Skip to content

Commit

Permalink
urls
Browse files Browse the repository at this point in the history
  • Loading branch information
xadupre committed Oct 7, 2024
1 parent 24bf841 commit 89f17cb
Show file tree
Hide file tree
Showing 25 changed files with 5,772 additions and 3,683 deletions.
7 changes: 7 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@
*.pyc
*.pyd
*.so
*.gv
*.gv.*
.coverage
.eggs/*
_cache/*
Expand Down Expand Up @@ -31,3 +33,8 @@ _unittests/ut__main/*.html
_unittests/.hypothesis/*
_doc/notebooks/ml/*.onnx
_doc/notebooks/dsgarden/*.onnx
_doc/notebooks/nlp/frwiki-*
_doc/notebooks/nlp/sample*.txt
frwiki-*
mobilenetv2-12.onnx
sample1000.txt
3 changes: 2 additions & 1 deletion _doc/c_clus/kohonen.rst
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,8 @@ Autres utilisation des cartes de Kohenen
On peut les utiliser pour déterminer le plus court
chemin passant par tous les noeuds d'un graphe,
c'est à dire appliquer
`Kohonen au problème du voyageur de commerce <http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/specials/tsp_kohonen.html>`_.
`Kohonen au problème du voyageur de commerce
<https://sdpython.github.io/doc/teachpyx/dev/c_expose/tsp/tsp_kohonen.html>`_.

Bibliographie
=============
Expand Down
3 changes: 1 addition & 2 deletions _doc/c_metric/roc.rst
Original file line number Diff line number Diff line change
Expand Up @@ -614,8 +614,7 @@ Le premier cas correspond par exemple à des problèmes de
`détection de fraude <https://en.wikipedia.org/wiki/Predictive_analytics#Fraud_detection>`_.
Le second cas correspond à taux de classification global. La courbe ROC
pour ce cas est en règle général moins bonne que la plupart des
courbes ROC obtenues pour chacune des classes prise séparément
(voir `Régression logistique <http://www.xavierdupre.fr/app/papierstat/helpsphinx/notebooks/wines_color.html>`_).
courbes ROC obtenues pour chacune des classes prise séparément.

Exemple
=======
Expand Down
2 changes: 1 addition & 1 deletion _doc/c_ml/index_reg_log.rst
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ construire une fonction prédictive
:math:`\hat{y_i} = f(X_i) = <X_i, \beta> = X_i \beta` où
:math:`\beta` est un vecteur de dimension *d*
(voir `classification
<http://www.xavierdupre.fr/app/papierstat/helpsphinx/lectures/regclass.html#classification>`_).
<https://sdpython.github.io/doc/teachpyx/dev/c_ml/regclass.html>`_).
Le signe de la fonction :math:`f(X_i)`
indique la classe de l'observation :math:`X_i` et la valeur
:math:`\frac{1}{1 + e^{f(X)}}` la probabilité d'être dans la classe 1.
Expand Down
2 changes: 1 addition & 1 deletion _doc/c_ml/l1l2.rst
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ Plus on ajoute de variables, plus l'erreur diminue.
Pour aller plus loin, voir [Char]_ et voir
son application à la séelection d'arbres dans une forêt aléatoire
`Réduction d’une forêt aléatoire
<http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/notebooks/td2a_tree_selection_correction.html>`_.
<https://github.com/sdpython/ensae_teaching_cs/blob/master/_doc/notebooks/td2a_ml/td2a_tree_selection_correction.ipynb>`_.

Bibliographie
=============
Expand Down
2 changes: 1 addition & 1 deletion _doc/c_ml/piecewise.rst
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ Problème et regréssion linéaire dans un espace à une dimension

Tout d'abord, une petite
illustration du problème avec la classe `PiecewiseRegression
<http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/piecewise_linear_regression.html>`_
<https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_piecewise_linear_regression.html>`_
implémentée selon l'API de :epkg:`scikit-learn`.

.. toctree::
Expand Down
2 changes: 1 addition & 1 deletion _doc/c_ml/regression_quantile.rst
Original file line number Diff line number Diff line change
Expand Up @@ -298,7 +298,7 @@ Bilbiographie

Des références sont disponibles sur la page de :epkg:`statsmodels` :
`QuantReg <http://www.statsmodels.org/stable/generated/statsmodels.regression.quantile_regression.QuantReg.html>`_ ou
là : `Régression quantile <http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/quantile_regression.html>`_.
là : `Régression quantile <https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_quantile_regression.html>`_.

.. [Koenker2017] `Quantile Regression, 40 years on <http://www.econ.uiuc.edu/~roger/courses/NIPE/handouts/QR40.pdf>`_,
Roger Koenker (2017)
Expand Down
4 changes: 2 additions & 2 deletions _doc/c_ml/survival_analysis.rst
Original file line number Diff line number Diff line change
Expand Up @@ -63,9 +63,9 @@ des dates à intervalles plutôt réguliers et croissants. La suite :math:`(n_i)
est décroissantes (on ne rescuscite pas).
Ces calculs rappellent les calculs liés à l'espérance de vie
(voir `Evoluation d’une population - énoncé
<http://www.xavierdupre.fr/app/actuariat_python/helpsphinx/notebooks/seance4_projection_population_enonce.html>`_,
<https://github.com/sdpython/actuariat_python/blob/master/_doc/notebooks/sessions/seance4_projection_population_enonce.ipynb>`_,
`Evoluation d'une population (correction)
<http://www.xavierdupre.fr/app/actuariat_python/helpsphinx/notebooks/seance4_projection_population_correction.html>`_).
<https://github.com/sdpython/actuariat_python/blob/master/_doc/notebooks/sessions/seance4_projection_population_correction.ipynb>`_).
L'espérance de vie est définie par :

.. math::
Expand Down
2 changes: 1 addition & 1 deletion _doc/c_nlp/completion_implementation.rst
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ Notion de trie
++++++++++++++

Une implémentation des tries est décrite dans ce notebook :
`Arbre et Trie <http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/notebooks/td1a_cenonce_session8.html>`_.
`Arbre et Trie <https://sdpython.github.io/doc/teachpyx/dev/practice/tds-base/trie.html>`_.
Les résultats de ce chapitre ont été produits avec le module :mod:`completion <mlstatpy.nlp.completion>`
et le notebook :ref:`/notebooks/nlp/completion_trie.ipynb`. Le notebook
:ref:`/notebooks/nlp/completion_profiling.ipynb` montre les résultats du profiling.
Expand Down
19 changes: 9 additions & 10 deletions _doc/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -167,37 +167,36 @@
epkg_dictionary = {
"ACP": "https://fr.wikipedia.org/wiki/Analyse_en_composantes_principales",
"AESA": "https://tavianator.com/aesa/",
"ApproximateNMFPredictor": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/mlinsights/mlmodel/anmf_predictor.html",
"ApproximateNMFPredictor": "https://sdpython.github.io/doc/mlinsights/dev/api/mlmodel.html",
"AUC": "https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve",
"B+ tree": "https://en.wikipedia.org/wiki/B%2B_tree",
"BLAS": "https://www.netlib.org/blas/",
"Branch and Bound": "https://en.wikipedia.org/wiki/Branch_and_bound",
"C++": "https://fr.wikipedia.org/wiki/C%2B%2B",
"Custom Criterion for DecisionTreeRegressor": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/piecewise_linear_regression_criterion.html",
"Custom Criterion for DecisionTreeRegressor": "https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_piecewise_linear_regression_criterion.html",
"cython": "https://cython.org/",
"DecisionTreeClassifier": "https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html",
"DecisionTreeRegressor optimized for Linear Regression": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/piecewise_linear_regression_criterion.html",
"DecisionTreeRegressor optimized for Linear Regression": "https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_piecewise_linear_regression_criterion.html",
"dot": "https://fr.wikipedia.org/wiki/DOT_(langage)",
"Holm-Bonferroni method": "https://en.wikipedia.org/wiki/Holm%E2%80%93Bonferroni_method",
"ICML 2016": "https://icml.cc/2016/index.html",
"KMeans": "https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html",
"LAESA": "https://tavianator.com/aesa/",
"LAPACK": "http://www.netlib.org/lapack/",
"mlinsights": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/index.html",
"mlinsights": "https://sdpython.github.io/doc/mlinsights/dev/index.html",
"mlstatpy": "https://sdpython.github.io/doc/mlstatpy/dev/",
"numpy": (
"https://www.numpy.org/",
("https://docs.scipy.org/doc/numpy/reference/generated/numpy.{0}.html", 1),
("https://docs.scipy.org/doc/numpy/reference/generated/numpy.{0}.{1}.html", 2),
),
"PiecewiseTreeRegressor": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/mlinsights/mlmodel/"
"piecewise_tree_regression.html#mlinsights.mlmodel.piecewise_tree_regression.PiecewiseTreeRegressor",
"PiecewiseTreeRegressor": "https://sdpython.github.io/doc/mlinsights/dev/api/mlmodel_tree.html#piecewisetreeregressor",
"Pillow": "https://pillow.readthedocs.io/en/stable/",
"Predictable t-SNE": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/predictable_tsne.html",
"QuantileLinearRegression": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/mlinsights/mlmodel/quantile_regression.html#mlinsights.mlmodel.quantile_regression.QuantileLinearRegression",
"Predictable t-SNE": "https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_predictable_tsne.html",
"QuantileLinearRegression": "https://sdpython.github.io/doc/mlinsights/dev/api/mlmodel.html#quantilelinearregression",
"R-tree": "https://en.wikipedia.org/wiki/R-tree",
"R* tree": "https://en.wikipedia.org/wiki/R*_tree",
"Regression with confidence interval": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/regression_confidence_interval.html",
"Regression with confidence interval": "https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_regression_confidence_interval.html",
"relu": "https://en.wikipedia.org/wiki/Rectifier_(neural_networks)",
"ROC": "https://fr.wikipedia.org/wiki/Courbe_ROC",
"scikit-learn": "https://scikit-learn.org/stable/index.html",
Expand All @@ -206,7 +205,7 @@
"statsmodels": "http://www.statsmodels.org/stable/index.html",
"SVD": "https://fr.wikipedia.org/wiki/D%C3%A9composition_en_valeurs_singuli%C3%A8res",
"tqdm": "https://tqdm.github.io/",
"Visualize a scikit-learn pipeline": "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/notebooks/visualize_pipeline.html",
"Visualize a scikit-learn pipeline": "https://sdpython.github.io/doc/mlinsights/dev/auto_examples/plot_visualize_pipeline.html",
"X-tree": "https://en.wikipedia.org/wiki/X-tree",
"wikipedia dumps": "https://dumps.wikimedia.org/frwiki/latest/",
}
Expand Down
866 changes: 425 additions & 441 deletions _doc/notebooks/dsgarden/correlation_non_lineaire.ipynb

Large diffs are not rendered by default.

Loading

0 comments on commit 89f17cb

Please sign in to comment.