Version 0.18
scikit-learn Docs · نسخهٔ 5e9184e53cd3 · BSD-3-Clause
============
Version 0.18
Scikit-learn 0.18 is the last major release of scikit-learn to support Python 2.6. Later versions of scikit-learn will require Python 2.7 or above.
Version 0.18.2
June 20, 2017
Changelog
- Fixes for compatibility with NumPy 1.13.0:
79468355by
Loic Esteve_.
- Minor compatibility changes in the examples
90108040
9149.
Code Contributors
Aman Dalmia, Loic Esteve, Nate Guerin, Sergei Lebedev
Version 0.18.1
November 11, 2016
Changelog
Enhancements ............
- Improved `
sample_without_replacement` speed by utilizing
numpy.random.permutation for most cases. As a result, samples may differ in this release for a fixed random state. Affected estimators:
ensemble.BaggingClassifierensemble.BaggingRegressorlinear_model.RANSACRegressormodel_selection.RandomizedSearchCVrandom_projection.SparseRandomProjection
This also affects the datasets.make_classification method.
Bug fixes .........
- Fix issue where `
min_grad_normandn_iter_without_progress`
parameters were not being utilised by manifold.TSNE. 6497 by Sebastian Säger <ssaeger>
- Fix bug for svm's decision values when `
decision_function_shape`
is `ovr in svm.SVC. svm.SVC's decision_function was incorrect from versions 0.17.0 through 0.18.0. 7724 by Bing Tian Dai`_
- Attribute `
explained_variance_ratio` of
discriminant_analysis.LinearDiscriminantAnalysis calculated with SVD and Eigen solver are now of the same length. 7632 by JPFrancoia <JPFrancoia>
- Fixes issue in
univariate_feature_selectionwhere score
functions were not accepting multi-label targets. 7676 by Mohammed Affan <affanv14>
- Fixed setting parameters when calling `
fit` multiple times on
feature_selection.SelectFromModel. 7756 by Andreas Müller_
- Fixes issue in `
partial_fit` method of
multiclass.OneVsRestClassifier when number of classes used in `partial_fit was less than the total number of classes in the data. 7786 by Srivatsan Ramesh`_
- Fixes issue in
calibration.CalibratedClassifierCVwhere
the sum of probabilities of each class for a data was not 1, and `CalibratedClassifierCV now handles the case where the training set has less number of classes than the total data. 7799 by Srivatsan Ramesh`_
- Fix a bug where
sklearn.feature_selection.SelectFdrdid not
exactly implement Benjamini-Hochberg procedure. It formerly may have selected fewer features than it should. 7490 by Peng Meng <mpjlu>.
sklearn.manifold.LocallyLinearEmbeddingnow correctly handles
integer inputs. 6282 by Jake Vanderplas_.
- The `
min_weight_fraction_leaf` parameter of tree-based classifiers and
regressors now assumes uniform sample weights by default if the `sample_weight argument is not passed to the fit function. Previously, the parameter was silently ignored. 7301 by Nelson Liu <nelson-liu>`.
- Numerical issue with
linear_model.RidgeCVon centered data when
n_features > n_samples. 6178 by Bertrand Thirion_
- Tree splitting criterion classes' cloning/pickling is now memory safe
7680 by Ibraim Ganiev <olologin>.
- Fixed a bug where
decomposition.NMFsets its `n_iters_`
attribute in transform(). 7553 by :user:Ekaterina Krivich <kiote>.
sklearn.linear_model.LogisticRegressionCVnow correctly handles
string labels. 5874 by Raghav RV_.
- Fixed a bug where
sklearn.model_selection.train_test_splitraised
an error when `stratify is a list of string labels. 7593 by Raghav RV`_.
- Fixed a bug where
sklearn.model_selection.GridSearchCVand
sklearn.model_selection.RandomizedSearchCV were not pickleable because of a pickling bug in `np.ma.MaskedArray. 7594 by Raghav RV`_.
- All cross-validation utilities in
sklearn.model_selectionnow
permit one time cross-validation splitters for the `cv parameter. Also non-deterministic cross-validation splitters (where multiple calls to split produce dissimilar splits) can be used as cv parameter. The sklearn.model_selection.GridSearchCV will cross-validate each parameter setting on the split produced by the first split call to the cross-validation splitter. 7660 by Raghav RV`_.
- Fix bug where
preprocessing.MultiLabelBinarizer.fit_transform
returned an invalid CSR matrix. 7750 by CJ Carey <perimosocordiae>.
- Fixed a bug where
metrics.pairwise.cosine_distancescould return a
small negative distance. 7732 by Artsion <asanakoy>.
API changes summary
Trees and forests
- The `
min_weight_fraction_leaf` parameter of tree-based classifiers and
regressors now assumes uniform sample weights by default if the `sample_weight argument is not passed to the fit function. Previously, the parameter was silently ignored. 7301 by :user:Nelson Liu <nelson-liu>`.
- Tree splitting criterion classes' cloning/pickling is now memory safe.
7680 by Ibraim Ganiev <olologin>.
Linear, kernelized and related models
- Length of `
explained_variance_ratio` of
discriminant_analysis.LinearDiscriminantAnalysis changed for both Eigen and SVD solvers. The attribute has now a length of min(n_components, n_classes - 1). 7632 by JPFrancoia <JPFrancoia>
- Numerical issue with
linear_model.RidgeCVon centered data when
`n_features > n_samples. 6178 by Bertrand Thirion`_
Version 0.18
September 28, 2016
Model Selection Enhancements and API Changes
- The model_selection module
The new module sklearn.model_selection, which groups together the functionalities of formerly sklearn.cross_validation, sklearn.grid_search and sklearn.learning_curve, introduces new possibilities such as nested cross-validation and better manipulation of parameter searches with Pandas.
Many things will stay the same but there are some key differences. Read below to know more about the changes.
- Data-independent CV splitters enabling nested cross-validation
The new cross-validation splitters, defined in the sklearn.model_selection, are no longer initialized with any data-dependent parameters such as `y. Instead they expose a split` method that takes in the data and yields a generator for the different splits.
This change makes it possible to use the cross-validation splitters to perform nested cross-validation, facilitated by model_selection.GridSearchCV and model_selection.RandomizedSearchCV utilities.
- The enhanced cv_results_ attribute
The new `cv_results_ attribute (of model_selection.GridSearchCV and model_selection.RandomizedSearchCV) introduced in lieu of the grid_scores_` attribute is a dict of 1D arrays with elements in each array corresponding to the parameter settings (i.e. search candidates).
The `cv_results_ dict can be easily imported into pandas as a DataFrame` for exploring the search results.
The `cv_results_ arrays include scores for each cross-validation split (with keys such as 'split0_test_score'), as well as their mean ('mean_test_score') and standard deviation ('std_test_score'`).
The ranks for the search candidates (based on their mean cross-validation score) is available at `cv_results_['rank_test_score']`.
The parameter values for each parameter is stored separately as numpy masked object arrays. The value, for that search candidate, is masked if the corresponding parameter is not applicable. Additionally a list of all the parameter dicts are stored at `cv_results_['params']`.
- Parameters n_folds and n_iter renamed to n_splits
Some parameter names have changed: The `n_folds parameter in new model_selection.KFold, model_selection.GroupKFold (see below for the name change), and model_selection.StratifiedKFold is now renamed to n_splits. The n_iter parameter in model_selection.ShuffleSplit, the new class model_selection.GroupShuffleSplit and model_selection.StratifiedShuffleSplit is now renamed to n_splits`.
- Rename of splitter classes which accepts group labels along with data
The cross-validation splitters `LabelKFold, LabelShuffleSplit, LeaveOneLabelOut and LeavePLabelOut have been renamed to model_selection.GroupKFold, model_selection.GroupShuffleSplit, model_selection.LeaveOneGroupOut and model_selection.LeavePGroupsOut` respectively.
Note the change from singular to plural form in model_selection.LeavePGroupsOut.
- Fit parameter labels renamed to groups
The `labels parameter in the split method of the newly renamed splitters model_selection.GroupKFold, model_selection.LeaveOneGroupOut, model_selection.LeavePGroupsOut, model_selection.GroupShuffleSplit is renamed to groups` following the new nomenclature of their class names.
- Parameter n_labels renamed to n_groups
The parameter `n_labels in the newly renamed model_selection.LeavePGroupsOut is changed to n_groups`.
- Training scores and Timing information
`cv_results_ also includes the training scores for each cross-validation split (with keys such as 'split0_train_score'), as well as their mean ('mean_train_score') and standard deviation ('std_train_score'). To avoid the cost of evaluating training score, set return_train_score=False`.
Additionally the mean and standard deviation of the times taken to split, train and score the model across all the cross-validation splits is available at the key `'mean_time' and 'std_time'` respectively.
Changelog
New features ............
Classifiers and Regressors
- The Gaussian Process module has been reimplemented and now offers classification
and regression estimators through gaussian_process.GaussianProcessClassifier and gaussian_process.GaussianProcessRegressor. Among other things, the new implementation supports kernel engineering, gradient-based hyperparameter optimization or sampling of functions from GP prior and GP posterior. Extensive documentation and examples are provided. By Jan Hendrik Metzen_.
- Added new supervised learning algorithm:
Multi-layer Perceptron <multilayer_perceptron>
3204 by Issam H. Laradji <IssamLaradji>
- Added
linear_model.HuberRegressor, a linear model robust to outliers.
5291 by Manoj Kumar_.
- Added the
multioutput.MultiOutputRegressormeta-estimator. It
converts single output regressors to multi-output regressors by fitting one regressor per output. By Tim Head <betatim>.
Other estimators
- New
mixture.GaussianMixtureandmixture.BayesianGaussianMixture
replace former mixture models, employing faster inference for sounder results. 7295 by Wei Xue <xuewei4d> and Thierry Guillemot <tguillemot>.
- Class
decomposition.RandomizedPCAis now factored intodecomposition.PCA
and it is available calling with parameter `svd_solver='randomized'. The default number of n_iter for 'randomized' has changed to 4. The old behavior of PCA is recovered by svd_solver='full'. An additional solver calls arpack and performs truncated (non-randomized) SVD. By default, the best solver is selected depending on the size of the input and the number of components requested. 5299 by Giorgio Patrini <giorgiop>`.
- Added two functions for mutual information estimation:
feature_selection.mutual_info_classif and feature_selection.mutual_info_regression. These functions can be used in feature_selection.SelectKBest and feature_selection.SelectPercentile as score functions. By Andrea Bravi <AndreaBravi> and Nikolay Mayorov <nmayorov>.
- Added the
ensemble.IsolationForestclass for anomaly detection based on
random forests. By Nicolas Goix_.
- Added `
algorithm="elkan"tocluster.KMeans` implementing
Elkan's fast K-Means algorithm. By Andreas Müller_.
Model selection and evaluation
- Added
metrics.fowlkes_mallows_score, the Fowlkes Mallows
Index which measures the similarity of two clusterings of a set of points By Arnaud Fouchet <afouchet> and Thierry Guillemot <tguillemot>.
- Added
metrics.calinski_harabaz_score, which computes the Calinski
and Harabaz score to evaluate the resulting clustering of a set of points. By Arnaud Fouchet <afouchet> and Thierry Guillemot <tguillemot>.
- Added new cross-validation splitter
model_selection.TimeSeriesSplit to handle time series data. 6586 by YenChen Lin <yenchenlin>
- The cross-validation iterators are replaced by cross-validation splitters
available from sklearn.model_selection, allowing for nested cross-validation. See model_selection_changes for more information. 4294 by Raghav RV_.
Enhancements ............
Trees and ensembles
- Added a new splitting criterion for
tree.DecisionTreeRegressor,
the mean absolute error. This criterion can also be used in ensemble.ExtraTreesRegressor, ensemble.RandomForestRegressor, and the gradient boosting estimators. 6667 by Nelson Liu <nelson-liu>.
- Added weighted impurity-based early stopping criterion for decision tree
growth. 6954 by Nelson Liu <nelson-liu>
- The random forest, extra tree and decision tree estimators now has a
method `decision_path which returns the decision path of samples in the tree. By Arnaud Joly`_.
- A new example has been added unveiling the decision tree structure.
By Arnaud Joly_.
- Random forest, extra trees, decision trees and gradient boosting estimator
accept the parameter `min_samples_split and min_samples_leaf provided as a percentage of the training samples. By yelite <yelite> and Arnaud Joly`_.
- Gradient boosting estimators accept the parameter `
criterion` to specify
to splitting criterion used in built decision trees. 6667 by Nelson Liu <nelson-liu>.
- The memory footprint is reduced (sometimes greatly) for
ensemble.bagging.BaseBagging and classes that inherit from it, i.e, ensemble.BaggingClassifier, ensemble.BaggingRegressor, and ensemble.IsolationForest, by dynamically generating attribute `estimators_samples_ only when it is needed. By David Staub <staubda>`.
- Added `
n_jobsandsample_weight` parameters for
ensemble.VotingClassifier to fit underlying estimators in parallel. 5805 by Ibraim Ganiev <olologin>.
Linear, kernelized and related models
- In
linear_model.LogisticRegression, the SAG solver is now
available in the multinomial case. 5251 by Tom Dupre la Tour_.
linear_model.RANSACRegressor,svm.LinearSVCand
svm.LinearSVR now support `sample_weight. By Imaculate <Imaculate>`.
- Add parameter `
losstolinear_model.RANSACRegressor` to measure the
error on the samples for every trial. By Manoj Kumar_.
- Prediction of out-of-sample events with Isotonic Regression
(isotonic.IsotonicRegression) is now much faster (over 1000x in tests with synthetic data). By Jonathan Arfa <jarfa>.
- Isotonic regression (
isotonic.IsotonicRegression) now uses a better algorithm to avoid
O(n^2) behavior in pathological cases, and is also generally faster (#6691). By Antony Lee_.
naive_bayes.GaussianNBnow accepts data-independent class-priors
through the parameter `priors. By Guillaume Lemaitre <glemaitre>`.
linear_model.ElasticNetandlinear_model.Lasso
now works with `np.float32 input data without converting it into np.float64. This allows to reduce the memory consumption. 6913 by YenChen Lin <yenchenlin>`.
semi_supervised.LabelPropagationandsemi_supervised.LabelSpreading
now accept arbitrary kernel functions in addition to strings `knn and rbf. 5762 by Utkarsh Upadhyay <musically-ut>`.
Decomposition, manifold learning and clustering
- Added `
inverse_transformfunction todecomposition.NMF` to compute
data matrix of original shape. By Anish Shah <AnishShah>.
cluster.KMeansandcluster.MiniBatchKMeansnow works
with `np.float32 and np.float64 input data without converting it. This allows to reduce the memory consumption by using np.float32. 6846 by Sebastian Säger <ssaeger> and YenChen Lin <yenchenlin>`.
Preprocessing and feature selection
preprocessing.RobustScalernow accepts `quantile_range` parameter.
5929 by Konstantin Podshumok <podshumok>.
feature_extraction.FeatureHashernow accepts string values.
6173 by Ryad Zenine <ryadzenine> and Devashish Deshpande <dsquareindia>.
- Keyword arguments can now be supplied to `
func` in
preprocessing.FunctionTransformer by means of the `kw_args parameter. By Brian McFee`_.
feature_selection.SelectKBestandfeature_selection.SelectPercentile
now accept score functions that take X, y as input and return only the scores. By Nikolay Mayorov <nmayorov>.
Model evaluation and meta-estimators
multiclass.OneVsOneClassifierandmulticlass.OneVsRestClassifier
now support `partial_fit. By Asish Panda <kaichogami> and Philipp Dowling <phdowling>`.
- Added support for substituting or disabling
pipeline.Pipeline
and pipeline.FeatureUnion components using the `set_params interface that powers sklearn.grid_search. See sphx_glr_auto_examples_compose_plot_compare_reduction.py By Joel Nothman_ and Robert McGibbon <rmcgibbo>`.
- The new `
cv_results_attribute ofmodel_selection.GridSearchCV`
(and model_selection.RandomizedSearchCV) can be easily imported into pandas as a `DataFrame. Ref model_selection_changes for more information. 6697 by Raghav RV`_.
- Generalization of
model_selection.cross_val_predict.
One can pass method names such as predict_proba to be used in the cross validation framework instead of the default predict. By Ori Ziv <zivori> and Sears Merritt <merritts>.
- The training scores and time taken for training followed by scoring for
each search candidate are now available at the `cv_results_ dict. See model_selection_changes for more information. 7325 by Eugene Chen <eyc88> and Raghav RV`_.
Metrics
- Added `
labelsflag tometrics.log_loss` to explicitly provide
the labels when the number of classes in `y_true and y_pred differ. 7239 by Hong Guangguo <hongguangguo> with help from Mads Jensen <indianajensen> and Nelson Liu <nelson-liu>`.
- Support sparse contingency matrices in cluster evaluation
(metrics.cluster.supervised) to scale to a large number of clusters. 7419 by Gregory Stupp <stuppie> and Joel Nothman_.
- Add `
sample_weightparameter tometrics.matthews_corrcoef`.
By Jatin Shah <jatinshah> and Raghav RV_.
- Speed up
metrics.silhouette_scoreby using vectorized operations.
By Manoj Kumar_.
- Add `
sample_weightparameter tometrics.confusion_matrix`.
By Bernardo Stein <DanielSidhion>.
Miscellaneous
- Added `
n_jobsparameter tofeature_selection.RFECV` to compute
the score on the test folds in parallel. By Manoj Kumar_
- Codebase does not contain C/C++ cython generated files: they are
generated during build. Distribution packages will still contain generated C/C++ files. By Arthur Mensch <arthurmensch>.
- Reduce the memory usage for 32-bit float input arrays of
utils.sparse_func.mean_variance_axis and utils.sparse_func.incr_mean_variance_axis by supporting cython fused types. By YenChen Lin <yenchenlin>.
- The
ignore_warningsnow accept a category argument to ignore only
the warnings of a specified type. By Thierry Guillemot <tguillemot>.
- Added parameter `
return_X_yand return type(data, target) : tuple` option to
datasets.load_iris dataset 7049, datasets.load_breast_cancer dataset 7152, datasets.load_digits dataset, datasets.load_diabetes dataset, datasets.load_linnerud dataset, datasets.load_boston dataset 7154 by Manvendra Singh<manu-chroma>.
- Simplification of the `
clone` function, deprecate support for estimators
that modify parameters in `__init__. 5540 by Andreas Müller`_.
- When unpickling a scikit-learn estimator in a different version than the one
the estimator was trained with, a `UserWarning is raised, see :ref:the documentation on model persistence <persistence_limitations> for more details. (7248) By Andreas Müller`_.
Bug fixes .........
Trees and ensembles
- Random forest, extra trees, decision trees and gradient boosting
won't accept anymore `min_samples_split=1 as at least 2 samples are required to split a decision tree node. By Arnaud Joly`_
ensemble.VotingClassifiernow raises `NotFittedErrorifpredict`,
`transform or predict_proba are called on the non-fitted estimator. by Sebastian Raschka`_.
- Fix bug where
ensemble.AdaBoostClassifierand
ensemble.AdaBoostRegressor would perform poorly if the `random_state was fixed (7411). By Joel Nothman`_.
- Fix bug in ensembles with randomization where the ensemble would not
set `random_state on base estimators in a pipeline or similar nesting. (7411). Note, results for ensemble.BaggingClassifier ensemble.BaggingRegressor, ensemble.AdaBoostClassifier and ensemble.AdaBoostRegressor will now differ from previous versions. By Joel Nothman`_.
Linear, kernelized and related models
- Fixed incorrect gradient computation for `
loss='squared_epsilon_insensitive'` in
linear_model.SGDClassifier and linear_model.SGDRegressor (6764). By Wenhua Yang <geekoala>.
- Fix bug in
linear_model.LogisticRegressionCVwhere
`solver='liblinear' did not accept class_weights='balanced. (6817). By Tom Dupre la Tour`_.
- Fix bug in
neighbors.RadiusNeighborsClassifierwhere an error
occurred when there were outliers being labelled and a weight function specified (6902). By LeonieBorne <https://github.com/LeonieBorne>_.
- Fix
linear_model.ElasticNetsparse decision function to match
output with dense in the multioutput case.
Decomposition, manifold learning and clustering
decomposition.RandomizedPCAdefault number ofiterated_poweris 4 instead of 3.
5141 by Giorgio Patrini <giorgiop>.
utils.extmath.randomized_svdperforms 4 power iterations by default, instead
of 0. In practice this is enough for obtaining a good approximation of the true eigenvalues/vectors in the presence of noise. When n_components is small (`< .1 * min(X.shape)) n_iter is set to 7, unless the user specifies a higher number. This improves precision with few components. 5299 by Giorgio Patrini<giorgiop>`.
- Whiten/non-whiten inconsistency between components of
decomposition.PCA
and decomposition.RandomizedPCA (now factored into PCA, see the New features) is fixed. components_ are stored with no whitening. 5299 by Giorgio Patrini <giorgiop>.
- Fixed bug in
manifold.spectral_embeddingwhere diagonal of unnormalized
Laplacian matrix was incorrectly set to 1. 4995 by Peter Fischer <yanlend>.
- Fixed incorrect initialization of
utils.arpack.eigshon all
occurrences. Affects cluster.bicluster.SpectralBiclustering, decomposition.KernelPCA, manifold.LocallyLinearEmbedding, and manifold.SpectralEmbedding (5012). By Peter Fischer <yanlend>.
- Attribute `
explained_variance_ratio_` calculated with the SVD solver
of discriminant_analysis.LinearDiscriminantAnalysis now returns correct results. By JPFrancoia <JPFrancoia>
Preprocessing and feature selection
preprocessing.data._transform_selectednow always passes a copy
of `X to transform function when copy=True (7194). By Caio Oliveira <https://github.com/caioaao>`_.
Model evaluation and meta-estimators
model_selection.StratifiedKFoldnow raises error if all n_labels
for individual classes is less than n_folds. 6182 by Devashish Deshpande <dsquareindia>.
- Fixed bug in
model_selection.StratifiedShuffleSplit
where train and test sample could overlap in some edge cases, see 6121 for more details. By Loic Esteve_.
- Fix in
sklearn.model_selection.StratifiedShuffleSplitto
return splits of size `train_size and test_size in all cases (6472). By Andreas Müller`_.
- Cross-validation of
multiclass.OneVsOneClassifierand
multiclass.OneVsRestClassifier now works with precomputed kernels. 7350 by Russell Smith <rsmith54>.
- Fix incomplete `
predict_proba` method delegation from
model_selection.GridSearchCV to linear_model.SGDClassifier (7159) by Yichuan Liu <https://github.com/yl565>_.
Metrics
- Fix bug in
metrics.silhouette_scorein which clusters of
size 1 were incorrectly scored. They should get a score of 0. By Joel Nothman_.
- Fix bug in
metrics.silhouette_samplesso that it now works with
arbitrary labels, not just those ranging from 0 to n_clusters - 1.
- Fix bug where expected and adjusted mutual information were incorrect if
cluster contingency cells exceeded `2**16. By Joel Nothman`_.
metrics.pairwise_distancesnow converts arrays to
boolean arrays when required in `scipy.spatial.distance. 5460 by Tom Dupre la Tour`_.
- Fix sparse input support in
metrics.silhouette_scoreas well as
example examples/text/document_clustering.py. By YenChen Lin <yenchenlin>.
metrics.roc_curveandmetrics.precision_recall_curveno
longer round `y_score values when creating ROC curves; this was causing problems for users with very small differences in scores (7353`).
Miscellaneous
model_selection.tests._search._check_param_gridnow works correctly with all types
that extends/implements Sequence (except string), including range (Python 3.x) and xrange (Python 2.x). 7323 by Viacheslav Kovalevskyi.
utils.extmath.randomized_range_finderis more numerically stable when many
power iterations are requested, since it applies LU normalization by default. If `n_iter<2 numerical issues are unlikely, thus no normalization is applied. Other normalization options are available: 'none', 'LU' and 'QR'. 5141 by Giorgio Patrini <giorgiop>`.
- Fix a bug where some formats of `
scipy.sparse` matrix, and estimators
with them as parameters, could not be passed to base.clone. By Loic Esteve_.
datasets.load_svmlight_filenow is able to read long int QID values.
7101 by Ibraim Ganiev <olologin>.
API changes summary
Linear, kernelized and related models
- `
residual_metrichas been deprecated inlinear_model.RANSACRegressor`.
Use `loss instead. By Manoj Kumar`_.
- Access to public attributes `
.X_and.y_` has been deprecated in
isotonic.IsotonicRegression. By Jonathan Arfa <jarfa>.
Decomposition, manifold learning and clustering
- The old
mixture.DPGMMis deprecated in favor of the new
mixture.BayesianGaussianMixture (with the parameter `weight_concentration_prior_type='dirichlet_process'). The new class solves the computational problems of the old class and computes the Gaussian mixture with a Dirichlet process prior faster than before. 7295 by Wei Xue <xuewei4d> and Thierry Guillemot <tguillemot>`.
- The old
mixture.VBGMMis deprecated in favor of the new
mixture.BayesianGaussianMixture (with the parameter `weight_concentration_prior_type='dirichlet_distribution'). The new class solves the computational problems of the old class and computes the Variational Bayesian Gaussian mixture faster than before. 6651 by Wei Xue <xuewei4d> and Thierry Guillemot <tguillemot>`.
- The old
mixture.GMMis deprecated in favor of the new
mixture.GaussianMixture. The new class computes the Gaussian mixture faster than before and some of computational problems have been solved. 6666 by Wei Xue <xuewei4d> and Thierry Guillemot <tguillemot>.
Model evaluation and meta-estimators
- The
sklearn.cross_validation,sklearn.grid_searchand
sklearn.learning_curve have been deprecated and the classes and functions have been reorganized into the sklearn.model_selection module. Ref model_selection_changes for more information. 4294 by Raghav RV_.
- The `
grid_scores_attribute ofmodel_selection.GridSearchCV`
and model_selection.RandomizedSearchCV is deprecated in favor of the attribute `cv_results_. Ref model_selection_changes for more information. 6697 by Raghav RV`_.
- The parameters `
n_iterorn_folds` in old CV splitters are replaced
by the new parameter `n_splits since it can provide a consistent and unambiguous interface to represent the number of train-test splits. 7187 by YenChen Lin <yenchenlin>`.
- `
classesparameter was renamed tolabels` in
metrics.hamming_loss. 7260 by Sebastián Vanrell <srvanrell>.
- The splitter classes `
LabelKFold,LabelShuffleSplit`,
`LeaveOneLabelOut and LeavePLabelsOut are renamed to model_selection.GroupKFold, model_selection.GroupShuffleSplit, model_selection.LeaveOneGroupOut and model_selection.LeavePGroupsOut respectively. Also the parameter labels in the split method of the newly renamed splitters model_selection.LeaveOneGroupOut and model_selection.LeavePGroupsOut is renamed to groups. Additionally in model_selection.LeavePGroupsOut, the parameter n_labels is renamed to n_groups. 6660 by Raghav RV`_.
- Error and loss names for `
scoring` parameters are now prefixed by
`'neg_', such as neg_mean_squared_error. The unprefixed versions are deprecated and will be removed in version 0.20. 7261 by Tim Head <betatim>`.
Code Contributors
Aditya Joshi, Alejandro, Alexander Fabisch, Alexander Loginov, Alexander Minyushkin, Alexander Rudy, Alexandre Abadie, Alexandre Abraham, Alexandre Gramfort, Alexandre Saint, alexfields, Alvaro Ulloa, alyssaq, Amlan Kar, Andreas Mueller, andrew giessel, Andrew Jackson, Andrew McCulloh, Andrew Murray, Anish Shah, Arafat, Archit Sharma, Ariel Rokem, Arnaud Joly, Arnaud Rachez, Arthur Mensch, Ash Hoover, asnt, b0noI, Behzad Tabibian, Bernardo, Bernhard Kratzwald, Bhargav Mangipudi, blakeflei, Boyuan Deng, Brandon Carter, Brett Naul, Brian McFee, Caio Oliveira, Camilo Lamus, Carol Willing, Cass, CeShine Lee, Charles Truong, Chyi-Kwei Yau, CJ Carey, codevig, Colin Ni, Dan Shiebler, Daniel, Daniel Hnyk, David Ellis, David Nicholson, David Staub, David Thaler, David Warshaw, Davide Lasagna, Deborah, definitelyuncertain, Didi Bar-Zev, djipey, dsquareindia, edwinENSAE, Elias Kuthe, Elvis DOHMATOB, Ethan White, Fabian Pedregosa, Fabio Ticconi, fisache, Florian Wilhelm, Francis, Francis O'Donovan, Gael Varoquaux, Ganiev Ibraim, ghg, Gilles Louppe, Giorgio Patrini, Giovanni Cherubin, Giovanni Lanzani, Glenn Qian, Gordon Mohr, govin-vatsan, Graham Clenaghan, Greg Reda, Greg Stupp, Guillaume Lemaitre, Gustav Mörtberg, halwai, Harizo Rajaona, Harry Mavroforakis, hashcode55, hdmetor, Henry Lin, Hobson Lane, Hugo Bowne-Anderson, Igor Andriushchenko, Imaculate, Inki Hwang, Isaac Sijaranamual, Ishank Gulati, Issam Laradji, Iver Jordal, jackmartin, Jacob Schreiber, Jake Vanderplas, James Fiedler, James Routley, Jan Zikes, Janna Brettingen, jarfa, Jason Laska, jblackburne, jeff levesque, Jeffrey Blackburne, Jeffrey04, Jeremy Hintz, jeremynixon, Jeroen, Jessica Yung, Jill-Jênn Vie, Jimmy Jia, Jiyuan Qian, Joel Nothman, johannah, John, John Boersma, John Kirkham, John Moeller, jonathan.striebel, joncrall, Jordi, Joseph Munoz, Joshua Cook, JPFrancoia, jrfiedler, JulianKahnert, juliathebrave, kaichogami, KamalakerDadi, Kenneth Lyons, Kevin Wang, kingjr, kjell, Konstantin Podshumok, Kornel Kielczewski, Krishna Kalyan, krishnakalyan3, Kvle Putnam, Kyle Jackson, Lars Buitinck, ldavid, LeiG, LeightonZhang, Leland McInnes, Liang-Chi Hsieh, Lilian Besson, lizsz, Loic Esteve, Louis Tiao, Léonie Borne, Mads Jensen, Maniteja Nandana, Manoj Kumar, Manvendra Singh, Marco, Mario Krell, Mark Bao, Mark Szepieniec, Martin Madsen, MartinBpr, MaryanMorel, Massil, Matheus, Mathieu Blondel, Mathieu Dubois, Matteo, Matthias Ekman, Max Moroz, Michael Scherer, michiaki ariga, Mikhail Korobov, Moussa Taifi, mrandrewandrade, Mridul Seth, nadya-p, Naoya Kanai, Nate George, Nelle Varoquaux, Nelson Liu, Nick James, NickleDave, Nico, Nicolas Goix, Nikolay Mayorov, ningchi, nlathia, okbalefthanded, Okhlopkov, Olivier Grisel, Panos Louridas, Paul Strickland, Perrine Letellier, pestrickland, Peter Fischer, Pieter, Ping-Yao, Chang, practicalswift, Preston Parry, Qimu Zheng, Rachit Kansal, Raghav RV, Ralf Gommers, Ramana.S, Rammig, Randy Olson, Rob Alexander, Robert Lutz, Robin Schucker, Rohan Jain, Ruifeng Zheng, Ryan Yu, Rémy Léone, saihttam, Saiwing Yeung, Sam Shleifer, Samuel St-Jean, Sartaj Singh, Sasank Chilamkurthy, saurabh.bansod, Scott Andrews, Scott Lowe, seales, Sebastian Raschka, Sebastian Saeger, Sebastián Vanrell, Sergei Lebedev, shagun Sodhani, shanmuga cv, Shashank Shekhar, shawpan, shengxiduan, Shota, shuckle16, Skipper Seabold, sklearn-ci, SmedbergM, srvanrell, Sébastien Lerique, Taranjeet, themrmax, Thierry, Thierry Guillemot, Thomas, Thomas Hallock, Thomas Moreau, Tim Head, tKammy, toastedcornflakes, Tom, TomDLT, Toshihiro Kamishima, tracer0tong, Trent Hauck, trevorstephens, Tue Vo, Varun, Varun Jewalikar, Viacheslav, Vighnesh Birodkar, Vikram, Villu Ruusmann, Vinayak Mehta, walter, waterponey, Wenhua Yang, Wenjian Huang, Will Welch, wyseguy7, xyguo, yanlend, Yaroslav Halchenko, yelite, Yen, YenChenLin, Yichuan Liu, Yoav Ram, Yoshiki, Zheng RuiFeng, zivori, Óscar Nájera