merged

Author: Julien Roussel

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.2
+current_version = 0.1.6
 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

.gitignore

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

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

@@ -2,12 +2,28 @@
 History
 =======
 
-??
+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)
 ------------------
 

README.rst

@@ -232,6 +232,8 @@ Selected Topics in Signal Processing 10.4 (2016): 740-756.
 [6] García, S., Luengo, J., & Herrera, F. "Data preprocessing in data mining". 2015.
 (`pdf <https://www.academia.edu/download/60477900/Garcia__Luengo__Herrera-Data_Preprocessing_in_Data_Mining_-_Springer_International_Publishing_201520190903-77973-th1o73.pdf>`__)
 
+[7] Botterman, HL., Roussel, J., Morzadec, T., Jabbari, A., Brunel, N. "Robust PCA for Anomaly Detection and Data Imputation in Seasonal Time Series" (2022) in International Conference on Machine Learning, Optimization, and Data Science. Cham: Springer Nature Switzerland, (`pdf <https://link.springer.com/chapter/10.1007/978-3-031-25891-6_21>`__)
+
 📝 License
 ==========
 

docs/api.rst

@@ -4,8 +4,8 @@ Qolmat API
 
 .. currentmodule:: qolmat
 
-Imputers
-=========
+Imputers API
+============
 
 .. autosummary::
     :toctree: generated/
@@ -15,10 +15,8 @@ Imputers
     imputations.imputers.ImputerKNN
     imputations.imputers.ImputerInterpolation
     imputations.imputers.ImputerLOCF
-    imputations.imputers.ImputerMedian
-    imputations.imputers.ImputerMean
+    imputations.imputers.ImputerSimple
     imputations.imputers.ImputerMICE
-    imputations.imputers.ImputerMode
     imputations.imputers.ImputerNOCB
     imputations.imputers.ImputerOracle
     imputations.imputers.ImputerRegressor
@@ -28,17 +26,17 @@ Imputers
     imputations.imputers.ImputerSoftImpute
     imputations.imputers.ImputerShuffle
 
-Comparator
-===========
+Comparator API
+==============
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
     benchmark.comparator.Comparator
 
-Missing Patterns
-================
+Missing Patterns API
+====================
 
 .. autosummary::
     :toctree: generated/
@@ -51,8 +49,8 @@ Missing Patterns
     benchmark.missing_patterns.GroupedHoleGenerator
 
 
-Metrics
-=======
+Metrics API
+===========
 
 .. autosummary::
     :toctree: generated/
@@ -63,6 +61,7 @@ Metrics
     benchmark.metrics.mean_absolute_error
     benchmark.metrics.mean_absolute_percentage_error
     benchmark.metrics.weighted_mean_absolute_percentage_error
+    benchmark.metrics.accuracy
     benchmark.metrics.dist_wasserstein
     benchmark.metrics.kl_divergence
     benchmark.metrics.kolmogorov_smirnov_test
@@ -75,19 +74,19 @@ Metrics
     benchmark.metrics.pattern_based_weighted_mean_metric
 
 
-RPCA engine
-================
+RPCA engine API
+===============
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
-    imputations.rpca.rpca_pcp.RPCAPCP
+    imputations.rpca.rpca_pcp.RpcaPcp
     imputations.rpca.rpca_noisy.RpcaNoisy
 
 
-EM engine
-================
+Expectation-Maximization engine API
+===================================
 
 .. autosummary::
     :toctree: generated/
@@ -96,8 +95,8 @@ EM engine
     imputations.em_sampler.MultiNormalEM
     imputations.em_sampler.VARpEM
 
-Diffusion engine
-================
+Diffusion Model engine API
+==========================
 
 .. autosummary::
     :toctree: generated/
@@ -107,9 +106,27 @@ Diffusion engine
     imputations.diffusions.ddpms.TabDDPM
     imputations.diffusions.ddpms.TsDDPM
 
+Preprocessing API
+=================
+
+.. autosummary::
+    :toctree: generated/
+    :template: class.rst
+    
+    imputations.preprocessing.MixteHGBM
+    imputations.preprocessing.BinTransformer
+    imputations.preprocessing.OneHotEncoderProjector
+    imputations.preprocessing.WrapperTransformer
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+    
+    imputations.preprocessing.make_pipeline_mixte_preprocessing
+    imputations.preprocessing.make_robust_MixteHGB
 
-Utils
-================
+Utils API
+=========
 
 .. autosummary::
     :toctree: generated/

docs/conf.py

@@ -27,7 +27,7 @@
 author = "Quantmetry"
 
 # The full version, including alpha/beta/rc tags
-version = "0.1.2"
+version = "0.1.6"
 release = version
 
 # -- General configuration ---------------------------------------------------