baohan
/
scikit-learn
mirror of https://github.com/scikit-learn/scikit-learn.git
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
27,260 Commits 31 Branches 142 Tags 892 MiB
Commit Graph

315 Commits

Author SHA1 Message Date
Thomas J. Fan ba58f3a693
BUG Fixes FunctionTransformer validation in inverse_transform (#20961) 2021-09-08 11:01:24 +02:00
Thomas J. Fan 4abd9f2d9e
API Implements get_feature_names_out for transformers that support get_feature_names (#18444) 
Co-authored-by: Andreas Mueller <andreas.mueller@columbia.edu>
Co-authored-by: Andreas Mueller <andreasmuellerml@gmail.com>
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
Co-authored-by: Olivier Grisel <olivier.grisel@gmail.com>
Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com>
 2021-09-07 10:56:57 +02:00
Thomas J. Fan f500326a9a CLN Removes unneeded test 2021-09-01 18:13:04 -07:00
Guillaume Lemaitre d6735f4851
FIX accept large Python numeric in OrdinalEncoder (#20727) 2021-08-16 23:12:35 +02:00
Maxwell 238451d55e
FIX StandardScaler.inverse_transform raise error when the input is a 1d array (#19752) 
Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-07-23 20:44:52 +02:00
Maxwell 9580530071
FIX OrdinalEncoder.fit should not raise an error `handle_unknown="use_encoded_value"` (#19906) 
Co-authored-by: Adrin Jalali <adrin.jalali@gmail.com>
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-07-23 18:55:24 +02:00
mlondschien 3a3f1bed10
ENH Allow `sample_weight` in `SplineTransformer.fit` method (#20526) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-07-21 16:36:52 +02:00
Thomas J. Fan 3ae7c76153
STY Enables black with experimental_string_processing=true (#20412) 2021-06-29 09:47:04 +02:00
Thomas J. Fan 383b53fa91
FIX Uses code literals in deprecated to prevent linking (#20410) 
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
 2021-06-28 15:49:19 +02:00
Christian Lorentzen bb2de70a17
ENH add minimal degree support to PolynomialFeatures (#20250) 2021-06-26 13:03:35 +02:00
Thomas J. Fan 82df48934e
MNT Applies black formatting to most of the code base (#18948) 2021-06-17 14:21:09 -04:00
Jérémie du Boisberranger 28bc843d88
MNT deprecate n_input_features_ in PolynomialFeatures (#20240) 2021-06-11 18:20:24 +02:00
mlondschien 778125645f
Allow `n_knots=None` if knots are explicitly specified in `SplineTransformer` (#20191) 
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
 2021-06-07 16:45:22 +02:00
Guillaume Lemaitre 6a562d31e4
ENH improve KernelCenterer documentation and tests (#19901) 
Co-authored-by: Julien Jerphanion <git@jjerphan.xyz>
Co-authored-by: Sylvain Marié <sylvain.marie@schneider-electric.com>
 2021-04-27 17:45:20 +02:00
Andrew Delong a67b284f90
FIX Encoder should accept categories having dtype='S' (#19727) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2021-04-21 17:34:28 -04:00
Thomas J. Fan 004b44d007
FIX OneHotEncoder.fit no longer alters the drop parameter (#19924) 2021-04-20 23:29:02 +02:00
Thomas J. Fan 5efcb10c3e
MAINT Vendors packaging/version.py for pep440 versioning (#19826) 
* MAINT Vendors packaging/version for pep440 versioning

* ENH Uses folder structure of packaging

* ENH Uses fixes parse_version

* ENH Uses packaging name

* MAINT Adds packaging

* BLD Use vendored version [cd build]
 2021-04-19 17:06:38 +02:00
Thomas J. Fan 5d8796b91d
FIX Fixes unknown handling for str dtypes in OrdinalEncoder.transform (#19888) 
* FIX Fixes unknown handling for str X in OrdinalEncoder.transform

* DOC Adds whats new

* DOC Move to 0.24.2

* DOC Adds reasoning in comment
 2021-04-18 17:31:50 +02:00
Jérémie du Boisberranger 684b7d1955
FIX detect near constant feature in StandardScaler and linear models (#19788) 
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
 2021-04-14 13:34:22 +02:00
Guillaume Lemaitre 8a3939aa69
FIX Error for sparse matrix in OrdinalEncoder.inverse_transform (#19879) 2021-04-13 07:59:30 -04:00
Frederick Robinson bc7cd3189b
ENH more efficient _num_combinations calculation in PolynomialFeatures (#19734) 2021-04-02 10:30:03 +02:00
Thomas J. Fan c9c89cfc85
ENH Adds support for drop + handle_unknown=ignore in the OneHotEncoder (#19041) 
Co-authored-by: Olivier Grisel <olivier.grisel@gmail.com>
 2021-03-31 16:45:38 +02:00
makoeppel df3f1bda42
FIX Adds check_array to inverse_transform of StandardScaler (#19356) 
Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
 2021-03-23 09:14:41 -04:00
LSturtew 3e45aeef90
TST Remove assert warn from preprocessing tests (#19691) 2021-03-20 10:07:09 -04:00
Avi Gupta ca9618c0e2
MNT move PolynomialFeatures from _data.py to _polynomial.py (#19611) 
Co-authored-by: Roman Yurchak <rth.yurchak@gmail.com>
 2021-03-18 14:58:51 +01:00
mlondschien 95b7c680ab
ENH Add periodic extrapolation to SplineTransformer (#19483) 
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com>
 2021-03-17 13:46:45 +01:00
mlondschien f0a6f054e0
FIX bug in SplineTransformer.n_features_out_ (#19577) 2021-02-27 13:09:43 +01:00
Olivier Grisel c748e465c7
FIX Don't scale near-constant features to large values (#19527) 2021-02-25 10:21:52 +01:00
Thomas J. Fan 638b7689bb
ENH Adds nan passthrough in OrdinalEncoder (#19069) 2021-02-24 17:23:44 +11:00
Christian Lorentzen 27f1c737f2
FEA Add SplineTransformer (#18368) 2021-01-24 10:53:27 +01:00
Guillaume Lemaitre 8ea176ae0c
FIX validate handle_unkown strategies in OrdinalEncoder (#19234) 2021-01-22 10:58:41 +01:00
Guillaume Lemaitre 2218ec4622
MNT change 0.25 to 1.0 and 0.26 to 1.1 in deprecation messages (#19005) 
Co-authored-by: Thomas J. Fan <thomasjpfan@gmail.com>
 2020-12-18 16:09:19 +00:00
Oleh Kozynets f9e0b7d55f
FIX VisibleDeprecationWarning in unit tests and docstrings (#18414) 2020-10-28 14:47:57 +01:00
Alexandre Gramfort 5263eea04d
ENH add support for sample_weights in StandardScaler when X is sparse (#18682) 2020-10-28 09:34:17 +01:00
Thomas J. Fan 53add71a54
FIX Fixes encoders for string dtypes (#15763) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
 2020-10-27 12:08:56 +01:00
Thomas J. Fan d933c20bef
ENH Checks n_features_in_ in preprocessing module (#18577) 
Co-authored-by: Olivier Grisel <olivier.grisel@gmail.com>
Co-authored-by: Joel Nothman <joel.nothman@gmail.com>
Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com>
Co-authored-by: Nicolas Hug <contact@nicolas-hug.com>
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2020-10-21 18:11:44 +02:00
Kevin Winata 5d5329c473
FIX raise error in OneHotEncoder.inverse_transform (#14982) 2020-10-19 21:21:47 +02:00
Thomas J. Fan eeddc17a85
ENH Adds missing value support to OneHotEncoder (#17317) 
OneHotEncoder supports categorical features with missing values by
considering the missing values as an additional category.
 2020-10-09 08:38:33 +02:00
Thomas J. Fan 02fa8f1adb
ENH Deprecates _pairwise attribute and adds pairwise to estimator tags (#18143) 2020-10-07 21:53:36 +11:00
Maria Telenczuk 64697c665f
MRG Sample weight for StandardScaler (#18510) 2020-10-07 10:10:30 +02:00
Nicolas Hug 4aada4e5fd
ENH Support unknown_value=np.nan in OrdinalEncoder (#18406) 2020-09-23 12:57:31 +02:00
Felix Wick 8a213df98f
FEA allow unknowns in OrdinalEncoder transform (#17406) 2020-08-05 18:49:25 +10:00
Yashika Sharma 3017ea8c30
ENH Added parameter clip to MinMaxScaler (#17833) 2020-07-10 22:50:30 +02:00
Juan Carlos Alfaro Jiménez 547ead6c0c
MNT More replacements of numpy aliases with built-in types (#17707) 
* MNT More replacements of numpy aliases with built-in types [scipy-dev]

* MNT More (manual) replacements of numpy aliases

* MNT More (manual) replacements of numpy aliases

* FIX Minor change

* MNT Trigger build [scipy-dev]

* FIX Minor change

* MNT Trigger build [scipy-dev]

* FIX More deprecations of numpy aliases [scipy-dev]

* MNT Silent numpy aliases warnings [scipy-dev]

* FIX Fix silent deprecations

* Trigger build [scipy-dev]

* FIX Add scape characters [scipy-dev]

* FIX Remove package specification from silent

* Trigger build [scipy-dev]

* Revert
 2020-06-26 12:45:03 +02:00
Thomas J. Fan 7cc0177f8e
MNT Replaces numpy alias with builtin typse (#17687) 
* MNT Replaces numpy alias with builtin typse

* STY Lint error
 2020-06-24 16:51:51 +02:00
Arthur Imbert 846d51771d
ENH Add dtype parameter to KBinsDiscretizer to manage the output data type (#16335) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2020-06-16 14:13:48 +02:00
Lucy Liu 863e58fcd5
ENH Add option to scale output to unit var in RobustScaler (#17193) 
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
 2020-06-02 14:50:27 +02:00
Thomas J Fan d40d993199
CLN Refactors _encode into two functions (#17101) 2020-05-12 14:23:00 -04:00
Thomas J Fan acbe13c07d
ENH Adds pandas IntegerArray support to check_array (#16508) 2020-04-28 19:00:12 +02:00
Thomas J Fan e54cd3c061
API Deprecate positional arguments in preprocessing (#16996) 
* API Deprecate positional arguments in preprocessing

* CLN Address comments

* CLN Uses classes as a keyword only argument

* BUG Fix
 2020-04-23 19:10:49 +02:00