0807e19dc2
MAINT deprecate fit_ovr, fit_ovo, fit_ecoc, predict_ovr, predict_ovo, predict_ecoc and predict_proba_ovr
2014-07-19 12:17:22 +02:00
bd1686b3a5
Merge pull request #2804 from arjoly/lrap
...
[MRG+1] Label ranking average precision
2014-07-19 12:05:48 +02:00
9f45e3730f
Modified sparse OvR to handle sparse target data
...
Defaulted label binarizer to set sparse_output=True when training ovr
classifiers, edited Label binarizer to allow for sparse binary column output
2014-07-18 12:10:50 +02:00
c19177196b
DOC improve documentatino thanks to @vene and remove mention of relevant labels
2014-07-17 17:15:08 +02:00
bb93ede201
DOC remove confusing mention to mean average precision
2014-07-17 11:25:21 +02:00
32c2692058
Typo
2014-07-17 11:21:28 +02:00
c3542bade9
DOC friendlier narrative documentation
2014-07-17 11:14:54 +02:00
9d8d7748bc
DOC FIX error + wording
2014-07-17 11:09:46 +02:00
35c90186ce
DOC write narrative doc for label ranking average precision
2014-07-17 11:09:46 +02:00
5b247f90e4
move around examples for better structure.
2014-07-17 09:35:30 +02:00
4e438a9aac
[DOC] minor fixes
2014-07-16 10:27:31 +02:00
4315e91339
DOC: expand documentation for logistic regression
2014-07-15 10:12:56 +02:00
5b5dba1487
DOC: fix classes not referenced in docs
2014-07-14 18:04:22 +02:00
2eb1e98eef
MAINT ensure that examples figures are displayed in the correct order
2014-07-14 15:47:17 +02:00
851d914ccc
DOC: add transpose and intercept to formula of logistic regression
2014-07-12 17:46:17 +02:00
b289d37e64
Merge branch 'pr/3358'
2014-07-12 16:20:54 +02:00
7022f3ed58
DOC: typo, envelop → envelope
2014-07-12 16:19:54 +02:00
ec05d9866f
fixed typo: diriclet -> dirichlet
2014-07-11 14:21:29 -07:00
7d8eaf756f
DOC: write cost function of logistic regression.
...
I feel it important to state clearly what is the cost function of the
model because:
* Some might want to compare their implementation against this one,
in which case it is important to know exactly what is the form of the
cost function
* Furthermore since the models are quite inconsistent in terms of
notation for the regularization parameter: some models in this
module penalize by 1/C, others by alpha and others by alpha/2
2014-07-11 14:26:34 +02:00
bd0f2d5619
Cosmetic: correct latex formula display
2014-07-11 14:10:16 +02:00
f5d9b5ba06
Fix labels of inliers vs outliers
...
At least based on what svm.OneClassSVM does in the example linked from this document, the description was wrong; labels actually assigned are 1/-1 for good/bad respectively, not 0/1.
2014-07-09 14:44:14 -07:00
5b55f57f25
Fix grammar
...
it's should be its
2014-07-09 13:17:34 -07:00
ab1a784f0b
FIX failing tests due to the change of the underlying sample generator
2014-07-08 12:21:55 +02:00
c176ced74d
DOC double backticks for fixed-width (code) font
...
Fixes #3337 . Also other minor fixes while I was at it.
2014-07-06 14:18:33 +02:00
3b8dc3dc72
Update Sphinx docs for GaussianNB partial_fit
2014-07-04 12:27:07 -07:00
03a78d573d
fix typo (on -> one)
2014-07-02 22:18:30 +09:00
b9f6ac4038
min_weight_fraction_leaf: narrative doc update
2014-07-02 11:47:33 +02:00
f62a6d1723
min_weight_fraction_leaf: narrative docs
2014-07-02 11:47:32 +02:00
0a3a67777d
DOC SVMs take string class labels as well as integers
...
http://stackoverflow.com/a/24512272/166749
2014-07-01 16:34:09 +02:00
4b79f220a4
Metadata information for unpickling models in future versions
2014-06-27 08:57:24 -03:00
78c0f61060
Simplified security and maintenance section
2014-06-27 08:57:24 -03:00
4c51809103
Remove trailing whitespace
2014-06-27 08:57:24 -03:00
be315ed0a6
Move model persistence doc inside model selection section
2014-06-27 08:57:23 -03:00
2bfca14c49
ENH sparse matrix support in label binarization
2014-06-25 16:15:19 -04:00
916050a28b
DOC hmm example has been removed
2014-06-25 11:36:46 +02:00
42e9f5d9ad
DOC fix bad formatting in decomposition.rst
2014-06-23 10:57:19 +02:00
59d6a11a57
bug fix and deprectation warning added to cross-validation
2014-06-21 21:39:51 +02:00
d580661554
DOC add the Random Kitchen Sink synonym to the RBFSampler section
...
This should make it easier for people to find this code if they search for the
terms 'random kitchen sink' and 'python'.
2014-06-19 15:59:36 +02:00
f458662faa
DOC typo in ExtraTrees
2014-06-19 00:03:48 +02:00
69b50e1206
DOC big fat warning about multithreaded BLAS
2014-06-18 22:08:42 +02:00
a75f44cc15
Merge pull request #3280 from larsmans/remove-hmm-docs
...
[MRG] remove HMM documentation
2014-06-17 08:11:18 +02:00
9772d9528e
DOC remove HMM documentation
2014-06-16 21:44:52 +02:00
5fa2f9cecf
DOC: copyedit log loss, hint how multiclass generalizes binary
...
Changed notation to use y for true label, p for prediction,
to be more consistent with the rest of the docs.
2014-06-15 16:05:35 +02:00
2f07590dca
DOC Correct definition of multiclass log loss
2014-06-15 16:05:35 +02:00
67b8601314
Minor fixes in the docs
2014-06-07 16:38:53 +02:00
7accbfa5d4
Merge pull request #3239 from larsmans/faster-poly-features
...
compute poly features directly and allow interaction features only
2014-06-05 18:00:58 +02:00
de42d692d8
ENH interaction_only in PolynomialFeatures
2014-06-05 17:46:07 +02:00
fc0150d08d
DOC/FIX Address @arjoly's comments
2014-06-05 11:20:36 +02:00
255895d951
DOC remove mention of sequence of sequences in Parameters sections
2014-06-05 11:20:36 +02:00
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
Arnaud Joly