Changing the package name and updating files

.github/workflows/matchers/mypy.json

@@ -1,18 +1,18 @@
 {
-    "problemMatcher": [
+  "problemMatcher": [
+    {
+      "owner": "mypy",
+      "severity": "error",
+      "pattern": [
         {
-            "owner": "mypy",
-            "severity": "error",
-            "pattern": [
-                {
-                    "regexp": "^(\\S*):(\\d+):(\\d+): ([a-z]+): (.*)$",
-                    "file": 1,
-                    "line": 2,
-                    "column": 3,
-                    "severity": 4,
-                    "message": 5
-                }
-            ]
+          "regexp": "^(\\S*):(\\d+):(\\d+): ([a-z]+): (.*)$",
+          "file": 1,
+          "line": 2,
+          "column": 3,
+          "severity": 4,
+          "message": 5
         }
-    ]
-}
+      ]
+    }
+  ]
+}

.github/workflows/mypy.yml

@@ -0,0 +1,70 @@
+name: mypy
+
+on:
+  - pull_request
+
+jobs:
+  mypy:
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      fail-fast: true
+      matrix:
+        os: ["ubuntu-latest", "macos-latest"]
+        python-version: ["3.10", "3.11"]
+    runs-on: ${{ matrix.os }}
+    steps:
+      #----------------------------------------------
+      #       check-out repo and set-up python
+      #----------------------------------------------
+      - name: Check out repository
+        uses: actions/checkout@v4
+      - name: Set up python ${{ matrix.python-version }}
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      #----------------------------------------------
+      #        -----  install poetry  -----
+      #----------------------------------------------
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+
+      #----------------------------------------------
+      #      install or use cached dependencies
+      #----------------------------------------------
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v3
+        with:
+          path: .venv
+          key: venv-${{ runner.os }}-python-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+      - name: Install dependencies
+        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        run: |
+          poetry install --no-interaction --no-root --all-extras --without dev
+
+      # always install current root package
+      - name: Install library
+        run: poetry install --no-interaction --all-extras --without dev
+
+      #----------------------------------------------
+      #  -----  setup matchers & run mypy   -----
+      #----------------------------------------------
+      - name: Setup matchers
+        run: |
+          echo "::add-matcher::.github/workflows/matchers/mypy.json"
+          echo "TERM: changing from $TERM -> xterm"
+          export TERM=xterm
+      - name: Run mypy
+        # NOTE: tomli is sometimes missing, install it explicitly
+        run: |
+          source $VENV
+          pip install tomli
+          pip install "mypy>=1.7.0"
+          mypy --show-column-numbers .

.github/workflows/publish.yml

@@ -1,36 +1,59 @@
-name: Publish to PyPI
+# This workflow will upload a Python Package to PyPI 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:
-  push:
-    tags:
-      - 'v0.1.1'
+  release:
+    types: [published]
+
+permissions:
+  contents: read
 
 jobs:
-  publish:
+  pypi-publish:
+    name: Upload release to PyPI
     runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/synthius/
+    permissions:
+      id-token: write
 
     steps:
-      - name: Check out code
-        uses: actions/checkout@v3
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
+      #----------------------------------------------
+      #       check-out repo and set-up python
+      #----------------------------------------------
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v5
         with:
-          python-version: '3.10.10'
+          python-version: "3.10"
 
+      #----------------------------------------------
+      #        -----  install poetry  -----
+      #----------------------------------------------
       - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python3 -
-
-      - name: Configure Poetry
-        run: poetry config virtualenvs.create false
+        uses: snok/install-poetry@v1
 
+      #----------------------------------------------
+      #   install dependencies and build packages
+      #----------------------------------------------
       - name: Install dependencies
-        run: poetry install
-
-      - name: Build package
+        run: poetry install --sync --no-interaction
+      - name: Package project
         run: poetry build
 
-      - name: Publish to PyPI
-        env:
-          POETRY_PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
-        run: poetry publish --username __token__ --password ${{ secrets.PYPI_TOKEN }}
+      #----------------------------------------------
+      #               upload to PyPI
+      #----------------------------------------------
+      - name: Publish release distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/

.github/workflows/ruff.yml

@@ -0,0 +1,37 @@
+name: Ruff
+
+on:
+  - pull_request
+
+jobs:
+  Ruff:
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      fail-fast: true
+      matrix:
+        os: ["ubuntu-latest", "macos-latest"]
+        python-version: ["3.10", "3.11"]
+    runs-on: ${{ matrix.os }}
+    steps:
+      #----------------------------------------------
+      #       check-out repo and set-up python
+      #----------------------------------------------
+      - name: Check out repository
+        uses: actions/checkout@v4
+      - name: Set up python ${{ matrix.python-version }}
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      #----------------------------------------------
+      #            -----  run ruff   -----
+      #----------------------------------------------
+      - name: Lint and check format with ruff
+        uses: astral-sh/ruff-action@v3
+        with:
+          version-file: "pyproject.toml"
+      - run: ruff check --output-format=github
+      - run: ruff format --check

.gitignore

@@ -6,9 +6,6 @@ __pycache__/
 # Caching directories
 .mypy_cache/
 
-# Data directories
-/data
-
 # Jupyter Notebook checkpoints
 .ipynb_checkpoints/
 
@@ -34,9 +31,4 @@ Thumbs.db
 
 # Other files and folders that should be ignored
 *.bak
-*.tmp
-/models
-/models-MIMIC
-/notebooks/MIMIC_
-/notebooks/outdated
-/documentation/figures
+*.tmp

README.md

@@ -23,16 +23,16 @@ pip install synthius
 ### Step 2: Usage Example
 To understand how to use this package, explore the three example Jupyter notebooks included in the repository:
 
-1. **[Generator](example/1_generator.ipynb)**
+1. **[Generator](examples/1_generator.ipynb)**
    - Demonstrates how to generate synthetic data using seven different models.
    - Update paths and configurations (e.g., file paths, target column) to fit your dataset.
    - Run the cells to generate synthetic datasets.
 
-2. **[AutoGloun](example/2_autogloun.ipynb)**
+2. **[AutoGloun](examples/2_autogloun.ipynb)**
    - Evaluates the utility.
    - Update the paths as needed to analyze your data.
 
-3. **[Evaluation](example/3_evaluation.ipynb)**
+3. **[Evaluation](examples/3_evaluation.ipynb)**
    - Provides examples of computing metrics for evaluating synthetic data, including:
      - Utility
      - Fidelity/Similarity

example/1_generator.ipynb → examples/1_generator.ipynb

@@ -7,6 +7,7 @@
    "outputs": [],
    "source": [
     "import warnings\n",
+    "from pathlib import Path\n",
     "\n",
     "import pandas as pd\n",
     "from sdv.metadata import SingleTableMetadata\n",
@@ -17,8 +18,8 @@
     "warnings.filterwarnings(\"ignore\")\n",
     "\n",
     "\n",
-    "data_path = \"PATH_TO_ORIGINAL_DATA\"  # TODO: Change this to the path of the original data\n",
-    "synt_path = \"PATH_TO_SYNTHETIC_DATA_DIRECTORY\"  # TODO: Change this to the path of the synthetic data\n",
+    "data_path = Path(\"PATH_TO_ORIGINAL_DATA\")  # TODO: Change this to the path of the original data\n",
+    "synt_path = Path(\"PATH_TO_SYNTHETIC_DATA_DIRECTORY\")  # TODO: Change this to the path of the synthetic data directory\n",
     "\n",
     "\n",
     "data = pd.read_csv(data_path, low_memory=False)\n",
@@ -170,7 +171,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from synthetic_data.model import GaussianMultivariateSynthesizer\n",
+    "from synthius.model import GaussianMultivariateSynthesizer\n",
     "\n",
     "gaussian_multivariate_synthesizer = GaussianMultivariateSynthesizer(train_data, synt_path)\n",
     "gaussian_multivariate_synthesizer.synthesize(num_sample=total_samples)"
@@ -191,8 +192,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from synthetic_data.data import DataImputationPreprocessor\n",
-    "from synthetic_data.model import WGAN, data_batcher\n",
+    "from synthius.data import DataImputationPreprocessor\n",
+    "from synthius.model import WGAN, data_batcher\n",
     "\n",
     "data_preprocessor = DataImputationPreprocessor(train_data)\n",
     "processed_train_data = data_preprocessor.fit_transform()\n",
@@ -225,7 +226,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from synthetic_data.model import ARF\n",
+    "from synthius.model import ARF\n",
     "\n",
     "model = ARF(x=train_data, id_column=ID, min_node_size=5, num_trees=50, max_features=0.3)\n",
     "forde = model.forde()\n",

example/2_autogloun.ipynb → examples/2_autogloun.ipynb

@@ -6,7 +6,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from synthetic_data.model import ModelFitter, ModelLoader"
+    "from pathlib import Path\n",
+    "\n",
+    "from synthius.model import ModelFitter, ModelLoader"
    ]
   },
   {
@@ -15,10 +17,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "train_data = \"PATH_TO_TRAIN_DATASET_AS_CSV\"  # TODO: Change this to the path of the training dataset\n",
-    "test_data = \"PATH_TO_TEST_DATASET_AS_CSV\"  # TODO: Change this to the path of the test dataset\n",
-    "synt_path = \"PATH_TO_SYNTHETIC_DATA_DIRECTORY\"  # TODO: Change this to the path of the synthetic data directory\n",
-    "models_path = \"PATH_TO_MODELS_DIRECTORY\"  # TODO: Change this to the path of the models directory\n",
+    "train_data = Path(\"PATH_TO_TRAIN_DATASET_AS_CSV\")  # TODO: Change this to the path of the training dataset\n",
+    "test_data = Path(\"PATH_TO_TEST_DATASET_AS_CSV\")  # TODO: Change this to the path of the test dataset\n",
+    "synt_path = Path(\"PATH_TO_SYNTHETIC_DATA_DIRECTORY\")  # TODO: Change this to the path of the synthetic data directory\n",
+    "models_path = Path(\"PATH_TO_MODELS_DIRECTORY\")  # TODO: Change this to the path of the models directory\n",
     "\n",
     "synthetic_data_paths = [\n",
     "    synt_path / \"CopulaGAN.csv\",\n",