Andreas Mueller
|
38b455d541
|
Cosmit pep8
|
2012-12-25 13:16:05 +01:00 |
|
Andreas Mueller
|
d9a6243c98
|
ENH rename k in clustering examples and doctests to n_clusters
|
2012-05-30 07:41:34 +02:00 |
|
Olivier Grisel
|
c0541fa03b
|
Renamed Vectorizer to TfidfVectorizer + deprecation warning
|
2012-03-07 06:48:56 -08:00 |
|
Olivier Grisel
|
57e32f43b0
|
enable stop words in clustering example
|
2012-03-06 07:39:13 +01:00 |
|
Lars Buitinck
|
216a0122b2
|
ENH demo sparse KMeans on 20news set (it's slow!)
Conflicts:
examples/document_clustering.py
|
2011-12-21 13:12:20 +01:00 |
|
Olivier Grisel
|
af05e765f0
|
Merge branch 'master' into minibatch-kmeans-optim
|
2011-12-20 09:56:19 +01:00 |
|
draxus
|
e5628f79c6
|
peping8 examples
|
2011-12-19 18:16:51 +01:00 |
|
Olivier Grisel
|
f87248dcec
|
new example to emphasize issues with current naive reinit scheme on sparse data
|
2011-11-06 23:50:12 +01:00 |
|
Olivier Grisel
|
982359cfab
|
first stab at a reinit strategy that work on low dim data only
|
2011-11-06 22:33:34 +01:00 |
|
Olivier Grisel
|
9fbe559139
|
make k-means++ work on sparse input and use it as default for MB k-means
|
2011-11-06 15:21:58 +01:00 |
|
Olivier Grisel
|
a0f259842c
|
switch to lazy sampling with explicit index to divide memory usage almost by 2 and decrease code complexity with no measurable impact on the run time
|
2011-11-03 12:58:38 +01:00 |
|
Olivier Grisel
|
b9087e5c8a
|
ENH: document clustering example simplification
|
2011-10-09 11:20:56 +02:00 |
|
Olivier Grisel
|
e6eff45d96
|
ENH: no need for L2 norm on input in doc clustering
The new TD-IDF implementation already does that by default.
|
2011-09-27 09:17:44 +02:00 |
|
Lars Buitinck
|
fa50e6885a
|
rename ari_score adjusted_rand_score
|
2011-09-13 16:50:30 +02:00 |
|
Olivier Grisel
|
75f2617579
|
FIX: fix broken document clustering example and add ARI to examples
|
2011-09-10 07:23:46 +02:00 |
|
Fabian Pedregosa
|
ddf4b72109
|
Move project directory from scikits.learn to sklearn
|
2011-09-02 12:06:57 +02:00 |
|
Fabian Pedregosa
|
68f27e3790
|
Revert "Move project directory from scikits.learn to sklearn"
This reverts commit fd0d3b879d.
|
2011-09-02 12:03:18 +02:00 |
|
Fabian Pedregosa
|
fd0d3b879d
|
Move project directory from scikits.learn to sklearn
|
2011-09-02 11:38:24 +02:00 |
|
Peter Prettenhofer
|
1872fb53ab
|
changed batch representation from indices to slices.
|
2011-07-04 22:23:34 +02:00 |
|
Peter Prettenhofer
|
981478e35d
|
more tests for (mini-batch) k-means (99% coverage).
|
2011-06-25 18:35:09 +02:00 |
|
Peter Prettenhofer
|
8bb2fc2471
|
set max_terms to 10k. Added spectral clustering.
|
2011-06-10 13:25:35 +02:00 |
|
Peter Prettenhofer
|
129fe597ad
|
Document clustering example updated.
|
2011-06-10 12:53:02 +02:00 |
|
Peter Prettenhofer
|
2f5248bb1d
|
changed mini batch representation in dense MiniBatchKMeans - saves mem but increases runtime.
added tol and max_iter to sparse MBKM.
|
2011-06-10 11:42:44 +02:00 |
|
Peter Prettenhofer
|
02b697ad7b
|
Use euclidean distance.
|
2011-06-10 10:06:00 +02:00 |
|
Peter Prettenhofer
|
6bb2b37995
|
added SpectralClustering to document_clustering example.
rm compute_cache from cython codebase.
|
2011-06-07 15:41:32 +02:00 |
|
Peter Prettenhofer
|
765ce7db5f
|
Added different compute_cache functions: dot and euclidean distance.
|
2011-06-07 12:07:32 +02:00 |
|
Peter Prettenhofer
|
1bf591c57d
|
enh: compute cache only on samples in current batch.
now significantly faster.
|
2011-06-06 21:53:31 +02:00 |
|
Peter Prettenhofer
|
50e9f18d7d
|
Initial checkin of sparse.MiniBatchKmeans clustering + document clustering example on 20 news.
|
2011-06-06 18:40:00 +02:00 |