Release History¶
Release notes for current and recent releases are detailed on this page, with previous releases linked below.
Tip: Subscribe to scikit-learn releases on libraries.io to be notified when new versions are released.
Version 0.20 (under development)¶
This release packs in a mountain of bug fixes, features and enhancements for the Scikit-learn library, and improvements to the documentation and examples. Thanks to our many contributors!
Highlights¶
We have tried to improve our support for common data-science use-cases including missing values, categorical variables, heterogeneous data, and features/targets with unusual distributions.
Missing values in features, represented by NaNs, are now accepted in
column-wise preprocessing such as scalers. Each feature is fitted disregarding
NaNs, and data containing NaNs can be transformed. The new impute
module provides estimators for learning despite missing data.
ColumnTransformer
handles the case where different features
or columns of a pandas.DataFrame need different preprocessing.
String or pandas Categorical columns can now be encoded with
OneHotEncoder
or
OrdinalEncoder
.
TransformedTargetRegressor
helps when the regression target
needs to be transformed to be modeled. PowerTransformer
and KBinsDiscretizer
join
QuantileTransformer
as non-linear transformations.
Beyond this, we have added sample_weight support to several estimators
(including KMeans
, BayesianRidge
and
KernelDensity
) and improved stopping criteria in others
(including MLPRegressor
,
GradientBoostingRegressor
and
SGDRegressor
).
This release is also the first to be accompanied by a Glossary of Common Terms and API Elements developed by Joel Nothman. The glossary is a reference resource to help users and contributors become familiar with the terminology and conventions used in Scikit-learn.
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.
decomposition.IncrementalPCA
in Python 2 (bug fix)isotonic.IsotonicRegression
(bug fix)linear_model.ARDRegression
(bug fix)linear_model.OrthogonalMatchingPursuit
(bug fix)metrics.roc_auc_score
(bug fix)metrics.roc_curve
(bug fix)neural_network.MLPRegressor
(bug fix)neural_network.MLPClassifier
(bug fix)neural_network.BaseMultilayerPerceptron
(bug fix)linear_model.SGDClassifier
(bug fix)linear_model.SGDRegressor
(bug fix)linear_model.PassiveAggressiveClassifier
(bug fix)linear_model.PassiveAggressiveRegressor
(bug fix)linear_model.Perceptron
(bug fix)ensemble.gradient_boosting.GradientBoostingClassifier
(bug fix affecting feature importances)- The v0.19.0 release notes failed to mention a backwards incompatibility with
model_selection.StratifiedKFold
whenshuffle=True
due to #7823.
Details are listed in the changelog below.
(While we are trying to better inform users by providing this information, we cannot assure that this list is complete.)
Changelog¶
Support for Python 3.3 has been officially dropped.
New features¶
Classifiers and regressors
ensemble.GradientBoostingClassifier
andensemble.GradientBoostingRegressor
now support early stopping vian_iter_no_change
,validation_fraction
andtol
. #7071 by Raghav RVdummy.DummyRegressor
now has areturn_std
option in itspredict
method. The returned standard deviations will be zeros.- Added
multioutput.RegressorChain
for multi-target regression. #9257 by Kumar Ashutosh. - Added
naive_bayes.ComplementNB
, which implements the Complement Naive Bayes classifier described in Rennie et al. (2003). #8190 by Michael A. Alcorn. ensemble.BaggingRegressor
andensemble.BaggingClassifier
can now be fit with missing/non-finite values in X and/or multi-output Y to support wrapping pipelines that perform their own imputation. #9707 by Jimmy Wan.
Preprocessing
- Expanded
preprocessing.OneHotEncoder
to allow to encode categorical string features as a numeric array using a one-hot (or dummy) encoding scheme, and addedpreprocessing.OrdinalEncoder
to convert to ordinal integers. Those two classes now handle encoding of all feature types (also handles string-valued features) and derives the categories based on the unique values in the features instead of the maximum value in the features. #9151 and #10521 by Vighnesh Birodkar and Joris Van den Bossche. - Added
preprocessing.KBinsDiscretizer
for turning continuous features into categorical or one-hot encoded features. #7668, #9647, #10195, #10192, #11272 and #11467. by Henry Lin, Hanmin Qin and Tom Dupre la Tour. - Added
compose.ColumnTransformer
, which allows to apply different transformers to different columns of arrays or pandas DataFrames. #9012 by Andreas Müller and Joris Van den Bossche, and #11315 by Thomas Fan. - Added
preprocessing.PowerTransformer
, which implements the Box-Cox power transformation, allowing users to map data from any distribution to a Gaussian distribution. This is useful as a variance-stabilizing transformation in situations where normality and homoscedasticity are desirable. #10210 by Eric Chang and Maniteja Nandana. - Added the
compose.TransformedTargetRegressor
which transforms the target y before fitting a regression model. The predictions are mapped back to the original space via an inverse transform. #9041 by Andreas Müller and Guillaume Lemaitre. - Added
impute.ChainedImputer
, which is a strategy for imputing missing values by modeling each feature with missing values as a function of other features in a round-robin fashion. #8478 by Sergey Feldman. linear_model.SGDClassifier
,linear_model.SGDRegressor
,linear_model.PassiveAggressiveClassifier
,linear_model.PassiveAggressiveRegressor
andlinear_model.Perceptron
now exposeearly_stopping
,validation_fraction
andn_iter_no_change
parameters, to stop optimization monitoring the score on a validation set. A new learning rate"adaptive"
strategy divides the learning rate by 5 each timen_iter_no_change
consecutive epochs fail to improve the model. #9043 by Tom Dupre la Tour.
Model evaluation
- Added the
metrics.davies_bouldin_score
metric for unsupervised evaluation of clustering models. #10827 by Luis Osa. - Added the
metrics.balanced_accuracy_score
metric and a corresponding'balanced_accuracy'
scorer for binary classification. #8066 by @xyguo and Aman Dalmia.
Decomposition, manifold learning and clustering
cluster.AgglomerativeClustering
now supports Single Linkage clustering vialinkage='single'
. #9372 by Leland McInnes and Steve Astels.cluster.KMeans
andcluster.MiniBatchKMeans
now support sample weights via new parametersample_weight
infit
function. #10933 by Johannes Hansen.dict_learning
functions and models now support positivity constraints. This applies to the dictionary and sparse code. #6374 by John Kirkham.
Metrics
- Partial AUC is available via
max_fpr
parameter inmetrics.roc_auc_score
. #3273 by Alexander Niederbühl. - Added
output_dict
parameter inmetrics.classification_report
to return classification statistics as dictionary. #11160 by Dan Barkhorn.
Misc
- A new configuration parameter,
working_memory
was added to control memory consumption limits in chunked operations, such as the newmetrics.pairwise_distances_chunked
. See Limiting Working Memory. #10280 by Joel Nothman and Aman Dalmia. - An environment variable to use the site joblib instead of the vendored
one was added (Environment variables). The main API of joblib is now
exposed in
sklearn.utils.joblib
. #11166 by Gael Varoquaux, Joel Nothman and Olivier Grisel.
Enhancements¶
Classifiers and regressors
- In
gaussian_process.GaussianProcessRegressor
, methodpredict
is faster when usingreturn_std=True
in particular more when called several times in a row. #9234 by andrewww and Minghui Liu. - Add named_estimators_ parameter in
ensemble.VotingClassifier
to access fitted estimators. #9157 by Herilalaina Rakotoarison. - Add var_smoothing parameter in
naive_bayes.GaussianNB
to give a precise control over variances calculation. #9681 by Dmitry Mottl. - Add n_iter_no_change parameter in
neural_network.BaseMultilayerPerceptron
,neural_network.MLPRegressor
, andneural_network.MLPClassifier
to give control over maximum number of epochs to not meettol
improvement. #9456 by Nicholas Nadeau. - A parameter
check_inverse
was added topreprocessing.FunctionTransformer
to ensure thatfunc
andinverse_func
are the inverse of each other. #9399 by Guillaume Lemaitre. - Add sample_weight parameter to the fit method of
linear_model.BayesianRidge
for weighted linear regression. #10111 by Peter St. John. dummy.DummyClassifier
anddummy.DummyRegressor
now only require X to be an object with finite length or shape. #9832 by Vrishank Bhardwaj.- Add sample_weight parameter to the fit method of
neighbors.KernelDensity
to enables weighting in kernel density estimation. #4394 by Samuel O. Ronsin. neighbors.RadiusNeighborsRegressor
andneighbors.RadiusNeighborsClassifier
are now parallelized according ton_jobs
regardless ofalgorithm
. #8003 by Joël Billaud.- Memory usage improvement for
_class_means
and_class_cov
indiscriminant_analysis
. #10898 by Nanxin Chen.` manifold.t_sne.trustworthiness
accepts metrics other than Euclidean. #9775 by William de Vazelhes.Nearest neighbors
query methods are now more memory efficient whenalgorithm='brute'
. #11136 by Joel Nothman and Aman Dalmia.
Cluster
cluster.KMeans
,cluster.MiniBatchKMeans
andcluster.k_means
passed withalgorithm='full'
now enforces row-major ordering, improving runtime. #10471 by Gaurav Dhingra.cluster.DBSCAN
now is parallelized according ton_jobs
regardless ofalgorithm
. #8003 by Joël Billaud.
Datasets
- In
datasets.make_blobs
, one can now pass a list to the n_samples parameter to indicate the number of samples to generate per cluster. #8617 by Maskani Filali Mohamed and Konstantinos Katrioplas.
Preprocessing
preprocessing.PolynomialFeatures
now supports sparse input. #10452 by Aman Dalmia and Joel Nothman.- Enable the call to
get_feature_names
in unfittedfeature_extraction.text.CountVectorizer
initialized with a vocabulary. #10908 by Mohamed Maskani. - The
transform
method ofsklearn.preprocessing.MultiLabelBinarizer
now ignores any unknown classes. A warning is raised stating the unknown classes classes found which are ignored. #10913 by Rodrigo Agundez. - NaN values are ignored and handled in the following preprocessing methods:
preprocessing.MaxAbsScaler
,preprocessing.MinMaxScaler
,preprocessing.RobustScaler
,preprocessing.StandardScaler
,preprocessing.PowerTransformer
,preprocessing.QuantileTransformer
classes andpreprocessing.maxabs_scale
,preprocessing.minmax_scale
,preprocessing.robust_scale
,preprocessing.scale
,preprocessing.power_transform
,preprocessing.quantile_transform
functions respectively addressed in issues #11011, #11005, #11308, #11206, #11306, and #10437. By Lucija Gregov and Guillaume Lemaitre. preprocessing.RobustScaler
andpreprocessing.robust_scale
can be fitted using sparse matrices. #11308 by Guillaume Lemaitre.
Model evaluation and meta-estimators
- A scorer based on
metrics.brier_score_loss
is also available. #9521 by Hanmin Qin. - The default of
iid
parameter ofmodel_selection.GridSearchCV
andmodel_selection.RandomizedSearchCV
will change fromTrue
toFalse
in version 0.22 to correspond to the standard definition of cross-validation, and the parameter will be removed in version 0.24 altogether. This parameter is of greatest practical significance where the sizes of different test sets in cross-validation were very unequal, i.e. in group-based CV strategies. #9085 by Laurent Direr and Andreas Müller. - The
predict
method ofpipeline.Pipeline
now passes keyword arguments on to the pipeline’s last estimator, enabling the use of parameters such asreturn_std
in a pipeline with caution. #9304 by Breno Freitas. - Add return_estimator parameter in
model_selection.cross_validate
to return estimators fitted on each split. #9686 by Aurélien Bellet. - New
refit_time_
attribute will be stored inmodel_selection.GridSearchCV
andmodel_selection.RandomizedSearchCV
ifrefit
is set toTrue
. This will allow measuring the complete time it takes to perform hyperparameter optimization and refitting the best model on the whole dataset. #11310 by Matthias Feurer.
Decomposition and manifold learning
- Speed improvements for both ‘exact’ and ‘barnes_hut’ methods in
manifold.TSNE
. #10593 and #10610 by Tom Dupre la Tour. - Support sparse input in
manifold.Isomap.fit
. #8554 by Leland McInnes.
Metrics
metrics.roc_auc_score
now supports binaryy_true
other than{0, 1}
or{-1, 1}
. #9828 by Hanmin Qin.metrics.label_ranking_average_precision_score
now supports vectorsample_weight
. #10845 by Jose Perez-Parras Toledano.- Add
dense_output
parameter tometrics.pairwise.linear_kernel
. When False and both inputs are sparse, will return a sparse matrix. #10999 by Taylor G Smith. metrics.cluster.silhouette_score
andmetrics.cluster.silhouette_samples
are more memory efficient and run faster. This avoids some reported freezes and MemoryErrors. #11135 by Joel Nothman.
Linear, kernelized and related models
- Deprecate
random_state
parameter insvm.OneClassSVM
as the underlying implementation is not random. #9497 by Albert Thomas.
Decomposition, manifold learning and clustering
- Deprecate
precomputed
parameter in functionmanifold.t_sne.trustworthiness
. Instead, the new parametermetric
should be used with any compatible metric including ‘precomputed’, in which case the input matrixX
should be a matrix of pairwise distances or squared distances. #9775 by William de Vazelhes.
Utils
- Avoid copying the data in
utils.check_array
when the input data is a memmap (andcopy=False
). #10663 by Arthur Mensch and Loïc Estève.
Miscellaneous
- Add
filename
attribute to datasets that have a CSV file. #9101 by alex-33 and Maskani Filali Mohamed.
Bug fixes¶
Classifiers and regressors
- Fixed a bug in
isotonic.IsotonicRegression
which incorrectly combined weights when fitting a model to data involving points with identical X values. #9432 by Dallas Card - Fixed a bug in
neural_network.BaseMultilayerPerceptron
,neural_network.MLPRegressor
, andneural_network.MLPClassifier
with newn_iter_no_change
parameter now at 10 from previously hardcoded 2. #9456 by Nicholas Nadeau. - Fixed a bug in
neural_network.MLPRegressor
where fitting quit unexpectedly early due to local minima or fluctuations. #9456 by Nicholas Nadeau - Fixed a bug in
naive_bayes.GaussianNB
which incorrectly raised error for prior list which summed to 1. #10005 by Gaurav Dhingra. - Fixed a bug in
linear_model.LogisticRegression
where when using the parametermulti_class='multinomial'
, thepredict_proba
method was returning incorrect probabilities in the case of binary outcomes. #9939 by Roger Westover. - Fixed a bug in
linear_model.LogisticRegressionCV
where thescore
method always computes accuracy, not the metric given by thescoring
parameter. #10998 by Thomas Fan. - Fixed a bug in
linear_model.OrthogonalMatchingPursuit
that was broken when settingnormalize=False
. #10071 by Alexandre Gramfort. - Fixed a bug in
linear_model.ARDRegression
which caused incorrectly updated estimates for the standard deviation and the coefficients. #10153 by Jörg Döpfert. - Fixed a bug when fitting
ensemble.GradientBoostingClassifier
orensemble.GradientBoostingRegressor
withwarm_start=True
which previously raised a segmentation fault due to a non-conversion of CSC matrix into CSR format expected bydecision_function
. Similarly, Fortran-ordered arrays are converted to C-ordered arrays in the dense case. #9991 by Guillaume Lemaitre. - Fixed a bug in
neighbors.NearestNeighbors
where fitting a NearestNeighbors model fails when a) the distance metric used is a callable and b) the input to the NearestNeighbors model is sparse. #9579 by Thomas Kober. - Fixed a bug in
linear_model.RidgeClassifierCV
where the parameterstore_cv_values
was not implemented though it was documented incv_values
as a way to set up the storage of cross-validation values for different alphas. #10297 by Mabel Villalba-Jiménez. - Fixed a bug in
naive_bayes.MultinomialNB
which did not accept vector valued pseudocounts (alpha). #10346 by Tobias Madsen - Fixed a bug in
svm.SVC
where when the argumentkernel
is unicode in Python2, thepredict_proba
method was raising an unexpected TypeError given dense inputs. #10412 by Jiongyan Zhang. - Fixed a bug in
tree.BaseDecisionTree
with splitter=”best” where split threshold could become infinite when values in X were near infinite. #10536 by Jonathan Ohayon. - Fixed a bug in
linear_model.ElasticNet
which caused the input to be overridden when using parametercopy_X=True
andcheck_input=False
. #10581 by Yacine Mazari. - Fixed a bug in
sklearn.linear_model.Lasso
where the coefficient had wrong shape whenfit_intercept=False
. #10687 by Martin Hahn. - Fixed a bug in
sklearn.linear_model.LogisticRegression
where the multi_class=’multinomial’ with binary output with warm_start = True #10836 by Aishwarya Srinivasan. - Fixed a bug in
linear_model.RidgeCV
where using integeralphas
raised an error. #10393 by Mabel Villalba-Jiménez. - Fixed condition triggering gap computation in
linear_model.Lasso
andlinear_model.ElasticNet
when working with sparse matrices. #10992 by Alexandre Gramfort. - Fixed a bug in
linear_model.SGDClassifier
,linear_model.SGDRegressor
,linear_model.PassiveAggressiveClassifier
,linear_model.PassiveAggressiveRegressor
andlinear_model.Perceptron
, where the stopping criterion was stopping the algorithm before convergence. A parameter n_iter_no_change was added and set by default to 5. Previous behavior is equivalent to setting the parameter to 1. #9043 by Tom Dupre la Tour. - Fixed a bug where liblinear and libsvm-based estimators would segfault if passed a scipy.sparse matrix with 64-bit indices. They now raise a ValueError. #11327 by Karan Dhingra and Joel Nothman.
- Fixed a bug in
ensemble.gradient_boosting.GradientBoostingRegressor
andensemble.gradient_boosting.GradientBoostingClassifier
to have feature importances summed and then normalized, rather than normalizing on a per-tree basis. The previous behavior over-weighted the Gini importance of features that appear in later stages. This issue only affected feature importances. #11176 by Gil Forsyth.
Decomposition, manifold learning and clustering
- Fix for uninformative error in
decomposition.IncrementalPCA
: now an error is raised if the number of components is larger than the chosen batch size. Then_components=None
case was adapted accordingly. #6452. By Wally Gauze. - Fixed a bug where the
partial_fit
method ofdecomposition.IncrementalPCA
used integer division instead of float division on Python 2 versions. #9492 by James Bourbeau. - Fixed a bug where the
fit
method ofcluster.AffinityPropagation
stored cluster centers as 3d array instead of 2d array in case of non-convergence. For the same class, fixed undefined and arbitrary behavior in case of training data where all samples had equal similarity. #9612. By Jonatan Samoocha. - In
decomposition.PCA
selecting a n_components parameter greater than the number of samples now raises an error. Similarly, then_components=None
case now selects the minimum of n_samples and n_features. #8484. By Wally Gauze. - Fixed a bug in
datasets.fetch_kddcup99
, where data were not properly shuffled. #9731 by Nicolas Goix. - Fixed a bug in
decomposition.PCA
where users will get unexpected error with large datasets whenn_components='mle'
on Python 3 versions. #9886 by Hanmin Qin. - Fixed a bug when setting parameters on meta-estimator, involving both a wrapped estimator and its parameter. #9999 by Marcus Voss and Joel Nothman.
k_means
now gives a warning, if the number of distinct clusters found is smaller thann_clusters
. This may occur when the number of distinct points in the data set is actually smaller than the number of cluster one is looking for. #10059 by Christian Braune.- Fixed a bug in
datasets.make_circles
, where no odd number of data points could be generated. #10037 by Christian Braune. - Fixed a bug in
cluster.spectral_clustering
where the normalization of the spectrum was using a division instead of a multiplication. #8129 by Jan Margeta, Guillaume Lemaitre, and Devansh D.. - Fixed a bug in
mixture.BaseMixture
where the reported n_iter_ was missing an iteration. It affectedmixture.GaussianMixture
andmixture.BayesianGaussianMixture
. #10740 by Erich Schubert and Guillaume Lemaitre. - Fixed a bug in
decomposition.SparseCoder
when running OMP sparse coding in parallel using readonly memory mapped datastructures. #5956 by Vighnesh Birodkar and Olivier Grisel. - Fixed a bug in
cluster.k_means_elkan
where the returned iteration was 1 less than the correct value. Also added the missing n_iter_ attribute in the docstring ofcluster.KMeans
. #11353 by Jeremie du Boisberranger.
Metrics
- Fixed a bug in
metrics.precision_recall_fscore_support
when truncated range(n_labels) is passed as value for labels. #10377 by Gaurav Dhingra. - Fixed a bug due to floating point error in
metrics.roc_auc_score
with non-integer sample weights. #9786 by Hanmin Qin. - Fixed a bug where
metrics.roc_curve
sometimes starts on y-axis instead of (0, 0), which is inconsistent with the document and other implementations. Note that this will not influence the result frommetrics.roc_auc_score
#10093 by alexryndin and Hanmin Qin. - Fixed a bug to avoid integer overflow. Casted product to 64 bits integer in
metrics.mutual_info_score
. #9772 by Kumar Ashutosh. - Fixed a bug in
metrics.fowlkes_mallows_score
to avoid integer overflow. Casted return value of contingency_matrix to int64 and computed product of square roots rather than square root of product. #9515 by Alan Liddell and Manh Dao.
Neighbors
- Fixed a bug so
predict
inneighbors.RadiusNeighborsRegressor
can handle empty neighbor set when using non uniform weights. Also raises a new warning when no neighbors are found for samples. #9655 by Andreas Bjerre-Nielsen.
Feature Extraction
- Fixed a bug in
feature_extraction.image.extract_patches_2d
which would throw an exception ifmax_patches
was greater than or equal to the number of all possible patches rather than simply returning the number of possible patches. #10100 by Varun Agrawal - Fixed a bug in
feature_extraction.text.CountVectorizer
,feature_extraction.text.TfidfVectorizer
,feature_extraction.text.HashingVectorizer
to support 64 bit sparse array indexing necessary to process large datasets with more than 2·10⁹ tokens (words or n-grams). #9147 by Claes-Fredrik Mannby and Roman Yurchak. - Fixed bug in
feature_extraction.text.TFIDFVectorizer
which was ignoring the parameterdtype
. In addition,feature_extraction.text.TFIDFTransformer
will preservedtype
for floating and raise a warning ifdtype
requested is integer. #10441 by Mayur Kulkarni and Guillaume Lemaitre.
Utils
utils.check_array
yield aFutureWarning
indicating that arrays of bytes/strings will be interpreted as decimal numbers beginning in version 0.22. #10229 by Ryan Lee
Preprocessing
- Fixed bugs in
preprocessing.LabelEncoder
which would sometimes throw errors whentransform
orinverse_transform
was called with empty arrays. #10458 by Mayur Kulkarni. - Fix ValueError in
preprocessing.LabelEncoder
when usinginverse_transform
on unseen labels. #9816 by Charlie Newey. - Fix bug in
preprocessing.OneHotEncoder
which discarded thedtype
when returning a sparse matrix output. #11042 by Daniel Morales. - Fix
fit
andpartial_fit
inpreprocessing.StandardScaler
in the rare case when with_mean=False and with_std=False which was crashing by callingfit
more than once and giving inconsistent results formean_
whether the input was a sparse or a dense matrix.mean_
will be set toNone
with both sparse and dense inputs.n_samples_seen_
will be also reported for both input types. #11235 by Guillaume Lemaitre.
Feature selection
- Fixed computation of
n_features_to_compute
for edge case with tied CV scores infeature_selection.RFECV
. #9222 by Nick Hoh <nickypie>.
Model evaluation and meta-estimators
- Add improved error message in
model_selection.cross_val_score
when multiple metrics are passed inscoring
keyword. #11006 by Ming Li.
Datasets
- Fixed a bug in
datasets.load_boston
which had a wrong data point. #10801 by Takeshi Yoshizawa. - Fixed a bug in
datasets.load_iris
which had two wrong data points. #11082 by Sadhana Srinivasan and Hanmin Qin.
API changes summary¶
Linear, kernelized and related models
- Deprecate
random_state
parameter insvm.OneClassSVM
as the underlying implementation is not random. #9497 by Albert Thomas. - Deprecate
positive=True
option inlinear_model.Lars
as the underlying implementation is broken. Uselinear_model.Lasso
instead. #9837 by Alexandre Gramfort. n_iter_
may vary from previous releases inlinear_model.LogisticRegression
withsolver='lbfgs'
andlinear_model.HuberRegressor
. For Scipy <= 1.0.0, the optimizer could perform more than the requested maximum number of iterations. Now both estimators will report at mostmax_iter
iterations even if more were performed. #10723 by Joel Nothman.- The default value of
gamma
parameter ofsvm.SVC
,NuSVC
,SVR
,NuSVR
,OneClassSVM
will change from'auto'
to'scale'
in version 0.22 to account better for unscaled features. #8361 by Gaurav Dhingra and Ting Neo. - Added convergence warning to
svm.LinearSVC
andlinear_model.LogisticRegression
whenverbose
is set to 0. #10881 by Alexandre Sevin.
Preprocessing
- Deprecate
n_values
andcategorical_features
parameters andactive_features_
,feature_indices_
andn_values_
attributes ofpreprocessing.OneHotEncoder
. Then_values
parameter can be replaced with the newcategories
parameter, and the attributes with the newcategories_
attribute. Selecting the categorical features with thecategorical_features
parameter is now better supported using thecompose.ColumnTransformer
. #10521 by Joris Van den Bossche.
Decomposition, manifold learning and clustering
- Deprecate
precomputed
parameter in functionmanifold.t_sne.trustworthiness
. Instead, the new parametermetric
should be used with any compatible metric including ‘precomputed’, in which case the input matrixX
should be a matrix of pairwise distances or squared distances. #9775 by William de Vazelhes. - Added function
fit_predict
tomixture.GaussianMixture
andmixture.GaussianMixture
, which is essentially equivalent to callingfit
andpredict
. #10336 by Shu Haoran and Andrew Peng.
Metrics
- Deprecate
reorder
parameter inmetrics.auc
as it’s no longer required formetrics.roc_auc_score
. Moreover usingreorder=True
can hide bugs due to floating point error in the input. #9851 by Hanmin Qin. - The
batch_size
parameter tometrics.pairwise_distances_argmin_min
andmetrics.pairwise_distances_argmin
is deprecated to be removed in v0.22. It no longer has any effect, as batch size is determined by globalworking_memory
config. See Limiting Working Memory. #10280 by Joel Nothman and Aman Dalmia.
Cluster
- Deprecate
pooling_func
unused parameter incluster.AgglomerativeClustering
. #9875 by Kumar Ashutosh.
Imputer
- Deprecate
preprocessing.Imputer
and move the corresponding module toimpute.SimpleImputer
. #9726 by Kumar Ashutosh. - The
axis
parameter that was inpreprocessing.Imputer
is no longer present inimpute.SimpleImputer
. The behavior is equivalent toaxis=0
(impute along columns). Row-wise imputation can be performed with FunctionTransformer (e.g.,FunctionTransformer(lambda X: SimpleImputer().fit_transform(X.T).T)
). #10829 by Guillaume Lemaitre and Gilberto Olimpio. - The
impute.SimpleImputer
has a new strategy,'constant'
, to complete missing values with a fixed one, given by thefill_value
parameter. This strategy supports numeric and non-numeric data, and so does the'most_frequent'
strategy now. #11211 by Jeremie du Boisberranger. - The NaN marker for the missing values has been changed between the
preprocessing.Imputer
and theimpute.SimpleImputer
.missing_values='NaN'
should now bemissing_values=np.nan
. #11211 by Jeremie du Boisberranger.
Outlier Detection models
- More consistent outlier detection API:
Add a
score_samples
method insvm.OneClassSVM
,ensemble.IsolationForest
,neighbors.LocalOutlierFactor
,covariance.EllipticEnvelope
. It allows to access raw score functions from original papers. A newoffset_
parameter allows to linkscore_samples
anddecision_function
methods. Thecontamination
parameter ofensemble.IsolationForest
andneighbors.LocalOutlierFactor
decision_function
methods is used to define thisoffset_
such that outliers (resp. inliers) have negative (resp. positive)decision_function
values. By default,contamination
is kept unchanged to 0.1 for a deprecation period. In 0.22, it will be set to “auto”, thus using method-specific score offsets. Incovariance.EllipticEnvelope
decision_function
method, theraw_values
parameter is deprecated as the shifted Mahalanobis distance will be always returned in 0.22. #9015 by Nicolas Goix.
Covariance
- The
covariance.graph_lasso
,covariance.GraphLasso
andcovariance.GraphLassoCV
have been renamed tocovariance.graphical_lasso
,covariance.GraphicalLasso
andcovariance.GraphicalLassoCV
respectively and will be removed in version 0.22. #9993 by Artiem Krinitsyn
Misc
- Changed warning type from
UserWarning
toexceptions.ConvergenceWarning
for failing convergence inlinear_model.logistic_regression_path
,linear_model.RANSACRegressor
,linear_model.ridge_regression
,gaussian_process.GaussianProcessRegressor
,gaussian_process.GaussianProcessClassifier
,decomposition.fastica
,cross_decomposition.PLSCanonical
,cluster.AffinityPropagation
, andcluster.Birch
. ##10306 by Jonathan Siebert. - Changed ValueError exception raised in
model_selection.ParameterSampler
to a UserWarning for case where the class is instantiated with a greater value ofn_iter
than the total space of parameters in the parameter grid.n_iter
now acts as an upper bound on iterations. ##10982 by Juliet Lawton - Invalid input for
model_selection.ParameterGrid
now raises TypeError. #10928 by Solutus Immensus utils.check_array
andutils.check_X_y
now haveaccept_large_sparse
to control whether scipy.sparse matrices with 64-bit indices should be rejected. #11327 by Karan Dhingra and Joel Nothman.
Preprocessing
- In
preprocessing.FunctionTransformer
, the default ofvalidate
will be fromTrue
toFalse
in 0.22. #10655 by Guillaume Lemaitre.
Changes to estimator checks¶
These changes mostly affect library developers.
- Allow tests in
utils.estimator_checks.check_estimator
to test functions that accept pairwise data. #9701 by Kyle Johnson - Allow
check_estimator
to check that there is no private settings apart from parameters during estimator initialization. #9378 by Herilalaina Rakotoarison - Add
check_methods_subset_invariance
tocheck_estimator
, which checks that estimator methods are invariant if applied to a data subset. #10420 by Jonathan Ohayon - Add tests in
utils.estimator_checks.check_estimator
to check that an estimator can handle read-only memmap input data. #10663 by Arthur Mensch and Loïc Estève. check_sample_weights_pandas_series
now uses 8 rather than 6 samples to accommodate for the default number of clusters incluster.KMeans
. #10933 by Johannes Hansen.
Version 0.19.1¶
October 23, 2017
This is a bug-fix release with some minor documentation improvements and enhancements to features released in 0.19.0.
Note there may be minor differences in TSNE output in this release (due to #9623), in the case where multiple samples have equal distance to some sample.
Changelog¶
API changes¶
- Reverted the addition of
metrics.ndcg_score
andmetrics.dcg_score
which had been merged into version 0.19.0 by error. The implementations were broken and undocumented. return_train_score
which was added tomodel_selection.GridSearchCV
,model_selection.RandomizedSearchCV
andmodel_selection.cross_validate
in version 0.19.0 will be changing its default value from True to False in version 0.21. We found that calculating training score could have a great effect on cross validation runtime in some cases. Users should explicitly setreturn_train_score
to False if prediction or scoring functions are slow, resulting in a deleterious effect on CV runtime, or to True if they wish to use the calculated scores. #9677 by Kumar Ashutosh and Joel Nothman.correlation_models
andregression_models
from the legacy gaussian processes implementation have been belatedly deprecated. #9717 by Kumar Ashutosh.
Bug fixes¶
- Avoid integer overflows in
metrics.matthews_corrcoef
. #9693 by Sam Steingold. - Fixed a bug in the objective function for
manifold.TSNE
(both exact and with the Barnes-Hut approximation) whenn_components >= 3
. #9711 by @goncalo-rodrigues. - Fix regression in
model_selection.cross_val_predict
where it raised an error withmethod='predict_proba'
for some probabilistic classifiers. #9641 by James Bourbeau. - Fixed a bug where
datasets.make_classification
modified its inputweights
. #9865 by Sachin Kelkar. model_selection.StratifiedShuffleSplit
now works with multioutput multiclass or multilabel data with more than 1000 columns. #9922 by Charlie Brummitt.- Fixed a bug with nested and conditional parameter setting, e.g. setting a pipeline step and its parameter at the same time. #9945 by Andreas Müller and Joel Nothman.
Regressions in 0.19.0 fixed in 0.19.1:
- Fixed a bug where parallelised prediction in random forests was not thread-safe and could (rarely) result in arbitrary errors. #9830 by Joel Nothman.
- Fix regression in
model_selection.cross_val_predict
where it no longer acceptedX
as a list. #9600 by Rasul Kerimov. - Fixed handling of
cross_val_predict
for binary classification withmethod='decision_function'
. #9593 by Reiichiro Nakano and core devs. - Fix regression in
pipeline.Pipeline
where it no longer acceptedsteps
as a tuple. #9604 by Joris Van den Bossche. - Fix bug where
n_iter
was not properly deprecated, leavingn_iter
unavailable for interim use inlinear_model.SGDClassifier
,linear_model.SGDRegressor
,linear_model.PassiveAggressiveClassifier
,linear_model.PassiveAggressiveRegressor
andlinear_model.Perceptron
. #9558 by Andreas Müller. - Dataset fetchers make sure temporary files are closed before removing them, which caused errors on Windows. #9847 by Joan Massich.
- Fixed a regression in
manifold.TSNE
where it no longer supported metrics other than ‘euclidean’ and ‘precomputed’. #9623 by Oli Blum.
Enhancements¶
- Our test suite and
utils.estimator_checks.check_estimators
can now be run without Nose installed. #9697 by Joan Massich. - To improve usability of version 0.19’s
pipeline.Pipeline
caching,memory
now allowsjoblib.Memory
instances. This make use of the newutils.validation.check_memory
helper. issue:9584 by Kumar Ashutosh - Some fixes to examples: #9750, #9788, #9815
- Made a FutureWarning in SGD-based estimators less verbose. #9802 by Vrishank Bhardwaj.
Code and Documentation Contributors¶
With thanks to:
Joel Nothman, Loic Esteve, Andreas Mueller, Kumar Ashutosh, Vrishank Bhardwaj, Hanmin Qin, Rasul Kerimov, James Bourbeau, Nagarjuna Kumar, Nathaniel Saul, Olivier Grisel, Roman Yurchak, Reiichiro Nakano, Sachin Kelkar, Sam Steingold, Yaroslav Halchenko, diegodlh, felix, goncalo-rodrigues, jkleint, oliblum90, pasbi, Anthony Gitter, Ben Lawson, Charlie Brummitt, Didi Bar-Zev, Gael Varoquaux, Joan Massich, Joris Van den Bossche, nielsenmarkus11
Version 0.19¶
August 12, 2017
Highlights¶
We are excited to release a number of great new features including
neighbors.LocalOutlierFactor
for anomaly detection,
preprocessing.QuantileTransformer
for robust feature transformation,
and the multioutput.ClassifierChain
meta-estimator to simply account
for dependencies between classes in multilabel problems. We have some new
algorithms in existing estimators, such as multiplicative update in
decomposition.NMF
and multinomial
linear_model.LogisticRegression
with L1 loss (use solver='saga'
).
Cross validation is now able to return the results from multiple metric
evaluations. The new model_selection.cross_validate
can return many
scores on the test data as well as training set performance and timings, and we
have extended the scoring
and refit
parameters for grid/randomized
search to handle multiple metrics.
You can also learn faster. For instance, the new option to cache
transformations in pipeline.Pipeline
makes grid
search over pipelines including slow transformations much more efficient. And
you can predict faster: if you’re sure you know what you’re doing, you can turn
off validating that the input is finite using config_context
.
We’ve made some important fixes too. We’ve fixed a longstanding implementation
error in metrics.average_precision_score
, so please be cautious with
prior results reported from that function. A number of errors in the
manifold.TSNE
implementation have been fixed, particularly in the
default Barnes-Hut approximation. semi_supervised.LabelSpreading
and
semi_supervised.LabelPropagation
have had substantial fixes.
LabelPropagation was previously broken. LabelSpreading should now correctly
respect its alpha parameter.
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.
cluster.KMeans
with sparse X and initial centroids given (bug fix)cross_decomposition.PLSRegression
withscale=True
(bug fix)ensemble.GradientBoostingClassifier
andensemble.GradientBoostingRegressor
wheremin_impurity_split
is used (bug fix)- gradient boosting
loss='quantile'
(bug fix) ensemble.IsolationForest
(bug fix)feature_selection.SelectFdr
(bug fix)linear_model.RANSACRegressor
(bug fix)linear_model.LassoLars
(bug fix)linear_model.LassoLarsIC
(bug fix)manifold.TSNE
(bug fix)neighbors.NearestCentroid
(bug fix)semi_supervised.LabelSpreading
(bug fix)semi_supervised.LabelPropagation
(bug fix)- tree based models where
min_weight_fraction_leaf
is used (enhancement) model_selection.StratifiedKFold
withshuffle=True
(this change, due to #7823 was not mentioned in the release notes at the time)
Details are listed in the changelog below.
(While we are trying to better inform users by providing this information, we cannot assure that this list is complete.)
Changelog¶
New features¶
Classifiers and regressors
- Added
multioutput.ClassifierChain
for multi-label classification. By Adam Kleczewski. - Added solver
'saga'
that implements the improved version of Stochastic Average Gradient, inlinear_model.LogisticRegression
andlinear_model.Ridge
. It allows the use of L1 penalty with multinomial logistic loss, and behaves marginally better than ‘sag’ during the first epochs of ridge and logistic regression. #8446 by Arthur Mensch.
Other estimators
- Added the
neighbors.LocalOutlierFactor
class for anomaly detection based on nearest neighbors. #5279 by Nicolas Goix and Alexandre Gramfort. - Added
preprocessing.QuantileTransformer
class andpreprocessing.quantile_transform
function for features normalization based on quantiles. #8363 by Denis Engemann, Guillaume Lemaitre, Olivier Grisel, Raghav RV, Thierry Guillemot, and Gael Varoquaux. - The new solver
'mu'
implements a Multiplicate Update indecomposition.NMF
, allowing the optimization of all beta-divergences, including the Frobenius norm, the generalized Kullback-Leibler divergence and the Itakura-Saito divergence. #5295 by Tom Dupre la Tour.
Model selection and evaluation
model_selection.GridSearchCV
andmodel_selection.RandomizedSearchCV
now support simultaneous evaluation of multiple metrics. Refer to the Specifying multiple metrics for evaluation section of the user guide for more information. #7388 by Raghav RV- Added the
model_selection.cross_validate
which allows evaluation of multiple metrics. This function returns a dict with more useful information from cross-validation such as the train scores, fit times and score times. Refer to The cross_validate function and multiple metric evaluation section of the userguide for more information. #7388 by Raghav RV - Added
metrics.mean_squared_log_error
, which computes the mean square error of the logarithmic transformation of targets, particularly useful for targets with an exponential trend. #7655 by Karan Desai. - Added
metrics.dcg_score
andmetrics.ndcg_score
, which compute Discounted cumulative gain (DCG) and Normalized discounted cumulative gain (NDCG). #7739 by David Gasquez. - Added the
model_selection.RepeatedKFold
andmodel_selection.RepeatedStratifiedKFold
. #8120 by Neeraj Gangwar.
Miscellaneous
- Validation that input data contains no NaN or inf can now be suppressed
using
config_context
, at your own risk. This will save on runtime, and may be particularly useful for prediction time. #7548 by Joel Nothman. - Added a test to ensure parameter listing in docstrings match the function/class signature. #9206 by Alexandre Gramfort and Raghav RV.
Enhancements¶
Trees and ensembles
- The
min_weight_fraction_leaf
constraint in tree construction is now more efficient, taking a fast path to declare a node a leaf if its weight is less than 2 * the minimum. Note that the constructed tree will be different from previous versions wheremin_weight_fraction_leaf
is used. #7441 by Nelson Liu. ensemble.GradientBoostingClassifier
andensemble.GradientBoostingRegressor
now support sparse input for prediction. #6101 by Ibraim Ganiev.ensemble.VotingClassifier
now allows changing estimators by usingensemble.VotingClassifier.set_params
. An estimator can also be removed by setting it toNone
. #7674 by Yichuan Liu.tree.export_graphviz
now shows configurable number of decimal places. #8698 by Guillaume Lemaitre.- Added
flatten_transform
parameter toensemble.VotingClassifier
to change output shape of transform method to 2 dimensional. #7794 by Ibraim Ganiev and Herilalaina Rakotoarison.
Linear, kernelized and related models
linear_model.SGDClassifier
,linear_model.SGDRegressor
,linear_model.PassiveAggressiveClassifier
,linear_model.PassiveAggressiveRegressor
andlinear_model.Perceptron
now exposemax_iter
andtol
parameters, to handle convergence more precisely.n_iter
parameter is deprecated, and the fitted estimator exposes an_iter_
attribute, with actual number of iterations before convergence. #5036 by Tom Dupre la Tour.- Added
average
parameter to perform weight averaging inlinear_model.PassiveAggressiveClassifier
. #4939 by Andrea Esuli. linear_model.RANSACRegressor
no longer throws an error when callingfit
if no inliers are found in its first iteration. Furthermore, causes of skipped iterations are tracked in newly added attributes,n_skips_*
. #7914 by Michael Horrell.- In
gaussian_process.GaussianProcessRegressor
, methodpredict
is a lot faster withreturn_std=True
. #8591 by Hadrien Bertrand. - Added
return_std
topredict
method oflinear_model.ARDRegression
andlinear_model.BayesianRidge
. #7838 by Sergey Feldman. - Memory usage enhancements: Prevent cast from float32 to float64 in:
linear_model.MultiTaskElasticNet
;linear_model.LogisticRegression
when using newton-cg solver; andlinear_model.Ridge
when using svd, sparse_cg, cholesky or lsqr solvers. #8835, #8061 by Joan Massich and Nicolas Cordier and Thierry Guillemot.
Other predictors
- Custom metrics for the
neighbors
binary trees now have fewer constraints: they must take two 1d-arrays and return a float. #6288 by Jake Vanderplas. algorithm='auto
inneighbors
estimators now chooses the most appropriate algorithm for all input types and metrics. #9145 by Herilalaina Rakotoarison and Reddy Chinthala.
Decomposition, manifold learning and clustering
cluster.MiniBatchKMeans
andcluster.KMeans
now use significantly less memory when assigning data points to their nearest cluster center. #7721 by Jon Crall.decomposition.PCA
,decomposition.IncrementalPCA
anddecomposition.TruncatedSVD
now expose the singular values from the underlying SVD. They are stored in the attributesingular_values_
, like indecomposition.IncrementalPCA
. #7685 by Tommy Löfstedtdecomposition.NMF
now faster whenbeta_loss=0
. #9277 by @hongkahjun.- Memory improvements for method
barnes_hut
inmanifold.TSNE
#7089 by Thomas Moreau and Olivier Grisel. - Optimization schedule improvements for Barnes-Hut
manifold.TSNE
so the results are closer to the one from the reference implementation lvdmaaten/bhtsne by Thomas Moreau and Olivier Grisel. - Memory usage enhancements: Prevent cast from float32 to float64 in
decomposition.PCA
anddecomposition.randomized_svd_low_rank
. #9067 by Raghav RV.
Preprocessing and feature selection
- Added
norm_order
parameter tofeature_selection.SelectFromModel
to enable selection of the norm order whencoef_
is more than 1D. #6181 by Antoine Wendlinger. - Added ability to use sparse matrices in
feature_selection.f_regression
withcenter=True
. #8065 by Daniel LeJeune. - Small performance improvement to n-gram creation in
feature_extraction.text
by binding methods for loops and special-casing unigrams. #7567 by Jaye Doepke - Relax assumption on the data for the
kernel_approximation.SkewedChi2Sampler
. Since the Skewed-Chi2 kernel is defined on the open interval \((-skewedness; +\infty)^d\), the transform function should not check whetherX < 0
but whetherX < -self.skewedness
. #7573 by Romain Brault. - Made default kernel parameters kernel-dependent in
kernel_approximation.Nystroem
. #5229 by Saurabh Bansod and Andreas Müller.
Model evaluation and meta-estimators
pipeline.Pipeline
is now able to cache transformers within a pipeline by using thememory
constructor parameter. #7990 by Guillaume Lemaitre.pipeline.Pipeline
steps can now be accessed as attributes of itsnamed_steps
attribute. #8586 by Herilalaina Rakotoarison.- Added
sample_weight
parameter topipeline.Pipeline.score
. #7723 by Mikhail Korobov. - Added ability to set
n_jobs
parameter topipeline.make_union
. ATypeError
will be raised for any other kwargs. #8028 by Alexander Booth. model_selection.GridSearchCV
,model_selection.RandomizedSearchCV
andmodel_selection.cross_val_score
now allow estimators with callable kernels which were previously prohibited. #8005 by Andreas Müller .model_selection.cross_val_predict
now returns output of the correct shape for all values of the argumentmethod
. #7863 by Aman Dalmia.- Added
shuffle
andrandom_state
parameters to shuffle training data before taking prefixes of it based on training sizes inmodel_selection.learning_curve
. #7506 by Narine Kokhlikyan. model_selection.StratifiedShuffleSplit
now works with multioutput multiclass (or multilabel) data. #9044 by Vlad Niculae.- Speed improvements to
model_selection.StratifiedShuffleSplit
. #5991 by Arthur Mensch and Joel Nothman. - Add
shuffle
parameter tomodel_selection.train_test_split
. #8845 by themrmax multioutput.MultiOutputRegressor
andmultioutput.MultiOutputClassifier
now support online learning usingpartial_fit
. :issue: 8053 by Peng Yu.- Add
max_train_size
parameter tomodel_selection.TimeSeriesSplit
#8282 by Aman Dalmia. - More clustering metrics are now available through
metrics.get_scorer
andscoring
parameters. #8117 by Raghav RV. - A scorer based on
metrics.explained_variance_score
is also available. #9259 by Hanmin Qin.
Metrics
metrics.matthews_corrcoef
now support multiclass classification. #8094 by Jon Crall.- Add
sample_weight
parameter tometrics.cohen_kappa_score
. #8335 by Victor Poughon.
Miscellaneous
utils.check_estimator
now attempts to ensure that methods transform, predict, etc. do not set attributes on the estimator. #7533 by Ekaterina Krivich.- Added type checking to the
accept_sparse
parameter inutils.validation
methods. This parameter now accepts only boolean, string, or list/tuple of strings.accept_sparse=None
is deprecated and should be replaced byaccept_sparse=False
. #7880 by Josh Karnofsky. - Make it possible to load a chunk of an svmlight formatted file by
passing a range of bytes to
datasets.load_svmlight_file
. #935 by Olivier Grisel. dummy.DummyClassifier
anddummy.DummyRegressor
now accept non-finite features. #8931 by @Attractadore.
Bug fixes¶
Trees and ensembles
- Fixed a memory leak in trees when using trees with
criterion='mae'
. #8002 by Raghav RV. - Fixed a bug where
ensemble.IsolationForest
uses an an incorrect formula for the average path length #8549 by Peter Wang. - Fixed a bug where
ensemble.AdaBoostClassifier
throwsZeroDivisionError
while fitting data with single class labels. #7501 by Dominik Krzeminski. - Fixed a bug in
ensemble.GradientBoostingClassifier
andensemble.GradientBoostingRegressor
where a float being compared to0.0
using==
caused a divide by zero error. #7970 by He Chen. - Fix a bug where
ensemble.GradientBoostingClassifier
andensemble.GradientBoostingRegressor
ignored themin_impurity_split
parameter. #8006 by Sebastian Pölsterl. - Fixed
oob_score
inensemble.BaggingClassifier
. #8936 by Michael Lewis - Fixed excessive memory usage in prediction for random forests estimators. #8672 by Mike Benfield.
- Fixed a bug where
sample_weight
as a list broke random forests in Python 2 #8068 by @xor. - Fixed a bug where
ensemble.IsolationForest
fails whenmax_features
is less than 1. #5732 by Ishank Gulati. - Fix a bug where gradient boosting with
loss='quantile'
computed negative errors for negative values ofytrue - ypred
leading to wrong values when calling__call__
. #8087 by Alexis Mignon - Fix a bug where
ensemble.VotingClassifier
raises an error when a numpy array is passed in for weights. #7983 by Vincent Pham. - Fixed a bug where
tree.export_graphviz
raised an error when the length of features_names does not match n_features in the decision tree. #8512 by Li Li.
Linear, kernelized and related models
- Fixed a bug where
linear_model.RANSACRegressor.fit
may run untilmax_iter
if it finds a large inlier group early. #8251 by @aivision2020. - Fixed a bug where
naive_bayes.MultinomialNB
andnaive_bayes.BernoulliNB
failed whenalpha=0
. #5814 by Yichuan Liu and Herilalaina Rakotoarison. - Fixed a bug where
linear_model.LassoLars
does not give the same result as the LassoLars implementation available in R (lars library). #7849 by Jair Montoya Martinez. - Fixed a bug in
linear_model.RandomizedLasso
,linear_model.Lars
,linear_model.LassoLars
,linear_model.LarsCV
andlinear_model.LassoLarsCV
, where the parameterprecompute
was not used consistently across classes, and some values proposed in the docstring could raise errors. #5359 by Tom Dupre la Tour. - Fix inconsistent results between
linear_model.RidgeCV
andlinear_model.Ridge
when usingnormalize=True
. #9302 by Alexandre Gramfort. - Fix a bug where
linear_model.LassoLars.fit
sometimes leftcoef_
as a list, rather than an ndarray. #8160 by CJ Carey. - Fix
linear_model.BayesianRidge.fit
to return ridge parameteralpha_
andlambda_
consistent with calculated coefficientscoef_
andintercept_
. #8224 by Peter Gedeck. - Fixed a bug in
svm.OneClassSVM
where it returned floats instead of integer classes. #8676 by Vathsala Achar. - Fix AIC/BIC criterion computation in
linear_model.LassoLarsIC
. #9022 by Alexandre Gramfort and Mehmet Basbug. - Fixed a memory leak in our LibLinear implementation. #9024 by Sergei Lebedev
- Fix bug where stratified CV splitters did not work with
linear_model.LassoCV
. #8973 by Paulo Haddad. - Fixed a bug in
gaussian_process.GaussianProcessRegressor
when the standard deviation and covariance predicted without fit would fail with a unmeaningful error by default. #6573 by Quazi Marufur Rahman and Manoj Kumar.
Other predictors
- Fix
semi_supervised.BaseLabelPropagation
to correctly implementLabelPropagation
andLabelSpreading
as done in the referenced papers. #9239 by Andre Ambrosio Boechat, Utkarsh Upadhyay, and Joel Nothman.
Decomposition, manifold learning and clustering
- Fixed the implementation of
manifold.TSNE
: early_exageration
parameter had no effect and is now used for the first 250 optimization iterations.- Fixed the
AssertionError: Tree consistency failed
exception reported in #8992. - Improve the learning schedule to match the one from the reference implementation lvdmaaten/bhtsne. by Thomas Moreau and Olivier Grisel.
- Fix a bug in
decomposition.LatentDirichletAllocation
where theperplexity
method was returning incorrect results because thetransform
method returns normalized document topic distributions as of version 0.18. #7954 by Gary Foreman. - Fix output shape and bugs with n_jobs > 1 in
decomposition.SparseCoder
transform anddecomposition.sparse_encode
for one-dimensional data and one component. This also impacts the output shape ofdecomposition.DictionaryLearning
. #8086 by Andreas Müller. - Fixed the implementation of
explained_variance_
indecomposition.PCA
,decomposition.RandomizedPCA
anddecomposition.IncrementalPCA
. #9105 by Hanmin Qin. - Fixed the implementation of
noise_variance_
indecomposition.PCA
. #9108 by Hanmin Qin. - Fixed a bug where
cluster.DBSCAN
gives incorrect result when input is a precomputed sparse matrix with initial rows all zero. #8306 by Akshay Gupta - Fix a bug regarding fitting
cluster.KMeans
with a sparse array X and initial centroids, where X’s means were unnecessarily being subtracted from the centroids. #7872 by Josh Karnofsky. - Fixes to the input validation in
covariance.EllipticEnvelope
. #8086 by Andreas Müller. - Fixed a bug in
covariance.MinCovDet
where inputting data that produced a singular covariance matrix would cause the helper method_c_step
to throw an exception. #3367 by Jeremy Steward - Fixed a bug in
manifold.TSNE
affecting convergence of the gradient descent. #8768 by David DeTomaso. - Fixed a bug in
manifold.TSNE
where it stored the incorrectkl_divergence_
. #6507 by Sebastian Saeger. - Fixed improper scaling in
cross_decomposition.PLSRegression
withscale=True
. #7819 by jayzed82. cluster.bicluster.SpectralCoclustering
andcluster.bicluster.SpectralBiclustering
fit
method conforms with API by acceptingy
and returning the object. #6126, #7814 by Laurent Direr and Maniteja Nandana.- Fix bug where
mixture
sample
methods did not return as many samples as requested. #7702 by Levi John Wolf. - Fixed the shrinkage implementation in
neighbors.NearestCentroid
. #9219 by Hanmin Qin.
Preprocessing and feature selection
- For sparse matrices,
preprocessing.normalize
withreturn_norm=True
will now raise aNotImplementedError
with ‘l1’ or ‘l2’ norm and with norm ‘max’ the norms returned will be the same as for dense matrices. #7771 by Ang Lu. - Fix a bug where
feature_selection.SelectFdr
did not exactly implement Benjamini-Hochberg procedure. It formerly may have selected fewer features than it should. #7490 by Peng Meng. - Fixed a bug where
linear_model.RandomizedLasso
andlinear_model.RandomizedLogisticRegression
breaks for sparse input. #8259 by Aman Dalmia. - Fix a bug where
feature_extraction.FeatureHasher
mandatorily applied a sparse random projection to the hashed features, preventing the use offeature_extraction.text.HashingVectorizer
in a pipeline withfeature_extraction.text.TfidfTransformer
. #7565 by Roman Yurchak. - Fix a bug where
feature_selection.mutual_info_regression
did not correctly usen_neighbors
. #8181 by Guillaume Lemaitre.
Model evaluation and meta-estimators
- Fixed a bug where
model_selection.BaseSearchCV.inverse_transform
returnsself.best_estimator_.transform()
instead ofself.best_estimator_.inverse_transform()
. #8344 by Akshay Gupta and Rasmus Eriksson. - Added
classes_
attribute tomodel_selection.GridSearchCV
,model_selection.RandomizedSearchCV
,grid_search.GridSearchCV
, andgrid_search.RandomizedSearchCV
that matches theclasses_
attribute ofbest_estimator_
. #7661 and #8295 by Alyssa Batula, Dylan Werner-Meier, and Stephen Hoover. - Fixed a bug where
model_selection.validation_curve
reused the same estimator for each parameter value. #7365 by Aleksandr Sandrovskii. model_selection.permutation_test_score
now works with Pandas types. #5697 by Stijn Tonk.- Several fixes to input validation in
multiclass.OutputCodeClassifier
#8086 by Andreas Müller. multiclass.OneVsOneClassifier
’spartial_fit
now ensures all classes are provided up-front. #6250 by Asish Panda.- Fix
multioutput.MultiOutputClassifier.predict_proba
to return a list of 2d arrays, rather than a 3d array. In the case where different target columns had different numbers of classes, aValueError
would be raised on trying to stack matrices with different dimensions. #8093 by Peter Bull. - Cross validation now works with Pandas datatypes that that have a read-only index. #9507 by Loic Esteve.
Metrics
metrics.average_precision_score
no longer linearly interpolates between operating points, and instead weighs precisions by the change in recall since the last operating point, as per the Wikipedia entry. (#7356). By Nick Dingwall and Gael Varoquaux.- Fix a bug in
metrics.classification._check_targets
which would return'binary'
ify_true
andy_pred
were both'binary'
but the union ofy_true
andy_pred
was'multiclass'
. #8377 by Loic Esteve. - Fixed an integer overflow bug in
metrics.confusion_matrix
and hencemetrics.cohen_kappa_score
. #8354, #7929 by Joel Nothman and Jon Crall. - Fixed passing of
gamma
parameter to thechi2
kernel inmetrics.pairwise.pairwise_kernels
#5211 by Nick Rhinehart, Saurabh Bansod and Andreas Müller.
Miscellaneous
- Fixed a bug when
datasets.make_classification
fails when generating more than 30 features. #8159 by Herilalaina Rakotoarison. - Fixed a bug where
datasets.make_moons
gives an incorrect result whenn_samples
is odd. #8198 by Josh Levy. - Some
fetch_
functions indatasets
were ignoring thedownload_if_missing
keyword. #7944 by Ralf Gommers. - Fix estimators to accept a
sample_weight
parameter of typepandas.Series
in theirfit
function. #7825 by Kathleen Chen. - Fix a bug in cases where
numpy.cumsum
may be numerically unstable, raising an exception if instability is identified. #7376 and #7331 by Joel Nothman and @yangarbiter. - Fix a bug where
base.BaseEstimator.__getstate__
obstructed pickling customizations of child-classes, when used in a multiple inheritance context. #8316 by Holger Peters. - Update Sphinx-Gallery from 0.1.4 to 0.1.7 for resolving links in documentation build with Sphinx>1.5 #8010, #7986 by Oscar Najera
- Add
data_home
parameter tosklearn.datasets.fetch_kddcup99
. #9289 by Loic Esteve. - Fix dataset loaders using Python 3 version of makedirs to also work in Python 2. #9284 by Sebastin Santy.
- Several minor issues were fixed with thanks to the alerts of [lgtm.com](http://lgtm.com). #9278 by Jean Helie, among others.
API changes summary¶
Trees and ensembles
- Gradient boosting base models are no longer estimators. By Andreas Müller.
- All tree based estimators now accept a
min_impurity_decrease
parameter in lieu of themin_impurity_split
, which is now deprecated. Themin_impurity_decrease
helps stop splitting the nodes in which the weighted impurity decrease from splitting is no longer at leastmin_impurity_decrease
. #8449 by Raghav RV.
Linear, kernelized and related models
n_iter
parameter is deprecated inlinear_model.SGDClassifier
,linear_model.SGDRegressor
,linear_model.PassiveAggressiveClassifier
,linear_model.PassiveAggressiveRegressor
andlinear_model.Perceptron
. By Tom Dupre la Tour.
Other predictors
neighbors.LSHForest
has been deprecated and will be removed in 0.21 due to poor performance. #9078 by Laurent Direr.neighbors.NearestCentroid
no longer purports to supportmetric='precomputed'
which now raises an error. #8515 by Sergul Aydore.- The
alpha
parameter ofsemi_supervised.LabelPropagation
now has no effect and is deprecated to be removed in 0.21. #9239 by Andre Ambrosio Boechat, Utkarsh Upadhyay, and Joel Nothman.
Decomposition, manifold learning and clustering
- Deprecate the
doc_topic_distr
argument of theperplexity
method indecomposition.LatentDirichletAllocation
because the user no longer has access to the unnormalized document topic distribution needed for the perplexity calculation. #7954 by Gary Foreman. - The
n_topics
parameter ofdecomposition.LatentDirichletAllocation
has been renamed ton_components
and will be removed in version 0.21. #8922 by @Attractadore. decomposition.SparsePCA.transform
’sridge_alpha
parameter is deprecated in preference for class parameter. #8137 by Naoya Kanai.cluster.DBSCAN
now has ametric_params
parameter. #8139 by Naoya Kanai.
Preprocessing and feature selection
feature_selection.SelectFromModel
now has apartial_fit
method only if the underlying estimator does. By Andreas Müller.feature_selection.SelectFromModel
now validates thethreshold
parameter and sets thethreshold_
attribute during the call tofit
, and no longer during the call totransform`
. By Andreas Müller.- The
non_negative
parameter infeature_extraction.FeatureHasher
has been deprecated, and replaced with a more principled alternative,alternate_sign
. #7565 by Roman Yurchak. linear_model.RandomizedLogisticRegression
, andlinear_model.RandomizedLasso
have been deprecated and will be removed in version 0.21. #8995 by Ramana.S.
Model evaluation and meta-estimators
- Deprecate the
fit_params
constructor input to themodel_selection.GridSearchCV
andmodel_selection.RandomizedSearchCV
in favor of passing keyword parameters to thefit
methods of those classes. Data-dependent parameters needed for model training should be passed as keyword arguments tofit
, and conforming to this convention will allow the hyperparameter selection classes to be used with tools such asmodel_selection.cross_val_predict
. #2879 by Stephen Hoover. - In version 0.21, the default behavior of splitters that use the
test_size
andtrain_size
parameter will change, such that specifyingtrain_size
alone will causetest_size
to be the remainder. #7459 by Nelson Liu. multiclass.OneVsRestClassifier
now haspartial_fit
,decision_function
andpredict_proba
methods only when the underlying estimator does. #7812 by Andreas Müller and Mikhail Korobov.multiclass.OneVsRestClassifier
now has apartial_fit
method only if the underlying estimator does. By Andreas Müller.- The
decision_function
output shape for binary classification inmulticlass.OneVsRestClassifier
andmulticlass.OneVsOneClassifier
is now(n_samples,)
to conform to scikit-learn conventions. #9100 by Andreas Müller. - The
multioutput.MultiOutputClassifier.predict_proba
function used to return a 3d array (n_samples
,n_classes
,n_outputs
). In the case where different target columns had different numbers of classes, aValueError
would be raised on trying to stack matrices with different dimensions. This function now returns a list of arrays where the length of the list isn_outputs
, and each array is (n_samples
,n_classes
) for that particular output. #8093 by Peter Bull. - Replace attribute
named_steps
dict
toutils.Bunch
inpipeline.Pipeline
to enable tab completion in interactive environment. In the case conflict value onnamed_steps
anddict
attribute,dict
behavior will be prioritized. #8481 by Herilalaina Rakotoarison.
Miscellaneous
Deprecate the
y
parameter intransform
andinverse_transform
. The method should not accepty
parameter, as it’s used at the prediction time. #8174 by Tahar Zanouda, Alexandre Gramfort and Raghav RV.SciPy >= 0.13.3 and NumPy >= 1.8.2 are now the minimum supported versions for scikit-learn. The following backported functions in
utils
have been removed or deprecated accordingly. #8854 and #8874 by Naoya KanaiThe
store_covariances
andcovariances_
parameters ofdiscriminant_analysis.QuadraticDiscriminantAnalysis
has been renamed tostore_covariance
andcovariance_
to be consistent with the corresponding parameter names of thediscriminant_analysis.LinearDiscriminantAnalysis
. They will be removed in version 0.21. #7998 by JiachengRemoved in 0.19:
utils.fixes.argpartition
utils.fixes.array_equal
utils.fixes.astype
utils.fixes.bincount
utils.fixes.expit
utils.fixes.frombuffer_empty
utils.fixes.in1d
utils.fixes.norm
utils.fixes.rankdata
utils.fixes.safe_copy
Deprecated in 0.19, to be removed in 0.21:
utils.arpack.eigs
utils.arpack.eigsh
utils.arpack.svds
utils.extmath.fast_dot
utils.extmath.logsumexp
utils.extmath.norm
utils.extmath.pinvh
utils.graph.graph_laplacian
utils.random.choice
utils.sparsetools.connected_components
utils.stats.rankdata
Estimators with both methods
decision_function
andpredict_proba
are now required to have a monotonic relation between them. The methodcheck_decision_proba_consistency
has been added in utils.estimator_checks to check their consistency. #7578 by Shubham BhardwajAll checks in
utils.estimator_checks
, in particularutils.estimator_checks.check_estimator
now accept estimator instances. Most other checks do not accept estimator classes any more. #9019 by Andreas Müller.Ensure that estimators’ attributes ending with
_
are not set in the constructor but only in thefit
method. Most notably, ensemble estimators (deriving fromensemble.BaseEnsemble
) now only haveself.estimators_
available afterfit
. #7464 by Lars Buitinck and Loic Esteve.
Code and Documentation Contributors¶
Thanks to everyone who has contributed to the maintenance and improvement of the project since version 0.18, including:
Joel Nothman, Loic Esteve, Andreas Mueller, Guillaume Lemaitre, Olivier Grisel, Hanmin Qin, Raghav RV, Alexandre Gramfort, themrmax, Aman Dalmia, Gael Varoquaux, Naoya Kanai, Tom Dupré la Tour, Rishikesh, Nelson Liu, Taehoon Lee, Nelle Varoquaux, Aashil, Mikhail Korobov, Sebastin Santy, Joan Massich, Roman Yurchak, RAKOTOARISON Herilalaina, Thierry Guillemot, Alexandre Abadie, Carol Willing, Balakumaran Manoharan, Josh Karnofsky, Vlad Niculae, Utkarsh Upadhyay, Dmitry Petrov, Minghui Liu, Srivatsan, Vincent Pham, Albert Thomas, Jake VanderPlas, Attractadore, JC Liu, alexandercbooth, chkoar, Óscar Nájera, Aarshay Jain, Kyle Gilliam, Ramana Subramanyam, CJ Carey, Clement Joudet, David Robles, He Chen, Joris Van den Bossche, Karan Desai, Katie Luangkote, Leland McInnes, Maniteja Nandana, Michele Lacchia, Sergei Lebedev, Shubham Bhardwaj, akshay0724, omtcyfz, rickiepark, waterponey, Vathsala Achar, jbDelafosse, Ralf Gommers, Ekaterina Krivich, Vivek Kumar, Ishank Gulati, Dave Elliott, ldirer, Reiichiro Nakano, Levi John Wolf, Mathieu Blondel, Sid Kapur, Dougal J. Sutherland, midinas, mikebenfield, Sourav Singh, Aseem Bansal, Ibraim Ganiev, Stephen Hoover, AishwaryaRK, Steven C. Howell, Gary Foreman, Neeraj Gangwar, Tahar, Jon Crall, dokato, Kathy Chen, ferria, Thomas Moreau, Charlie Brummitt, Nicolas Goix, Adam Kleczewski, Sam Shleifer, Nikita Singh, Basil Beirouti, Giorgio Patrini, Manoj Kumar, Rafael Possas, James Bourbeau, James A. Bednar, Janine Harper, Jaye, Jean Helie, Jeremy Steward, Artsiom, John Wei, Jonathan LIgo, Jonathan Rahn, seanpwilliams, Arthur Mensch, Josh Levy, Julian Kuhlmann, Julien Aubert, Jörn Hees, Kai, shivamgargsya, Kat Hempstalk, Kaushik Lakshmikanth, Kennedy, Kenneth Lyons, Kenneth Myers, Kevin Yap, Kirill Bobyrev, Konstantin Podshumok, Arthur Imbert, Lee Murray, toastedcornflakes, Lera, Li Li, Arthur Douillard, Mainak Jas, tobycheese, Manraj Singh, Manvendra Singh, Marc Meketon, MarcoFalke, Matthew Brett, Matthias Gilch, Mehul Ahuja, Melanie Goetz, Meng, Peng, Michael Dezube, Michal Baumgartner, vibrantabhi19, Artem Golubin, Milen Paskov, Antonin Carette, Morikko, MrMjauh, NALEPA Emmanuel, Namiya, Antoine Wendlinger, Narine Kokhlikyan, NarineK, Nate Guerin, Angus Williams, Ang Lu, Nicole Vavrova, Nitish Pandey, Okhlopkov Daniil Olegovich, Andy Craze, Om Prakash, Parminder Singh, Patrick Carlson, Patrick Pei, Paul Ganssle, Paulo Haddad, Paweł Lorek, Peng Yu, Pete Bachant, Peter Bull, Peter Csizsek, Peter Wang, Pieter Arthur de Jong, Ping-Yao, Chang, Preston Parry, Puneet Mathur, Quentin Hibon, Andrew Smith, Andrew Jackson, 1kastner, Rameshwar Bhaskaran, Rebecca Bilbro, Remi Rampin, Andrea Esuli, Rob Hall, Robert Bradshaw, Romain Brault, Aman Pratik, Ruifeng Zheng, Russell Smith, Sachin Agarwal, Sailesh Choyal, Samson Tan, Samuël Weber, Sarah Brown, Sebastian Pölsterl, Sebastian Raschka, Sebastian Saeger, Alyssa Batula, Abhyuday Pratap Singh, Sergey Feldman, Sergul Aydore, Sharan Yalburgi, willduan, Siddharth Gupta, Sri Krishna, Almer, Stijn Tonk, Allen Riddell, Theofilos Papapanagiotou, Alison, Alexis Mignon, Tommy Boucher, Tommy Löfstedt, Toshihiro Kamishima, Tyler Folkman, Tyler Lanigan, Alexander Junge, Varun Shenoy, Victor Poughon, Vilhelm von Ehrenheim, Aleksandr Sandrovskii, Alan Yee, Vlasios Vasileiou, Warut Vijitbenjaronk, Yang Zhang, Yaroslav Halchenko, Yichuan Liu, Yuichi Fujikawa, affanv14, aivision2020, xor, andreh7, brady salz, campustrampus, Agamemnon Krasoulis, ditenberg, elena-sharova, filipj8, fukatani, gedeck, guiniol, guoci, hakaa1, hongkahjun, i-am-xhy, jakirkham, jaroslaw-weber, jayzed82, jeroko, jmontoyam, jonathan.striebel, josephsalmon, jschendel, leereeves, martin-hahn, mathurinm, mehak-sachdeva, mlewis1729, mlliou112, mthorrell, ndingwall, nuffe, yangarbiter, plagree, pldtc325, Breno Freitas, Brett Olsen, Brian A. Alfano, Brian Burns, polmauri, Brandon Carter, Charlton Austin, Chayant T15h, Chinmaya Pancholi, Christian Danielsen, Chung Yen, Chyi-Kwei Yau, pravarmahajan, DOHMATOB Elvis, Daniel LeJeune, Daniel Hnyk, Darius Morawiec, David DeTomaso, David Gasquez, David Haberthür, David Heryanto, David Kirkby, David Nicholson, rashchedrin, Deborah Gertrude Digges, Denis Engemann, Devansh D, Dickson, Bob Baxley, Don86, E. Lynch-Klarup, Ed Rogers, Elizabeth Ferriss, Ellen-Co2, Fabian Egli, Fang-Chieh Chou, Bing Tian Dai, Greg Stupp, Grzegorz Szpak, Bertrand Thirion, Hadrien Bertrand, Harizo Rajaona, zxcvbnius, Henry Lin, Holger Peters, Icyblade Dai, Igor Andriushchenko, Ilya, Isaac Laughlin, Iván Vallés, Aurélien Bellet, JPFrancoia, Jacob Schreiber, Asish Mahapatra
Previous Releases¶
- Version 0.18.2
- Version 0.18.1
- Version 0.18
- Version 0.17.1
- Version 0.17
- Version 0.16.1
- Version 0.16
- Version 0.15.2
- Version 0.15.1
- Version 0.15
- Version 0.14
- Version 0.13.1
- Version 0.13
- Version 0.12.1
- Version 0.12
- Version 0.11
- Version 0.10
- Version 0.9
- Version 0.8
- Version 0.7
- Version 0.6
- Version 0.5
- Version 0.4
- Earlier versions