Version 0.16

فهرست فصل‌ها دانلود آرشیوناشر

scikit-learn Docs · نسخهٔ 5e9184e53cd3 · BSD-3-Clause

============

Version 0.16

Version 0.16.1

April 14, 2015

Changelog

Bug fixes .........

  • Allow input data larger than `block_size` in

covariance.LedoitWolf by Andreas Müller_.

  • Fix a bug in isotonic.IsotonicRegression deduplication that

caused unstable result in calibration.CalibratedClassifierCV by Jan Hendrik Metzen_.

  • Fix sorting of labels in preprocessing.label_binarize by Michael Heilman.
  • Fix several stability and convergence issues in

cross_decomposition.CCA and cross_decomposition.PLSCanonical by Andreas Müller_

  • Fix a bug in cluster.KMeans when `precompute_distances=False`

on fortran-ordered data.

  • Fix a speed regression in ensemble.RandomForestClassifier's `predict`

and `predict_proba by Andreas Müller`_.

  • Fix a regression where `utils.shuffle converted lists and dataframes to arrays, by Olivier Grisel`_

Version 0.16

March 26, 2015

Highlights

  • Speed improvements (notably in cluster.DBSCAN), reduced memory

requirements, bug-fixes and better default settings.

  • Multinomial Logistic regression and a path algorithm in

linear_model.LogisticRegressionCV.

  • Out-of core learning of PCA via decomposition.IncrementalPCA.
  • Probability calibration of classifiers using

calibration.CalibratedClassifierCV.

  • cluster.Birch clustering method for large-scale datasets.
  • Scalable approximate nearest neighbors search with Locality-sensitive

hashing forests in neighbors.LSHForest.

  • Improved error messages and better validation when using malformed input data.
  • More robust integration with pandas dataframes.

Changelog

New features ............

  • The new neighbors.LSHForest implements locality-sensitive hashing

for approximate nearest neighbors search. By Maheshakya Wijewardena<maheshakya>.

  • Added svm.LinearSVR. This class uses the liblinear implementation

of Support Vector Regression which is much faster for large sample sizes than svm.SVR with linear kernel. By Fabian Pedregosa_ and Qiang Luo.

  • Incremental fit for GaussianNB <naive_bayes.GaussianNB>.
  • Added `sample_weight support to dummy.DummyClassifier` and

dummy.DummyRegressor. By Arnaud Joly_.

  • Added the metrics.label_ranking_average_precision_score metrics.

By Arnaud Joly_.

  • Add the metrics.coverage_error metrics. By Arnaud Joly_.
  • Added linear_model.LogisticRegressionCV. By

Manoj Kumar_, Fabian Pedregosa_, Gael Varoquaux_ and Alexandre Gramfort_.

  • Added `warm_start` constructor parameter to make it possible for any

trained forest model to grow additional trees incrementally. By Laurent Direr<ldirer>.

  • Added `sample_weight support to ensemble.GradientBoostingClassifier` and

ensemble.GradientBoostingRegressor. By Peter Prettenhofer_.

  • Added decomposition.IncrementalPCA, an implementation of the PCA

algorithm that supports out-of-core learning with a `partial_fit method. By Kyle Kastner`_.

  • Averaged SGD for SGDClassifier <linear_model.SGDClassifier>

and SGDRegressor <linear_model.SGDRegressor> By Danny Sullivan <dsullivan7>.

  • Added cross_val_predict

function which computes cross-validated estimates. By Luis Pedro Coelho_

  • Added linear_model.TheilSenRegressor, a robust

generalized-median-based estimator. By Florian Wilhelm <FlorianWilhelm>.

  • Added metrics.median_absolute_error, a robust metric.

By Gael Varoquaux_ and Florian Wilhelm <FlorianWilhelm>.

  • Add cluster.Birch, an online clustering algorithm. By

Manoj Kumar_, Alexandre Gramfort_ and Joel Nothman_.

  • Added shrinkage support to discriminant_analysis.LinearDiscriminantAnalysis

using two new solvers. By Clemens Brunner <cle1109> and Martin Billinger_.

  • Added kernel_ridge.KernelRidge, an implementation of

kernelized ridge regression. By Mathieu Blondel_ and Jan Hendrik Metzen_.

  • All solvers in linear_model.Ridge now support sample_weight.

By Mathieu Blondel_.

  • Added cross_validation.PredefinedSplit cross-validation

for fixed user-provided cross-validation folds. By Thomas Unterthiner <untom>.

  • Added calibration.CalibratedClassifierCV, an approach for

calibrating the predicted probabilities of a classifier. By Alexandre Gramfort_, Jan Hendrik Metzen_, Mathieu Blondel_ and Balazs Kegl <kegl>.

Enhancements ............

  • Add option `return_distance in hierarchical.ward_tree`

to return distances between nodes for both structured and unstructured versions of the algorithm. By Matteo Visconti di Oleggio Castello_. The same option was added in hierarchical.linkage_tree. By Manoj Kumar_

  • Add support for sample weights in scorer objects. Metrics with sample

weight support will automatically benefit from it. By Noel Dawe_ and Vlad Niculae_.

  • Added `newton-cg and lbfgs` solver support in

linear_model.LogisticRegression. By Manoj Kumar_.

  • Add `selection="random"` parameter to implement stochastic coordinate

descent for linear_model.Lasso, linear_model.ElasticNet and related. By Manoj Kumar_.

  • Add `sample_weight` parameter to

metrics.jaccard_similarity_score and metrics.log_loss. By Jatin Shah <jatinshah>.

  • Support sparse multilabel indicator representation in

preprocessing.LabelBinarizer and multiclass.OneVsRestClassifier (by Hamzeh Alsalhi <hamsal> with thanks to Rohit Sivaprasad), as well as evaluation metrics (by Joel Nothman_).

  • Add `sample_weight parameter to metrics.jaccard_similarity_score`.

By Jatin Shah.

  • Add support for multiclass in metrics.hinge_loss. Added `labels=None`

as optional parameter. By Saurabh Jha.

  • Add `sample_weight parameter to metrics.hinge_loss`.

By Saurabh Jha.

  • Add `multi_class="multinomial"` option in

linear_model.LogisticRegression to implement a Logistic Regression solver that minimizes the cross-entropy or multinomial loss instead of the default One-vs-Rest setting. Supports lbfgs and newton-cg solvers. By Lars Buitinck_ and Manoj Kumar_. Solver option newton-cg by Simon Wu.

  • `DictVectorizer can now perform fit_transform` on an iterable in a

single pass, when giving the option `sort=False. By :user:Dan Blanchard <dan-blanchard>`.

  • model_selection.GridSearchCV and

model_selection.RandomizedSearchCV can now be configured to work with estimators that may fail and raise errors on individual folds. This option is controlled by the error_score parameter. This does not affect errors raised on re-fit. By Michal Romaniuk <romaniukm>.

  • Add `digits parameter to metrics.classification_report` to allow

report to show different precision of floating point numbers. By Ian Gilmore <agileminor>.

  • Add a quantile prediction strategy to the dummy.DummyRegressor.

By Aaron Staple <staple>.

  • Add `handle_unknown option to preprocessing.OneHotEncoder` to

handle unknown categorical features more gracefully during transform. By Manoj Kumar_.

  • Added support for sparse input data to decision trees and their ensembles.

By Fares Hedyati_ and Arnaud Joly_.

  • Optimized cluster.AffinityPropagation by reducing the number of

memory allocations of large temporary data-structures. By Antony Lee_.

  • Parallelization of the computation of feature importances in random forest.

By Olivier Grisel_ and Arnaud Joly_.

  • Add `n_iter_ attribute to estimators that accept a max_iter` attribute

in their constructor. By Manoj Kumar_.

  • Added decision function for multiclass.OneVsOneClassifier

By Raghav RV_ and Kyle Beauchamp <kyleabeauchamp>.

  • neighbors.kneighbors_graph and radius_neighbors_graph

support non-Euclidean metrics. By Manoj Kumar_

  • Parameter `connectivity in cluster.AgglomerativeClustering`

and family now accept callables that return a connectivity matrix. By Manoj Kumar_.

  • Sparse support for metrics.pairwise.paired_distances. By Joel Nothman_.
  • cluster.DBSCAN now supports sparse input and sample weights and

has been optimized: the inner loop has been rewritten in Cython and radius neighbors queries are now computed in batch. By Joel Nothman_ and Lars Buitinck_.

  • Add `class_weight` parameter to automatically weight samples by class

frequency for ensemble.RandomForestClassifier, tree.DecisionTreeClassifier, ensemble.ExtraTreesClassifier and tree.ExtraTreeClassifier. By Trevor Stephens_.

  • grid_search.RandomizedSearchCV now does sampling without

replacement if all parameters are given as lists. By Andreas Müller_.

  • Parallelized calculation of metrics.pairwise_distances is now supported

for scipy metrics and custom callables. By Joel Nothman_.

  • Allow the fitting and scoring of all clustering algorithms in

pipeline.Pipeline. By Andreas Müller_.

  • More robust seeding and improved error messages in cluster.MeanShift

by Andreas Müller_.

  • Make the stopping criterion for mixture.GMM,

mixture.DPGMM and mixture.VBGMM less dependent on the number of samples by thresholding the average log-likelihood change instead of its sum over all samples. By Hervé Bredin_.

  • The outcome of manifold.spectral_embedding was made deterministic

by flipping the sign of eigenvectors. By Hasil Sharma <Hasil-Sharma>.

  • Significant performance and memory usage improvements in

preprocessing.PolynomialFeatures. By Eric Martin_.

  • Numerical stability improvements for preprocessing.StandardScaler

and preprocessing.scale. By Nicolas Goix_

  • svm.SVC fitted on sparse input now implements `decision_function`.

By Rob Zinkov_ and Andreas Müller_.

  • cross_validation.train_test_split now preserves the input type,

instead of converting to numpy arrays.

Documentation improvements ..........................

  • Added example of using pipeline.FeatureUnion for heterogeneous input.

By Matt Terry <mrterry>

  • Documentation on scorers was improved, to highlight the handling of loss

functions. By Matt Pico <MattpSoftware>.

  • A discrepancy between liblinear output and scikit-learn's wrappers

is now noted. By Manoj Kumar_.

  • Improved documentation generation: examples referring to a class or

function are now shown in a gallery on the class/function's API reference page. By Joel Nothman_.

  • More explicit documentation of sample generators and of data

transformation. By Joel Nothman_.

  • sklearn.neighbors.BallTree and sklearn.neighbors.KDTree

used to point to empty pages stating that they are aliases of BinaryTree. This has been fixed to show the correct class docs. By Manoj Kumar_.

  • Added silhouette plots for analysis of KMeans clustering using

metrics.silhouette_samples and metrics.silhouette_score. See sphx_glr_auto_examples_cluster_plot_kmeans_silhouette_analysis.py

Bug fixes .........

  • Metaestimators now support ducktyping for the presence of `decision_function`,

`predict_proba and other methods. This fixes behavior of grid_search.GridSearchCV, grid_search.RandomizedSearchCV, pipeline.Pipeline, feature_selection.RFE, feature_selection.RFECV when nested. By Joel Nothman`_

  • The `scoring` attribute of grid-search and cross-validation methods is no longer

ignored when a grid_search.GridSearchCV is given as a base estimator or the base estimator doesn't have predict.

  • The function hierarchical.ward_tree now returns the children in

the same order for both the structured and unstructured versions. By Matteo Visconti di Oleggio Castello_.

  • feature_selection.RFECV now correctly handles cases when

`step is not equal to 1. By Nikolay Mayorov <nmayorov>`

  • The decomposition.PCA now undoes whitening in its

`inverse_transform. Also, its components_ now always have unit length. By Michael Eickenberg <eickenberg>`.

  • Fix incomplete download of the dataset when

datasets.download_20newsgroups is called. By Manoj Kumar_.

  • Various fixes to the Gaussian processes subpackage by Vincent Dubourg

and Jan Hendrik Metzen.

  • Calling `partial_fit with class_weight=='auto'` throws an

appropriate error message and suggests a workaround. By Danny Sullivan <dsullivan7>.

  • RBFSampler <kernel_approximation.RBFSampler> with `gamma=g`

formerly approximated rbf_kernel <metrics.pairwise.rbf_kernel> with `gamma=g/2.; the definition of gamma is now consistent, which may substantially change your results if you use a fixed value. (If you cross-validated over gamma, it probably doesn't matter too much.) By Dougal Sutherland <dougalsutherland>`.

  • Pipeline object delegates the `classes_` attribute to the underlying

estimator. It allows, for instance, to make bagging of a pipeline object. By Arnaud Joly_

  • neighbors.NearestCentroid now uses the median as the centroid

when metric is set to `manhattan. It was using the mean before. By Manoj Kumar`_

  • Fix numerical stability issues in linear_model.SGDClassifier

and linear_model.SGDRegressor by clipping large gradients and ensuring that weight decay rescaling is always positive (for large l2 regularization and large learning rate values). By Olivier Grisel_

  • When compute_full_tree is set to "auto", the full tree is

built when n_clusters is high and is early stopped when n_clusters is low, while the behavior should be vice versa in cluster.AgglomerativeClustering (and friends). This has been fixed By Manoj Kumar_

  • Fix lazy centering of data in linear_model.enet_path and

linear_model.lasso_path. It was centered around one. It has been changed to be centered around the origin. By Manoj Kumar_

  • Fix handling of precomputed affinity matrices in

cluster.AgglomerativeClustering when using connectivity constraints. By Cathy Deng <cathydeng>

  • Correct `partial_fit handling of class_prior` for

sklearn.naive_bayes.MultinomialNB and sklearn.naive_bayes.BernoulliNB. By Trevor Stephens_.

  • Fixed a crash in metrics.precision_recall_fscore_support

when using unsorted `labels in the multi-label setting. By Andreas Müller`_.

  • Avoid skipping the first nearest neighbor in the methods `radius_neighbors`,

`kneighbors, kneighbors_graph and radius_neighbors_graph in sklearn.neighbors.NearestNeighbors and family, when the query data is not the same as fit data. By Manoj Kumar`_.

  • Fix log-density calculation in the mixture.GMM with

tied covariance. By Will Dawson_

  • Fixed a scaling error in feature_selection.SelectFdr

where a factor `n_features was missing. By Andrew Tulloch`_

  • Fix zero division in neighbors.KNeighborsRegressor and related

classes when using distance weighting and having identical data points. By Garret-R <https://github.com/Garrett-R>_.

  • Fixed round off errors with non positive-definite covariance matrices

in GMM. By Alexis Mignon <AlexisMignon>.

  • Fixed an error in the computation of conditional probabilities in

naive_bayes.BernoulliNB. By Hanna Wallach_.

  • Make the method `radius_neighbors` of

neighbors.NearestNeighbors return the samples lying on the boundary for `algorithm='brute'. By Yan Yi`_.

  • Flip sign of `dual_coef_ of svm.SVC`

to make it consistent with the documentation and `decision_function`. By Artem Sobolev.

  • Fixed handling of ties in isotonic.IsotonicRegression.

We now use the weighted average of targets (secondary method). By Andreas Müller_ and Michael Bommarito <https://bommaritollc.com/>_.

API changes summary

  • GridSearchCV and

cross_val_score and other meta-estimators don't convert pandas DataFrames into arrays any more, allowing DataFrame specific operations in custom estimators.

  • multiclass.fit_ovr, multiclass.predict_ovr,

predict_proba_ovr, multiclass.fit_ovo, multiclass.predict_ovo, multiclass.fit_ecoc and multiclass.predict_ecoc are deprecated. Use the underlying estimators instead.

  • Nearest neighbors estimators used to take arbitrary keyword arguments

and pass these to their distance metric. This will no longer be supported in scikit-learn 0.18; use the `metric_params` argument instead.

  • n_jobs parameter of the fit method shifted to the constructor of the

LinearRegression class.

  • The `predict_proba method of multiclass.OneVsRestClassifier`

now returns two probabilities per sample in the multiclass case; this is consistent with other estimators and with the method's documentation, but previous versions accidentally returned only the positive probability. Fixed by Will Lamond and Lars Buitinck_.

  • Change default value of precompute in linear_model.ElasticNet and

linear_model.Lasso to False. Setting precompute to "auto" was found to be slower when n_samples > n_features since the computation of the Gram matrix is computationally expensive and outweighs the benefit of fitting the Gram for just one alpha. `precompute="auto" is now deprecated and will be removed in 0.18 By Manoj Kumar`_.

  • Expose `positive option in linear_model.enet_path` and

linear_model.enet_path which constrains coefficients to be positive. By Manoj Kumar_.

  • Users should now supply an explicit `average` parameter to

sklearn.metrics.f1_score, sklearn.metrics.fbeta_score, sklearn.metrics.recall_score and sklearn.metrics.precision_score when performing multiclass or multilabel (i.e. not binary) classification. By Joel Nothman_.

  • scoring parameter for cross validation now accepts 'f1_micro',

'f1_macro' or 'f1_weighted'. 'f1' is now for binary classification only. Similar changes apply to 'precision' and 'recall'. By Joel Nothman_.

  • The `fit_intercept, normalize and return_models` parameters in

linear_model.enet_path and linear_model.lasso_path have been removed. They were deprecated since 0.14

  • From now onwards, all estimators will uniformly raise `NotFittedError`

when any of the `predict like methods are called before the model is fit. By Raghav RV`_.

  • Input data validation was refactored for more consistent input

validation. The `check_arrays function was replaced by check_array and check_X_y. By Andreas Müller`_.

  • Allow `X=None in the methods radius_neighbors, kneighbors`,

`kneighbors_graph and radius_neighbors_graph in sklearn.neighbors.NearestNeighbors and family. If set to None, then for every sample this avoids setting the sample itself as the first nearest neighbor. By Manoj Kumar`_.

  • Add parameter `include_self in neighbors.kneighbors_graph`

and neighbors.radius_neighbors_graph which has to be explicitly set by the user. If set to True, then the sample itself is considered as the first nearest neighbor.

  • thresh parameter is deprecated in favor of new tol parameter in

GMM, DPGMM and VBGMM. See Enhancements section for details. By Hervé Bredin_.

  • Estimators will treat input with dtype object as numeric when possible.

By Andreas Müller_

  • Estimators now raise ValueError consistently when fitted on empty

data (less than 1 sample or less than 1 feature for 2D input). By Olivier Grisel_.

  • The `shuffle option of .linear_model.SGDClassifier`,

linear_model.SGDRegressor, linear_model.Perceptron, linear_model.PassiveAggressiveClassifier and linear_model.PassiveAggressiveRegressor now defaults to `True`.

  • cluster.DBSCAN now uses a deterministic initialization. The

random_state parameter is deprecated. By Erich Schubert <kno10>.

Code Contributors

A. Flaxman, Aaron Schumacher, Aaron Staple, abhishek thakur, Akshay, akshayah3, Aldrian Obaja, Alexander Fabisch, Alexandre Gramfort, Alexis Mignon, Anders Aagaard, Andreas Mueller, Andreas van Cranenburgh, Andrew Tulloch, Andrew Walker, Antony Lee, Arnaud Joly, banilo, Barmaley.exe, Ben Davies, Benedikt Koehler, bhsu, Boris Feld, Borja Ayerdi, Boyuan Deng, Brent Pedersen, Brian Wignall, Brooke Osborn, Calvin Giles, Cathy Deng, Celeo, cgohlke, chebee7i, Christian Stade-Schuldt, Christof Angermueller, Chyi-Kwei Yau, CJ Carey, Clemens Brunner, Daiki Aminaka, Dan Blanchard, danfrankj, Danny Sullivan, David Fletcher, Dmitrijs Milajevs, Dougal J. Sutherland, Erich Schubert, Fabian Pedregosa, Florian Wilhelm, floydsoft, Félix-Antoine Fortin, Gael Varoquaux, Garrett-R, Gilles Louppe, gpassino, gwulfs, Hampus Bengtsson, Hamzeh Alsalhi, Hanna Wallach, Harry Mavroforakis, Hasil Sharma, Helder, Herve Bredin, Hsiang-Fu Yu, Hugues SALAMIN, Ian Gilmore, Ilambharathi Kanniah, Imran Haque, isms, Jake VanderPlas, Jan Dlabal, Jan Hendrik Metzen, Jatin Shah, Javier López Peña, jdcaballero, Jean Kossaifi, Jeff Hammerbacher, Joel Nothman, Jonathan Helmus, Joseph, Kaicheng Zhang, Kevin Markham, Kyle Beauchamp, Kyle Kastner, Lagacherie Matthieu, Lars Buitinck, Laurent Direr, leepei, Loic Esteve, Luis Pedro Coelho, Lukas Michelbacher, maheshakya, Manoj Kumar, Manuel, Mario Michael Krell, Martin, Martin Billinger, Martin Ku, Mateusz Susik, Mathieu Blondel, Matt Pico, Matt Terry, Matteo Visconti dOC, Matti Lyra, Max Linke, Mehdi Cherti, Michael Bommarito, Michael Eickenberg, Michal Romaniuk, MLG, mr.Shu, Nelle Varoquaux, Nicola Montecchio, Nicolas, Nikolay Mayorov, Noel Dawe, Okal Billy, Olivier Grisel, Óscar Nájera, Paolo Puggioni, Peter Prettenhofer, Pratap Vardhan, pvnguyen, queqichao, Rafael Carrascosa, Raghav R V, Rahiel Kasim, Randall Mason, Rob Zinkov, Robert Bradshaw, Saket Choudhary, Sam Nicholls, Samuel Charron, Saurabh Jha, sethdandridge, sinhrks, snuderl, Stefan Otte, Stefan van der Walt, Steve Tjoa, swu, Sylvain Zimmer, tejesh95, terrycojones, Thomas Delteil, Thomas Unterthiner, Tomas Kazmar, trevorstephens, tttthomasssss, Tzu-Ming Kuo, ugurcaliskan, ugurthemaster, Vinayak Mehta, Vincent Dubourg, Vjacheslav Murashkin, Vlad Niculae, wadawson, Wei Xue, Will Lamond, Wu Jiang, x0l, Xinfan Meng, Yan Yi, Yu-Chin