Commit Graph

118 Commits

Author SHA1 Message Date
Rémy Léone 9b7176dd9d [DOC] Fix broken links 2016-03-23 12:45:34 -07:00
Harry Mavroforakis b50d3ed37e Fixes make_sparse_spd_matrix documentation
Updates the documentation of the parameter alpha in make_sparse_spd_matrix() to reflect its effect in sparsity.
2016-01-28 17:00:34 -05:00
seales 0485ada58b General spelling fixes 2015-12-16 09:46:42 -08:00
KamalakerDadi f2e35411fa Added more versions of 0.17 2015-11-04 00:02:52 +01:00
Joel Nothman 71c99dc73c FIX error introduced during rebase 2015-08-30 23:19:01 +10:00
Kashif Rasul aaae2db9dc make_multilabel_classification sparse target
for issue #3554
2015-08-30 23:00:29 +10:00
Raghav R V 7e828db722 MAINT remove unused import warnings 2015-08-11 22:27:15 +05:30
Raghav R V 6fb17a1f95 FIX revert generation of seq of seq in make_multilabel_classification 2015-08-11 22:27:15 +05:30
Raghav R V 664d78eb7c MAINT Remove support for the deprecated sequence of sequences
MAINT Remove sequence of sequence support from datasets
MAINT Remove return_indicator param
MAINT Remove multilabel-seq test in OVR
MAINT Remove multilable-seq test in check_cv
MAINT Remove multilabel seq test in label_binarizer
TST type_of_target returns "unknown" for multilabel-sequence types
TST _check_targets should raise a ValueError
DOC show multilabel indicator as an example; remove return_indicator param
DOC use consistent lower case y for target
2015-08-11 22:26:44 +05:30
Phil Roth b26e8794d7 allowing for different cluster stds 2015-07-11 16:52:57 -05:00
Andreas Mueller 0650d5502e DOC adding backlinks to docstrings 2015-06-03 00:24:04 -04:00
Andreas Mueller 6beacc3fb6 remove deprecated stuff from 0.17 2015-03-18 14:49:04 -04:00
Raghav R V b3fbccca38 FIX various mismatch between docstring and signature params
DOC max_iterations -> max_iter. Make it consistent with kmeans

MAINT Replace the deprecated dx parameter with d in the docstrings

MAINT Deprecation warning for max_iterations parameter.
2015-01-16 11:54:57 -05:00
Andreas Mueller c970fb51e7 COSMIT spelling 2015-01-15 15:09:35 -05:00
Olivier Grisel fd57806755 MAINT remove integer warnings under Python 3 + numpy 1.8+ 2014-10-08 13:33:53 +02:00
Joel Nothman 787e4a0cea DOC extend documentation on sample generators
Also allow make_multilabel_classification to return underlying
distributions.
2014-08-25 19:36:58 +10:00
Joel Nothman e58764feab DOC more explicit parameter descriptions in make_multilabel_classification 2014-08-20 00:06:00 +10:00
Joel Nothman a52085f6ac DOC correct default value 2014-08-13 12:58:23 +10:00
Andreas Mueller 6e2a83b4e1 remove check_arrays stuff and old input validation 2014-07-20 13:31:45 +02:00
Joel Nothman 5ea6b3ac95 COSMIT in response to @arjoly's comments 2014-07-08 11:13:58 +02:00
Joel Nothman e633f25233 ENH make_multilabel_classification for large n_features: faster and sparse output support 2014-07-08 11:13:58 +02:00
Lars Buitinck cdd2279c09 ENH fix astype usage to prevent copying
Removed where possible; using copy=False (from utils.fixes) where needed.

Also some C integer type fixes to gradient boosting.
2014-06-18 11:01:28 +02:00
Andreas Mueller 55ecfa2c32 COSMIT TYPO 2014-06-08 21:45:40 +02:00
Joel Nothman 18c399e20a MAINT deprecate sequences of sequences support
* add warnings
 * provide alternative binarizer, sklearn.preprocessing.MultiLabelBinarizer
 * fix documentation
2014-06-05 11:20:35 +02:00
Lars Buitinck 23b3cc2eb5 MAINT drop support for SciPy < 0.9
TODO: get rid of solve_triangular. Just replacing it by scipy.linalg's
breaks OMP and least-angle regression.
2014-03-02 20:13:57 +01:00
Chen Liu f657d9c1ee using floor division in python3 2014-01-28 15:12:21 -05:00
Gilles Louppe 1a887dda68 COSMIT: Various PEP8 2014-01-16 14:34:10 +01:00
Mathieu Blondel 8f71e46b1d Handle n_features < n_informative case in make_regression.
Useful if n_informative is not explicitly specified, in which case
n_informative=10.
2014-01-09 17:20:13 +09:00
Joel Nothman 224a4d593b TST/COSMIT cleaner make_classification and fix tests
* refactored make_classification
* new test for make_classification
* skip problematic common test for class_weights
2014-01-01 23:00:50 +11:00
Joel Nothman 33b8430203 Use internal sample_with_replacement rather than Python's random.sample 2013-12-31 15:44:52 +01:00
Joel Nothman bd58cf9772 Remove debug print statement 2013-12-31 15:44:51 +01:00
Joel Nothman f8a4a63dca FIX don't leave clusters in uint8 2013-12-31 15:44:51 +01:00
Joel Nothman ba1a68482a FIX Low-memory cluster sampling in make_classification
This allows larger `n_informative` with small cost, but will not produce
the same output as in previous versions.
2013-12-31 15:44:51 +01:00
Joel Nothman a60020506e FIX suspected bug for non-hypercube make_classification 2013-12-31 15:44:51 +01:00
Lars Buitinck 4b8542384b Revert "ENH: faster cartesian product in make_classification and document complexity"
This reverts commit 03352bf5f9.

Apparently doesn't work with older NumPy.
2013-12-08 01:50:51 +01:00
Lars Buitinck 03352bf5f9 ENH: faster cartesian product in make_classification and document complexity
This version
* is 4-6x faster
* takes less memory, and
* (on my box) is more likely to give a decent MemoryError instead of
  triggering the OOM killer, because it allocates in one go.

See #2534.
2013-12-08 01:10:59 +01:00
Lars Buitinck 5ae399f140 ENH: don't call astype when a copy is not needed
See #2206. This doesn't fix all of the cases.
2013-09-13 17:07:06 +02:00
Brooke Osborn 2eddb1a29f BUG fix whitespace in error messages
Partial fix for #2380.

Signed-off-by: Lars Buitinck <L.J.Buitinck@uva.nl>
2013-08-26 17:02:52 +02:00
Arnaud Joly c6fa3a0318 ENH allows make_multilabel_classification to return label indicator format 2013-07-26 15:57:35 +02:00
Gilles Louppe de86e97548 Merge pull request #2241 from arjoly/grid-cv-multioutput
[MRG] Make sure that cross_validation_score and grid_search_cv support multi-output / multi-target output
2013-07-26 01:33:41 -07:00
Kemal Eren f9efd1bfab fixed some docstrings: backticks and missing parameters 2013-07-25 19:19:24 +02:00
Kemal Eren 96e0264ede moved shuffle functionality to utility function 2013-07-25 19:19:22 +02:00
Kemal Eren 5ad0dfb69b wrote bicluster scoring using jaccard index and hungarian matching 2013-07-25 19:19:21 +02:00
Kemal Eren 836f3f0817 fixed some errors reported by pyflakes 2013-07-25 19:19:18 +02:00
Kemal Eren 36daa8bbc8 fixed bug in make_checkerboard(), so tests pass again 2013-07-25 19:19:18 +02:00
Kemal Eren 34caec676b checkerboard panels may have arbitary values. 2013-07-25 19:19:16 +02:00
Kemal Eren ddf82eef14 use random state in data generator 2013-07-25 19:19:15 +02:00
Kemal Eren ca902adcaa wrote methods for generating bicluster data 2013-07-25 19:19:14 +02:00
Arnaud Joly 8436201dee ENH allows make_multilabel_classification to return label indicator f… 2013-07-25 18:24:17 +02:00
Philippe Gervais b5950ad070 Style fixes 2013-07-22 17:20:52 +02:00