Skip to content

Latest commit

 

History

History
110 lines (82 loc) · 3.9 KB

v1.2.rst

File metadata and controls

110 lines (82 loc) · 3.9 KB
Raw

sklearn

Version 1.2.0

In Development

Changed models

The following estimators and functions, when fit with the same data and parameters, may produce different models from the previous version. This often occurs due to changes in the modelling logic (bug fixes or enhancements), or in random sampling procedures.

Changelog

sklearn.cluster

  • The predict and fit_predict methods of cluster.OPTICS now accept sparse data type for input data. 14736 by Hunt Zhan <huntzhan>, 20802 by Brandon Pokorny <Clickedbigfoot>, and 22965 by Meekail Zain <micky774>.
  • cluster.Birch now preserves dtype for numpy.float32 inputs. 22968 by Meekail Zain <micky774>.

sklearn.datasets

  • Introduce the new parameter parser in datasets.fetch_openml. parser="pandas" allows to use the very CPU and memory efficient pandas.read_csv parser to load dense ARFF formatted dataset files. It is possible to pass parser="liac-arff" to use the old LIAC parser. When parser="auto", dense datasets are loaded with "pandas" and sparse datasets are loaded with "liac-arff". Currently, parser="liac-arff" by default and will change to parser="auto" in version 1.4 21938 by Guillaume Lemaitre <glemaitre>.

sklearn.ensemble

  • Improve runtime performance of ensemble.IsolationForest by avoiding data copies. 23252 by Zhehao Liu <MaxwellLZH>.

sklearn.metrics

  • class_likelihood_ratios is added to compute the positive and negative likelihood ratios derived from the confusion matrix of a binary classification problem. 22518 by Arturo Amor <ArturoAmorQ>.

sklearn.neighbors

  • neighbors.KernelDensity bandwidth parameter now accepts definition using Scott's and Silvermann's estimation methods. 10468 by Ruben <icfly2> and 22993 by Jovan Stojanovic <jovan-stojanovic>.
  • Adds new function neighbors.sort_graph_by_row_values to sort a CSR sparse graph such that each row is stored with increasing values. This is useful to improve efficiency when using precomputed sparse distance matrices in a variety of estimators and avoid an EfficiencyWarning. 23139 by Tom Dupre la Tour.

sklearn.tree

  • Fixed invalid memory access bug during fit in tree.DecisionTreeRegressor and tree.DecisionTreeClassifier. 23273 by Thomas Fan.

sklearn.utils

  • utils.extmath.randomized_svd now accepts an argument, lapack_svd_driver, to specify the lapack driver used in the internal deterministic SVD used by the randomized SVD algorithm. 20617 by Srinath Kailasa <skailasa>

Code and Documentation Contributors

Thanks to everyone who has contributed to the maintenance and improvement of the project since version 1.1, including:

TODO: update at the time of the release.