merged

Author: Julien Roussel

.github/workflows/test.yml

@@ -17,7 +17,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest]
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.11", "3.12"]
     defaults:
       run:
         shell: bash -l {0}
@@ -28,10 +28,10 @@ jobs:
         run: |
           if [[ "${GITHUB_REF}" == "refs/heads/main" || "${GITHUB_REF}" == "refs/heads/dev" ]]; then
             echo "os-matrix=ubuntu-latest,windows-latest" >> $GITHUB_ENV
-            echo "python-matrix=3.8,3.9,3.10,3.11" >> $GITHUB_ENV
+            echo "python-matrix=3.9,3.11,3.12" >> $GITHUB_ENV
           else
             echo "os-matrix=ubuntu-latest" >> $GITHUB_ENV
-            echo "python-matrix=3.11" >> $GITHUB_ENV
+            echo "python-matrix=3.12" >> $GITHUB_ENV
           fi
       - name: Checkout
         uses: actions/checkout@v3
@@ -62,35 +62,6 @@ jobs:
         uses: codecov/codecov-action@v3
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-
-  docs:
-    runs-on: ubuntu-latest
-    needs: check
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-      - name: Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-      - name: Cache Poetry
-        uses: actions/cache@v3
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
-          key: ${{ runner.os }}-poetry-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-${{ matrix.python-version }}-
-      - name: Poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: 1.8.3
-      - name: Lock
-        run: poetry lock --no-update
-      - name: Install
-        run: poetry install
       - name: Check Changed Files
         id: changed-files
         run: |

.python-version

@@ -0,0 +1 @@
+env_qolmat_3.9

docs/index.rst

@@ -22,14 +22,14 @@
 .. toctree::
    :maxdepth: 2
    :hidden:
-   :caption: API
+   :caption: ANALYSIS
 
-   api
+   analysis
+   examples/tutorials/plot_tuto_mcar
 
 .. toctree::
    :maxdepth: 2
    :hidden:
-   :caption: ANALYSIS
+   :caption: API
 
-   analysis
-   examples/tutorials/plot_tuto_mcar
+   api

examples/benchmark.md

@@ -311,7 +311,7 @@ from qolmat.imputations.imputers_pytorch import ImputerDiffusion
 from qolmat.imputations.diffusions.ddpms import TabDDPM
 
 X = np.array([[1, 1, 1, 1], [np.nan, np.nan, 3, 2], [1, 2, 2, 1], [2, 2, 2, 2]])
-imputer = ImputerDiffusion(model=TabDDPM(random_state=11), epochs=50, batch_size=1)
+imputer = ImputerDiffusion(epochs=50, batch_size=1, random_state=11)
 
 imputer.fit_transform(X)
 ```
@@ -322,7 +322,7 @@ from qolmat.imputations.imputers_pytorch import ImputerDiffusion
 from qolmat.imputations.diffusions.ddpms import TabDDPM
 
 X = np.array([[1, 1, 1, 1], [np.nan, np.nan, 3, 2], [1, 2, 2, 1], [2, 2, 2, 2]])
-imputer = ImputerDiffusion(model=TabDDPM(random_state=11), epochs=50, batch_size=1)
+imputer = ImputerDiffusion(epochs=50, batch_size=1, random_state=11)
 
 imputer.fit_transform(X)
 ```
@@ -358,7 +358,7 @@ encoder, decoder  = imputers_pytorch.build_autoencoder(input_dim=n_variables,lat
 ```python
 dict_imputers["MLP"] = imputer_mlp = imputers_pytorch.ImputerRegressorPyTorch(estimator=estimator, groups=('station',), epochs=500)
 dict_imputers["Autoencoder"] = imputer_autoencoder = imputers_pytorch.ImputerAutoencoder(encoder, decoder, max_iterations=100, epochs=100)
-dict_imputers["Diffusion"] = imputer_diffusion = imputers_pytorch.ImputerDiffusion(model=TabDDPM(num_sampling=5), epochs=100, batch_size=100)
+dict_imputers["Diffusion"] = imputer_diffusion = imputers_pytorch.ImputerDiffusion(epochs=100, batch_size=100, num_sampling=5)
 ```
 
 We can re-run the imputation model benchmark as before.

examples/tutorials/plot_tuto_diffusion_models.py

@@ -71,7 +71,6 @@
 df_data_valid = df_data.iloc[:500]
 
 tabddpm = ImputerDiffusion(
-    model=TabDDPM(),
     epochs=10,
     batch_size=100,
     x_valid=df_data_valid,
@@ -160,12 +159,8 @@
 # reconstruction errors (mae) but increases distribution distance (kl_columnwise).
 
 dict_imputers = {
-    "num_sampling=5": ImputerDiffusion(
-        model=TabDDPM(num_sampling=5), epochs=10, batch_size=100
-    ),
-    "num_sampling=10": ImputerDiffusion(
-        model=TabDDPM(num_sampling=10), epochs=10, batch_size=100
-    ),
+    "num_sampling=5": ImputerDiffusion(epochs=10, batch_size=100, num_sampling=5),
+    "num_sampling=10": ImputerDiffusion(epochs=10, batch_size=100, num_sampling=10),
 }
 
 comparison = comparator.Comparator(
@@ -187,7 +182,7 @@
 #
 # Two important hyperparameters for processing time-series data are ``index_datetime``
 # and ``freq_str``.
-# E.g., ``ImputerDiffusion(model=TabDDPM(), index_datetime='datetime', freq_str='1D')``,
+# E.g., ``ImputerDiffusion(index_datetime='datetime', freq_str='1D')``,
 #
 # * ``index_datetime``: the column name of datetime in index. It must be a pandas datetime object.
 #
@@ -210,15 +205,16 @@
 #   but requires a longer training/inference time.
 
 dict_imputers = {
-    "tabddpm": ImputerDiffusion(
-        model=TabDDPM(num_sampling=5), epochs=10, batch_size=100
+    "tabddpm": ImputerDiffusion(model="TabDDPM", epochs=10, batch_size=100, num_sampling=5
     ),
     "tsddpm": ImputerDiffusion(
-        model=TsDDPM(num_sampling=5, is_rolling=False),
+        model="TsDDPM",
         epochs=10,
         batch_size=5,
         index_datetime="date",
         freq_str="5D",
+        num_sampling=5,
+        is_rolling=False
     ),
 }
 

pyproject.toml

@@ -34,30 +34,32 @@ classifiers = [
 # DEPENDENCIES
 
 [tool.poetry.dependencies]
-python = ">=3.8.1,<3.12"
+python = ">=3.9,<3.13"
+hyperopt = "*"
+numpy = ">= 1.24"
+pandas = ">= 2.0.1"
+scipy = "*"
+scikit-learn = ">= 1.6"
+sphinx-markdown-tables = { version = "*", optional = true }
+statsmodels = ">= 0.14.0"
+typed-ast = { version = "*", optional = true }
+category-encoders = "^2.6.3"
+dcor = ">= 0.6"
+
+[tool.poetry.group.torch.dependencies]
+torch = "< 2.5"
+
+[tool.poetry.group.dev.dependencies]
 bump2version = "1.0.1"
+ipykernel = "^6.29.5"
 jupyter = "1.0.0"
 jupyterlab = "1.2.6"
 jupytext = "1.14.4"
-hyperopt = "0.2.7"
-numpy = "1.24.4"
+matplotlib = "*"
 packaging = "23.1"
-pandas = "2.0.1"
-scipy = "1.10.1"
-scikit-learn = "1.3.2"
-sphinx-markdown-tables = { version = "*", optional = true }
-statsmodels = "0.14.0"
-typed-ast = { version = "*", optional = true }
+pre-commit = "2.21.0"
 twine = "3.7.1"
 wheel = "0.37.1"
-category-encoders = "^2.6.3"
-ipykernel = "^6.29.5"
-torch = "*"
-dcor = "0.6"
-
-[tool.poetry.group.dev.dependencies]
-matplotlib = "3.6.2"
-pre-commit = "2.21.0"
 
 [tool.poetry.group.checkers.dependencies]
 bandit = "^1.7.9"
@@ -72,7 +74,7 @@ codecov = "^2.1.13"
 
 [tool.poetry.group.docs.dependencies]
 numpydoc = "1.1.0"
-sphinx = "4.3.2"
+sphinx = ">= 5.0"
 sphinx-gallery = "0.10.1"
 sphinx_rtd_theme = "1.0.0"
 sphinx_markdown_tables = "0.0.17"
@@ -141,7 +143,15 @@ docstring-code-format = true
 
 [tool.ruff.lint]
 select = ["C", "D", "E", "F", "I", "Q", "W"]
-ignore = ["C901", "D107", "D203", "D213"]
+ignore = [
+    "C901",
+    "D107",
+    "D203",
+    "D213",
+    "N803",  # allow X as a name for data
+    "N806",  # allow X as a name for data
+    "N816",  # allow mixed case names such as np_X_t as a name for data
+]
 
 [tool.ruff.lint.isort]
 known-first-party = ["qolmat"]