History

current - 2019-07-11 - 0.00Mb

  • issue61: Fix bug in pipeline2dot when keyword “passthrough is used” (2019-07-11)

  • issue60: Fix visualisation of pipeline which contains string “passthrough” (2019-07-09)

  • issue58: Explores a way to compute recommandations without training (2019-06-05)

0.2.288 - 2019-05-28 - 0.66Mb

  • issue56: Fixes #55, explore caching for scikit-learn pipeline (2019-05-22)

  • issue55: Explore caching for gridsearchCV (2019-05-22)

  • issue53: implements a function to extract intermediate model outputs within a pipeline (2019-05-07)

  • issue51: Implements a tfidfvectorizer which keeps more information about n-grams (2019-04-26)

  • issue46: implements a way to determine close leaves in a decision tree (2019-04-01)

  • issue44: implements a model which produces confidence intervals based on bootstrapping (2019-03-29)

  • issue40: implements a custom criterion for a decision tree optimizing for a linear regression (2019-03-28)

  • issue39: implements a custom criterion for decision tree (2019-03-26)

  • issue41: implements a direct call to a lapack function from cython (2019-03-25)

  • issue38: better implementation of a regression criterion (2019-03-25)

0.1.199 - 2019-03-05 - 0.05Mb

  • issue37: implements interaction_only for polynomial features (2019-02-26)

  • issue36: add parameter include_bias to extended features (2019-02-25)

  • issue34: rename PiecewiseLinearRegression into PiecewiseRegression (2019-02-23)

  • issue33: implement the piecewise classifier (2019-02-23)

  • issue31: uses joblib for piecewise linear regression (2019-02-23)

  • issue30: explore transpose matrix before computing the polynomial features (2019-02-17)

  • issue29: explore different implementation of polynomialfeatures (2019-02-15)

  • issue28: implement PiecewiseLinearRegression (2019-02-10)

  • issue27: implement TransferTransformer (2019-02-04)

  • issue26: add function to convert a scikit-learn pipeline into a graph (2019-02-01)

  • issue25: implements kind of trainable t-SNE (2019-01-31)

  • issue6: use keras and pytorch (2019-01-03)

  • issue22: modifies plot gallery to impose coordinates (2018-11-10)

  • issue20: implements a QuantileMLPRegressor (quantile regression with MLP) (2018-10-22)

  • issue19: fix issues introduced with changes in keras 2.2.4 (2018-10-06)

  • issue18: remove warning from scikit-learn about cloning (2018-09-16)

  • issue16: move CI to python 3.7 (2018-08-21)

  • issue17: replace as_matrix by values (pandas deprecated warning) (2018-07-29)

  • issue14: add transform to convert a learner into a transform (sometimes called a featurizer) (2018-06-19)

  • issue13: add transform to do model stacking (2018-06-19)

  • issue8: move items from papierstat (2018-06-19)

  • issue12: fix bug in quantile regression: wrong weight for linear regression (2018-06-16)

  • issue11: specifying quantile (2018-06-16)

  • issue4: add function to compute non linear correlations (2018-06-16)

  • issue10: implements combination between logistic regression and k-means (2018-05-27)

  • issue9: move items from ensae_teaching_cs (2018-05-08)

  • issue7: add quantile regression (2018-05-07)

  • issue5: replace flake8 by code style (2018-04-14)

  • issue1: change background for cells in notebooks converted into rst then in html, highlight-ipython3 (2018-01-05)

  • issue2: save features and metadatas for the search engine and retrieves them (2017-12-03)