Merge pull request #6 from soda-inria/package4

Package4

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 120
+ignore = E203, E402, E265, F403, W503, W504, E731
+exclude = .git, venv*, docs, build
+per-file-ignores = **/__init__.py:F401

.github/workflows/style.yml

@@ -1,183 +1,96 @@
 name: style
 
-
-
 on:
-
   push:
-
     branches: [main, develop]
-
   pull_request:
-
     branches: [main, develop]
 
-
-
 jobs:
-
   flake8:
-
     runs-on: ${{ matrix.os }}
-
     strategy:
-
       matrix:
-
         os: [ubuntu-latest]
-
-        python: [3.8]
+        python: [3.10, 3.11]
 
     steps:
-
       - uses: actions/checkout@v2
-
       - name: Set up Python
-
         uses: actions/setup-python@v1
-
         with:
-
           python-version: ${{ matrix.python }}
-
           architecture: x64
-
       - name: Run flake8
-
         run: |
-
           pip install flake8
-
           flake8 --version
-
-          flake8
-
-
+          flake8 carte/carte_ai
 
   isort:
-
     runs-on: ${{ matrix.os }}
-
     strategy:
-
       matrix:
-
         os: [ubuntu-latest]
-
-        python: [3.8]
+        python: [3.10, 3.11]
 
     steps:
-
       - uses: actions/checkout@v2
-
       - name: Set up Python
-
         uses: actions/setup-python@v1
-
         with:
-
           python-version: ${{ matrix.python }}
-
           architecture: x64
-
       - name: Run isort
-
         run: |
-
           pip install isort
-
           isort --version
-
-          isort .
-
+          isort carte/carte_ai
           if [ -n "$(git status --porcelain --untracked-files=no)" ]; then exit 1; else echo "All clear"; fi
 
-
-
   mypy:
-
     runs-on: ${{ matrix.os }}
-
     strategy:
-
       matrix:
-
         os: [ubuntu-latest]
-
-        python: [3.8]
+        python: [3.10, 3.11]
 
     steps:
-
       - uses: actions/checkout@v2
-
       - name: Set up Python
-
         uses: actions/setup-python@v1
-
         with:
-
           python-version: ${{ matrix.python }}
-
           architecture: x64
-
       - name: Cache python modules
-
         uses: actions/cache@v2
-
         with:
-
           path: ~/.cache/pip
-
           key: ${{ runner.os }}-python-${{ matrix.python }}-${{ hashFiles('pyproject.toml') }}
-
       - name: Install dependencies
-
         run: |
-
           pip install mypy
-
       - name: Run mypy
-
         run: |
-
           mypy --version
-
-          mypy
-
-
+          mypy carte/carte_ai
 
   black:
-
     runs-on: ${{ matrix.os }}
-
     strategy:
-
       matrix:
-
         os: [ubuntu-latest]
-
-        python: [3.8]
+        python: [3.10, 3.11]
 
     steps:
-
       - uses: actions/checkout@v2
-
       - name: Set up Python
-
         uses: actions/setup-python@v2
-
         with:
-
           python-version: ${{ matrix.python }}
-
           architecture: x64
-
       - name: Run black
-
         run: |
-
           pip install black
-
           black --version
-
-          black --check --diff .
+          black --check --diff carte/carte_ai

.gitignore

@@ -1,3 +1,128 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+*.egg
+*.egg-info/
+dist/
+build/
+*.egg-info/
+.eggs/
+
+# 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
+*.cover
+.cache
+nosetests.xml
+coverage.xml
+*.coveragerc
+*.py,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery beat schedule files
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+*.env
+*.env.*
+
+# IDEs and editors
+.vscode/
+.idea/
+*.sublime-workspace
+
+# PyCharm
+*.iml
+*.iws
+.idea/
+out/
+
+# VS Code
+.vscode/
+
+# MacOS
+.DS_Store
+
+# Thumbnails
+._*
+
+# Windows
+Thumbs.db
+ehthumbs.db
+Desktop.ini
+
+# Visual Studio
+.vs/
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# PyCharm working directory
+.idea/
+
+
 # Data
 data/data_multitable/
 data/data_singletable/

carte_ai/__init__.py

@@ -2,4 +2,4 @@
 from carte_ai.configs import *
 from carte_ai.data import *
 from carte_ai.scripts import *
-from .src import CARTERegressor, CARTEClassifier, Table2GraphTransformer
+from .src import CARTERegressor, CARTEClassifier, Table2GraphTransformer

carte_ai/configs/carte_configs.py

@@ -1,6 +1,6 @@
 """Specific configurations for the CARTE paper."""
 
-## Dataset names
+# Dataset names
 carte_datalist = [
     "anime_planet",
     "babies_r_us",
@@ -55,7 +55,7 @@
     "zomato",
 ]
 
-## Dictionary of baseline methods
+# Dictionary of baseline methods
 carte_singletable_baselines = dict()
 carte_singletable_baselines["full"] = [
     "carte-gnn",
@@ -110,7 +110,7 @@
 ]
 
 
-## Dictionary of method mapping
+# Dictionary of method mapping
 carte_singletable_baseline_mapping = dict()
 carte_singletable_baseline_mapping["carte-gnn"] = "CARTE"
 
@@ -137,7 +137,7 @@
 # Bagging
 carte_singletable_baseline_mapping["bagging"] = "Bagging"
 
-## Colors for visualization
+# Colors for visualization
 carte_singletable_color_palette = dict()
 carte_singletable_color_palette["CARTE"] = "C3"
 carte_singletable_color_palette["CatBoost"] = "C0"
@@ -151,7 +151,7 @@
 carte_singletable_color_palette["TabVec-MLP"] = "C9"
 carte_singletable_color_palette["TarEnc-TabPFN"] = "#A9561E"
 
-## Markers for visualization
+# Markers for visualization
 carte_singletable_markers = dict()
 carte_singletable_markers["CARTE"] = "o"
 carte_singletable_markers["TabVec-XGB"] = (4, 0, 45)

carte_ai/configs/directory.py

@@ -1,13 +1,17 @@
 from pathlib import Path
 
 # Get the base path relative to this file's location
-base_path = Path(__file__).resolve().parent.parent  # This gives '/home/infres/gbrison/carte/carte_ai'
+base_path = (
+    Path(__file__).resolve().parent.parent
+)  # This gives '/home/infres/gbrison/carte/carte_ai'
 
 config_directory = dict()
 config_directory["base_path"] = base_path
 
 config_directory["data"] = str(base_path / "data/")
-config_directory["pretrained_model"] = str(base_path / "data/etc/kg_pretrained.pt")  # Correct path
+config_directory["pretrained_model"] = str(
+    base_path / "data/etc/kg_pretrained.pt"
+)  # Correct path
 config_directory["data_raw"] = str(base_path / "data/data_raw/")
 config_directory["data_singletable"] = str(base_path / "data/data_singletable/")
 config_directory["data_yago"] = str(base_path / "data/data_yago/")