    "pydantic>=2",
+    "PyYAML>=5.0.0, <6.1",
+    "jinja2>=2.11.1, <3.2",
+    "visions[type_image_path]>=0.7.5, <0.7.7",
+    "numpy>=1.16.0,<2.2",
+    # Could be optional
+    # Related to HTML report
+    "htmlmin==0.1.12",
+    # Correlations
+    "phik>=0.11.1,<0.13",
+    # Examples
+    "requests>=2.24.0, <3",
+    # Progress bar
+    "tqdm>=4.48.2, <5",
+    "seaborn>=0.10.1, <0.14",
+    "multimethod>=1.4, <2",
+    # metrics
+    "statsmodels>=0.13.2, <1",
+    # type checking
+    "typeguard>=3, <5",
+    "imagehash==4.3.1",
+    "wordcloud>=1.9.3",
+    "dacite>=1.8",
+    "numba>=0.56.0, <1",
+]
+
+dynamic = ["version"]
+
+[project.optional-dependencies]
+# dependencies for development and testing
+dev = [
+    "black>=20.8b1",
+    "isort>=5.0.7",
+    "pre-commit>=2.8.2",
+    "virtualenv>=20.0.33",
+    "twine",
+    "wheel",
+    "myst-parser>=0.18.1",
+    "sphinx_rtd_theme>=0.4.3",
+    "sphinx-autodoc-typehints>=1.10.3",
+    "sphinx-multiversion>=0.2.3",
+    "autodoc_pydantic",
+]
+# this provides the recommended pyspark and pyarrow versions for spark to work on pandas-profiling
+# note that if you are using pyspark 2.3 or 2.4 and pyarrow >= 0.15, you might need to
+# set ARROW_PRE_0_15_IPC_FORMAT=1 in your conf/spark-env.sh for toPandas functions to work properly
+spark = [
+    "pyspark>=2.3.0",
+    "pyarrow>=2.0.0",
+    "pandas>1.1, <2, !=1.4.0",
+    "numpy>=1.16.0,<1.24",
+    "visions[type_image_path]==0.7.5",
+]
+test = [
+    "pytest",
+    "coverage>=6.5, <8",
+    "codecov",
+    "pytest-cov",
+    "pytest-spark",
+    "nbval",
+    "pyarrow",
+    "twine>=3.1.1",
+    "kaggle",
+]
+notebook = [
+    "jupyter>=1.0.0",
+    "ipywidgets>=7.5.1",
+]
+docs = [
+    "mkdocs>=1.6.0,<1.7.0",
+    "mkdocs-material>=9.0.12,<10.0.0",
+    "mkdocs-material-extensions>=1.1.1,<2.0.0",
+    "mkdocs-table-reader-plugin<=2.2.0",
+    "mike>=2.1.1,<2.2.0",
+    "mkdocstrings[python]>=0.20.0,<1.0.0",
+    "mkdocs-badges",
+]
+unicode= [
+    "tangled-up-in-unicode==0.2.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+ydata_profiling = ["py.typed"]
+
+[tool.setuptools]
+include-package-data = true
+
+[project.scripts]
+ydata_profiling = "ydata_profiling.controller.console:main"
+pandas_profiling = "ydata_profiling.controller.console:main"
+
+[project.urls]
+homepage = "https://github.com/ydataai/ydata-profiling"

setup.py

@@ -1,16 +1,12 @@
 from pathlib import Path
 
-from setuptools import find_packages, setup
+from setuptools import setup
 
 # Read the contents of README file
 source_root = Path(".")
 with (source_root / "README.md").open(encoding="utf-8") as f:
     long_description = f.read()
 
-# Read the requirements
-with (source_root / "requirements.txt").open(encoding="utf8") as f:
-    requirements = f.readlines()
-
 try:
     version = (source_root / "VERSION").read_text().rstrip("\n")
 except FileNotFoundError:
@@ -20,58 +16,8 @@
     version_file.write(f"__version__ = '{version}'")
 
 setup(
-    name="ydata-profiling",
     version=version,
-    author="YData Labs Inc",
-    author_email="[email protected]",
-    packages=find_packages("src"),
-    package_dir={"": "src"},
-    url="https://github.com/ydataai/ydata-profiling",
-    license="MIT",
-    description="Generate profile report for pandas DataFrame",
-    python_requires=">=3.7, <3.13",
-    install_requires=requirements,
-    extras_require={
-        "notebook": [
-            "jupyter>=1.0.0",
-            "ipywidgets>=7.5.1",
-        ],
-        "unicode": [
-            "tangled-up-in-unicode==0.2.0",
-        ],
-    },
-    package_data={
-        "ydata_profiling": ["py.typed"],
-    },
-    include_package_data=True,
-    classifiers=[
-        "Development Status :: 5 - Production/Stable",
-        "Topic :: Software Development :: Build Tools",
-        "License :: OSI Approved :: MIT License",
-        "Environment :: Console",
-        "Operating System :: OS Independent",
-        "Intended Audience :: Science/Research",
-        "Intended Audience :: Developers",
-        "Intended Audience :: Financial and Insurance Industry",
-        "Intended Audience :: Healthcare Industry",
-        "Topic :: Scientific/Engineering",
-        "Framework :: IPython",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-        "Programming Language :: Python :: 3.12",
-    ],
-    keywords="pandas data-science data-analysis python jupyter ipython",
     long_description=long_description,
     long_description_content_type="text/markdown",
-    entry_points={
-        "console_scripts": [
-            "ydata_profiling = ydata_profiling.controller.console:main",
-            "pandas_profiling = ydata_profiling.controller.console:main",
-        ]
-    },
     options={"bdist_wheel": {"universal": True}},
 )