0974fb6d3c
ENH: Call plot twice per class label rather than for every point.
2013-10-10 00:37:31 -07:00
10b048032f
API : set return_models to False by default in path functions in coordinate descent
2013-09-29 15:18:13 +02:00
2ca483260e
DOC typo: polynominial
2013-09-28 17:38:12 +02:00
9cb3b96753
Merge pull request #2222 from FedericoV/Out_of_core_example
...
[MRG] Added comparison of other classifiers using partial fit methods
2013-09-18 01:18:34 -07:00
72334f1e8d
removing NWS from list of stock prices
2013-09-16 11:53:04 +02:00
9a9b9e85ed
DOC+COSMIT: typos, lots of them
...
Fixes #2102 . There's one typo left in joblib which is better fixed
upstream.
2013-09-13 16:29:42 +02:00
74d395215b
ENH bagging meta-estimator
2013-09-11 13:51:09 +02:00
3072c66f67
Merge pull request #2424 from sergiopasra/no-shebang
...
No shebang
2013-09-08 02:48:50 -07:00
572b30d804
COSMIT pep8/257
2013-09-06 18:05:58 +02:00
9f325a6c0f
cosmit pep8/257
2013-09-06 17:45:05 +02:00
5c7050c123
Fixed misc style changes suggested by Ogrisel
2013-09-06 17:44:38 +02:00
4cf42c8380
ENH: Added comparison of other classifiers using partial fit methods
2013-09-06 17:43:08 +02:00
6c3e176ae6
Remove execute pemission
2013-09-06 15:37:17 +02:00
915a58ba64
avoid zip + topic in doc
2013-09-06 08:51:06 +02:00
ab015af18e
pimp example
2013-09-05 21:50:28 +02:00
7d83cf33ac
API : add score_samples in FactorAnalysis + update example
2013-09-05 21:41:45 +02:00
c1ad0c76f3
pep8 + misc
2013-09-05 21:40:27 +02:00
d024326999
ENH : add PCA+FA model selection example
2013-09-05 21:39:58 +02:00
841fb88727
ENH prettier output from NMF example
...
Better stopword and noise filtering, increased n_samples to 2000
since the recent optimizations to tf-idf and NMF allow this.
Also some micro-optimizations to NMF itself.
2013-09-01 19:04:56 +02:00
3d772e9034
Add pairwise_distances_argmin.
2013-08-30 22:31:09 +09:00
70695caf78
Use pairwise_distances_argmin_min in examples.
2013-08-30 22:21:55 +09:00
dedc822edf
ENH export randomized_svd publicly
...
... and don't use an import from utils in an example script!
2013-08-30 10:17:40 +02:00
41b3ddd2d6
ENH speed up NMF (about 30% off topic extraction runtime)
2013-08-30 03:19:28 +02:00
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
f066c52e8a
Updated whats_new and fixed a typo in plot_precision_recall.py
2013-08-21 11:03:00 +02:00
d8112989a4
Added link to precision_score
2013-08-21 11:02:35 +02:00
8b2d9ebf42
Added links to cross_val_score, auc_score, and recall_score
2013-08-21 11:02:35 +02:00
56f0b86d9f
Added random_state argument to svm.SVC
2013-08-21 11:02:35 +02:00
4168576fee
Further expansion of the precision_recall curve explanation, spelling corrections, and general cleanup.
2013-08-21 11:02:35 +02:00
bf946fd475
Removed random_seed argument to svm.SVC
2013-08-21 11:02:35 +02:00
5e3bc74e82
Adjusted to fit 80 character columns, and corrected definition of precision
2013-08-21 11:02:35 +02:00
392866f6ea
Attempted a clearer explanation of precision-recall score
2013-08-21 11:02:35 +02:00
3af3bb27ec
Clarified a few wordy sentences
2013-08-21 11:02:34 +02:00
716bece132
Corrected some typos, and added more explanation for the precision recall example.
2013-08-21 11:02:34 +02:00
2ddea88bfe
Updated with more explanatory text. Also changed to use train_test_split function
2013-08-21 11:02:34 +02:00
4e8ac10c56
FIX py2.6 compat in biclustering example
2013-08-12 12:52:17 +02:00
af549f2b06
FIX + COSMIT Reuters out-of-core example
...
* download to scikit_learn_data, not pwd
* copyedited the docs
* rewrote a class as a simple function
* use glob instead of os.walk, the directory structure is flat
* trim output to fit in an 80-column terminal window
* changed some identifiers
XXX there's a bug in the minibatch splitting: I only get 973 test
samples, while a 1000 are requested:
Test set is 973 documents (125 positive)
100 train docs ( 14 positive) accuracy: 0.840 in 1.09s ( 91 docs/s)
1067 train docs ( 166 positive) accuracy: 0.918 in 2.28s ( 467 docs/s)
2027 train docs ( 310 positive) accuracy: 0.925 in 3.36s ( 603 docs/s)
...
2013-08-10 12:55:16 +02:00
c3bcbbd6bd
MISC: fix wrong timing in example
2013-08-07 22:50:25 +02:00
5cadbe68ff
DOC typos involving Nyström
2013-07-30 18:02:23 +02:00
98b95ca711
DOC fix example comments
...
* @GaelVaroquaux's name was misspelled
* users won't know what a "Documentation merge" is
2013-07-30 12:41:56 +02:00
9bffc8fd81
MISC: fix plot_multilabel example
2013-07-28 18:00:36 +02:00
b0035bf9e8
Rename cv_scores(_) back to grid_scores(_) to keep the name free for a future refactoring
2013-07-28 17:10:14 +02:00
75af99e231
EXAMPLES remove non-existing example from doc, don't trigger deprecated interface in enet_path, lasso_path
2013-07-28 15:17:14 +02:00
26eb3c606f
DOC/EXAMPLES fix more documentation errors, deprecated api usages.
2013-07-28 15:01:48 +02:00
04f7d4989e
DOC copyedit example docstring
2013-07-28 14:10:30 +02:00
c7c7ade0e8
FIX don't use old API in examples
2013-07-28 12:58:59 +02:00
c16da082de
Refactor loss_func and score_func warnings in cross_validation + replacement in two examples
2013-07-28 10:45:44 +02:00
0682711af9
COSMIT: typo in examples/imputation.py
2013-07-28 09:03:56 +02:00
190449424d
DOC reference and rename cross decomposition module
2013-07-28 02:56:12 +02:00
d65de5e76c
Fix libsvm seed when predict_proba in tests and examples
2013-07-27 19:50:25 +02:00
Eric Jacobsen