6ec33ff899
FIX : removing useless seed fix in plot_mean_shift
2011-05-18 22:20:36 -04:00
b2818993c3
ENH : using make_blobs in plot_mini_batch_kmeans
2011-05-18 22:18:40 -04:00
3e0aeac85e
ENH : using make_blobs in plot_mean_shift
2011-05-18 22:16:09 -04:00
2ab954c6f0
ENH : using make_blobs in plot_affinity_propagation
2011-05-18 22:14:35 -04:00
fd9919de3a
ENH: better / simpler handling of shuffling in MiniBatchKMeans
2011-05-18 02:16:38 +02:00
cd9e727492
DOC: cosmit in MiniBatchKMeans docs
2011-05-17 22:57:11 +02:00
5b397103c8
Merge remote branch 'gael/batchKMeans' into batchKMeans
2011-05-17 21:38:58 +01:00
0cb216b2ac
merge with master
2011-05-17 21:10:38 +01:00
08340af0d4
DOC: Prettify MiniBatchKmean example
2011-05-17 21:50:16 +02:00
582fa8248c
[MiniBatchKMeans] Minor modifications on the examples
...
Deleted redondant examples
2011-05-17 19:52:38 +01:00
d3e526234e
ENH: simpler import statement in example + explicit square
2011-05-15 15:24:22 +02:00
7cac98e0e4
ENH: simpler import statement in example
2011-05-15 15:21:06 +02:00
1d0b8df77b
[MiniBatchKMeans] Updated the example to compare BatchKMeans and MiniBatchKMeans - added the copy_x option to the BatchKMeans
2011-05-15 12:03:24 +01:00
a3521a5b84
[MiniBatchKMeans] Added an example
2011-05-09 23:00:11 +01:00
1d66d0b8b9
illustrate clustering metrics on affinity propagation example
2011-05-08 10:43:14 +02:00
fd2fdc2971
use V-measure metrics in K-means example
2011-05-07 19:07:43 +02:00
5bb104f59f
[MiniBatchKMeans] Added a fit method to the MiniBatchKMeans
2011-05-07 17:21:50 +01:00
b6ab08a4d7
[MiniBatchKMeans] PEP8 compliance
2011-05-04 22:00:41 +01:00
fd8353cf63
[MiniBatchKMeans] Added some documentation and example
2011-05-04 21:49:48 +01:00
52c4cef783
merge with master
2011-05-04 19:05:57 +01:00
8b5a0274d2
kill trailing spaces
2011-05-04 17:49:17 +02:00
f1c6265727
Return also t from swiss_roll generator (needed to plot colors)
2011-05-04 11:08:11 +02:00
6470049313
ENH: fix example docstring
2011-04-16 11:47:23 +02:00
62c5fe6366
ENH: more interesting batch size
2011-04-16 11:24:30 +02:00
d2702e16a1
[MiniBatchKMeans] Removed the unnecessary import in examples/cluster/mini_batch_kmeans.py
2011-04-15 20:44:27 +01:00
7dcaceda66
[BatchKMeans] Small fixes following Olivier & Gael's review
...
- PEP8 compliance
- examples/cluster/mini_batch_kmeans.py
- passed k to the mini_batch function
- renamed chunk to batch_size
- changed the data variable (global) to the X one (local)
- Fixed all the calls to the mini_batch function
- Defaulted iterations to 300 in the mini_batch function
- scikits/learn/cluters/k_means_.py:
- More documentation
2011-04-15 20:34:54 +01:00
5e11d75cdc
Merge branch 'master' into batchKMeans
2011-04-11 20:31:07 +01:00
a30197cbc6
[MiniBatchKMeans] Small fixes
...
- Updated the example to have them run properly with the new API for mini batch KMeans
- Small fixes in the code
2011-04-11 20:21:01 +01:00
f57b26ea9d
[MiniBatchKMeans] Starting refactoring code after the review
...
- Renamed BatchKMeans in MiniBatchKMeans
- Implemented the partial_fit method
- Updated examples for the new API
2011-04-11 19:05:00 +01:00
09851fcc05
DOC: Fix warnings
...
Patching the numpy docscraper to avoid the use of 'toctree' that create a
lot of warnings for little good.
Fix warnings throughout the docs.
2011-04-10 22:44:13 +02:00
98d920c51f
[batch k-means] Fixed the computation of the batch kmeans centroids
...
I had a mean instead of a sum in the computation of the batch kmeans.
Added some more examples with different chunk size.
2011-04-07 21:27:28 +01:00
79e7f87e1a
Batch K-Means
...
Changed the example of the batch K-Means to be a comparison of several Batch K-Means with different chunk size, and of the normal K-Means with the same initialisation of the centers, and the same set of data
2011-04-06 20:23:58 +01:00
8747939cd9
First draft of the mini batch KMeans - works, but a lot of cleaning up to do
2011-04-05 19:45:25 +01:00
53c92b036c
API: components_ shape fixed in PCA classes
2011-04-05 10:13:50 +03:00
ea2aa805f4
Decomposition module WIP
2011-04-04 14:31:48 +03:00
078d3c108e
DOC: better docs for Ward
2011-04-02 20:58:27 +02:00
1e5ae890e1
BUG: fix multiple figure plotting
2011-04-02 16:52:41 +02:00
632364c3ba
cosmits with trailing spaces
2011-04-01 12:36:49 -04:00
3c9113d0b2
always use scikits ward algo when no structure is provided
2011-04-01 12:18:29 +02:00
7d6b8b1dad
BUG: fix grid_to_graph
2011-03-03 13:59:22 +01:00
a3bc7eafcf
ENH : factorizing img_to_graph and grid_to_graph
...
there was no bug before but an obscure img_to_graph(mask, mask)
that is now replaced by grid_to_graph (makes a connectivity structure
for a grid of pixels/voxels)
2011-02-28 10:58:00 -05:00
5c9df2cefc
FIX: ugly bug in connectivity on grids and images
2011-02-25 15:37:41 -05:00
8c6ece869b
fix remaining n_comp
2011-02-24 16:59:49 -05:00
c5aa155621
Merge branch 'hcluster' into hcluster2 that matches master
...
- pipeline and GridSearchCV have been cleaned
- feat agglo inherits from TransformerMixin
- s / n_comp / n_components in hierarchical.py
Conflicts:
scikits/learn/feature_selection/univariate_selection.py
scikits/learn/pipeline.py
scikits/learn/tests/test_pipeline.py
2011-02-21 21:28:34 -05:00
abd9a193c7
moving swiss_roll generator in samples generator
...
better 3D axes orientation for viz
2011-02-01 22:29:50 -05:00
1cd924e404
better ward rst doc examples
2011-01-31 22:16:31 -05:00
f7eacfded0
remaining s/k/n_clusters
2011-01-25 13:16:14 -05:00
de06c23ba7
in hierarchical : s/adjacency_matrix/connectivity, s/k/n_clusters
2011-01-25 13:06:06 -05:00
704ed7e83f
ENH : improving ward for better joblib caching
2011-01-25 11:39:59 -05:00
e49cd50020
ENH: Reorganise the feature agglomeration
2011-01-23 11:36:07 +01:00
Alexandre Gramfort