Merge branch 'dev' into chp_add_rand_state_ddpm

Author: Julien Roussel

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.0.15
+current_version = 0.1.7
 commit = True
 tag = True
 

.coveragerc

@@ -0,0 +1,2 @@
+[run]
+omit = qolmat/_version.py

.flake8

@@ -1,5 +1,5 @@
 [flake8]
-exclude = .git,__pycache__,.vscode,tests
+exclude = .git,__pycache__,.vscode
 max-line-length=99
 ignore=E302,E305,W503,E203,E731,E402,E266,E712,F401,F821
 indent-size = 4

.github/workflows/publish.yml

@@ -11,9 +11,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v4
       with:
         python-version: '3.10'
     - name: Install dependencies

.github/workflows/test.yml

@@ -1,4 +1,4 @@
-name: Unit test on many environments
+name: Unit tests
 
 on:
   push:
@@ -31,11 +31,9 @@ jobs:
           environment-file: environment.ci.yml
       - name: Lint with flake8
         run: |
-          conda install flake8
           flake8
       - name: Test with pytest
         run: |
-          conda install pytest
           make coverage
       - name: typing with mypy
         run: |

.github/workflows/test_quick.yml

@@ -1,4 +1,4 @@
-name: Unit test Qolmat
+name: Unit tests fast
 
 on:
   push:
@@ -21,19 +21,44 @@ jobs:
     steps:
       - name: Git clone
         uses: actions/checkout@v3
-      - name: Set up venv for ci
+
+      # See caching environments
+      # https://github.com/conda-incubator/setup-miniconda#caching-environments
+      - name: Setup Mambaforge
         uses: conda-incubator/setup-miniconda@v2
         with:
-          python-version: ${{matrix.python-version}}
-          environment-file: environment.ci.yml
+            miniforge-variant: Mambaforge
+            miniforge-version: latest
+            activate-environment: env_qolmat_ci
+            use-mamba: true
+
+      - name: Get Date
+        id: get-date
+        run: echo "today=$(/bin/date -u '+%Y%m%d')" >> $GITHUB_OUTPUT
+
+      - name: Cache Conda env
+        uses: actions/cache@v2
+        with:
+          path: ${{ env.CONDA }}/envs
+          key:
+            conda-${{ runner.os }}--${{ runner.arch }}--${{
+            steps.get-date.outputs.today }}-${{
+            hashFiles('environment.ci.yml') }}-${{ env.CACHE_NUMBER
+            }}
+        env:
+          # Increase this value to reset cache if environment.ci.yml has not changed
+          CACHE_NUMBER: 0
+        id: cache
+
+      - name: Update environment
+        run: mamba env update -n env_qolmat_ci -f environment.ci.yml
+        if: steps.cache.outputs.cache-hit != 'true'
+
       - name: Lint with flake8
         run: |
-          conda install flake8
           flake8
       - name: Test with pytest
         run: |
-          conda install pytest
-          pip install -e .[pytorch]
           make coverage
       - name: Test docstrings
         run: make doctest

.gitignore

@@ -59,7 +59,7 @@ examples/*.ipynb
 examples/figures/*
 examples/data/*
 examples/local
-
+data/data_local/*
 
 # VSCode
 .vscode

.readthedocs.yml

@@ -9,6 +9,8 @@ python:
   install:
     - method: pip
       path: .
+      extra_requirements:
+        - pytorch
 
 conda:
   environment: environment.doc.yml

AUTHORS.rst

@@ -5,10 +5,10 @@ Credits
 Development Team
 ----------------
 
-* Julien Roussel <jroussel@quantmetry.com>
-* Anh Khoa Ngo Ho <angoho@quantmetry.com>
-* Charles-Henri Prat <chprat@quantmetry.com>
-* Guillaume Saës <gsaes@quantmetry.com>
+* Julien Roussel <julien.a.roussel@capgemini.com>
+* Anh Khoa Ngo Ho <anh-khoa.ngo-ho@capgemini.com>
+* Guillaume Saës <guillaume.saes@capgemini.com>
+* Yasser Zidani <yasser.zidani@capgemini.com>
 
 Past Contributors
 -----------------
@@ -19,3 +19,4 @@ Past Contributors
 * Mikaïl Duran
 * Rima Hajou
 * Thomas Morzadec
+* Charles-Henri Prat

HISTORY.rst

@@ -2,10 +2,55 @@
 History
 =======
 
-0.1.1 (2023-??-??)
+0.1.7 (2024-06-13)
+------------------
+* Little's test implemented in a new hole_characterization module
+* Documentation now includes an analysis section with a tutorial
+* Hole generators now provide reproducible outputs
+
+0.1.5 (2024-04-17)
+------------------
+
+* CICD now relies on Node.js 20
+* New tests for comparator.py and data.py
+
+0.1.4 (2024-04-15)
+------------------
+
+* ImputerMean, ImputerMedian and ImputerMode have been merged into ImputerSimple
+* File preprocessing.py added with classes new MixteHGBM, BinTransformer, OneHotEncoderProjector and WrapperTransformer providing tools to manage mixed types data
+* Tutorial plot_tuto_categorical showcasing mixed type imputation
+* Titanic dataset added
+* accuracy metric implemented
+* metrics.py rationalized, and split with algebra.py
+
+0.1.3 (2024-03-07)
+------------------
+
+* RPCA algorithms now start with a normalizing scaler
+* The EM algorithms now include a gradient projection step to be more robust to colinearity
+* The EM algorithm based on the Gaussian model is now initialized using a robust estimation of the covariance matrix
+* A bug in the EM algorithm has been patched: the normalizing matrix gamma was creating a sampling biais
+* Speed up of the EM algorithm likelihood maximization, using the conjugate gradient method
+* The ImputeRegressor class now handles the nans by `row` by default
+* The metric `frechet` was not correctly called and has been patched
+* The EM algorithm with VAR(p) now fills initial holes in order to avoid exponential explosions
+
+0.1.2 (2024-02-28)
+------------------
+
+* RPCA Noisy now has separate fit and transform methods, allowing to impute efficiently new data without retraining
+* The class ImputerRPCA has been splitted between a class ImputerRpcaNoisy, which can fit then transform, and a class ImputerRpcaPcp which can only fit_transform
+* The class SoftImpute has been recoded to better fit the architecture, and is more tested
+* The class RPCANoisy now relies on sparse matrices for H, speeding it up for large instances
+
+0.1.1 (2023-11-03)
 -------------------
 
 * Hotfix reference to tensorflow in the documentation, when it should be pytorch
+* Metrics KL forest has been removed from package
+* EM imputer made more robust to colinearity, and transform bug patched
+* CICD made faster with mamba and a quick test setting
 
 0.1.0 (2023-10-11)
 -------------------