 Ryan Curtin
|
e7d39b4e92
|
Compile libmlpack.so not libmlpack.a.
|
2011-12-14 12:16:49 +00:00 |
|
|
Ryan Curtin
|
435ef442b1
|
Allow compilation with -DARMA_EXTRA_DEBUG.
|
2011-12-14 12:16:27 +00:00 |
|
|
Ryan Curtin
|
4d76e86abb
|
Make it how it was before.
|
2011-12-14 12:13:02 +00:00 |
|
|
Ryan Curtin
|
9c343e05bb
|
Clean up CLI output again and again. Then change how Timers works because it
was being destructed before CLI in some cases. That's the danger of
singletons...
|
2011-12-14 12:11:41 +00:00 |
|
|
Ryan Curtin
|
3b9fdd2947
|
Update for transposition of output.
|
2011-12-14 11:42:54 +00:00 |
|
|
Ryan Curtin
|
b625bfd9f3
|
Refactoring of EMST/UnionFind API.
|
2011-12-14 10:53:18 +00:00 |
|
|
Ryan Curtin
|
e804539a3f
|
Refactor and clean up EMST code.
|
2011-12-14 10:53:00 +00:00 |
|
|
Ryan Curtin
|
2409554792
|
Restructure test.
|
2011-12-14 08:19:14 +00:00 |
|
|
Ryan Curtin
|
69ce9b8ff2
|
New Statistic API.
|
2011-12-14 08:04:33 +00:00 |
|
|
Ryan Curtin
|
069684470c
|
New Statistic API.
|
2011-12-14 08:04:13 +00:00 |
|
|
Ryan Curtin
|
534cdb854a
|
Make statistics useful again.
|
2011-12-14 08:04:08 +00:00 |
|
|
Ryan Curtin
|
d68d9c963f
|
Oops, I need a <>.
|
2011-12-14 06:43:10 +00:00 |
|
|
Ryan Curtin
|
3463039973
|
Document EMST better.
|
2011-12-13 22:12:53 +00:00 |
|
|
Ryan Curtin
|
55af68fbc2
|
Clean up CLI formatting... for like the fifth time.
|
2011-12-13 21:55:33 +00:00 |
|
|
Ryan Curtin
|
d1a73ed08c
|
Abstract-ize NBC to allow sparse matrices.
|
2011-12-13 19:34:59 +00:00 |
|
|
tekhnofiend
|
9f1b2af2d1
|
removed random seed from radical_test.cpp
|
2011-12-13 19:08:34 +00:00 |
|
|
Ryan Curtin
|
dab5f8f48d
|
Sparse NCA doesn't actually make sense.
|
2011-12-13 19:04:19 +00:00 |
|
|
tekhnofiend
|
8eaab7a83e
|
increased tolerance for RADICAL test
|
2011-12-13 19:00:15 +00:00 |
|
|
Ryan Curtin
|
48e3a0fde4
|
Abstract-ize matrix type used for NCA datasets. The covariance matrix should
not be sparse, though.
|
2011-12-13 11:31:00 +00:00 |
|
|
Ryan Curtin
|
3e4f4f0690
|
Unused variables.
|
2011-12-13 11:30:22 +00:00 |
|
|
Ryan Curtin
|
d54173bf15
|
Test sparse K-Means.
|
2011-12-13 11:18:03 +00:00 |
|
|
Ryan Curtin
|
887e569b2b
|
Use a const reference internally in SpSubviews.
|
2011-12-13 11:17:55 +00:00 |
|
|
Ryan Curtin
|
94df1983db
|
Support SpSubview proxies.
|
2011-12-13 11:17:34 +00:00 |
|
|
Ryan Curtin
|
4db8c8deb7
|
Centroids should be sparse, too, if we want them to be.
|
2011-12-13 10:47:12 +00:00 |
|
|
Ryan Curtin
|
c3b30c6a77
|
Explicit conversion to mat.
|
2011-12-13 10:21:18 +00:00 |
|
|
Ryan Curtin
|
2039f13c90
|
Abstractize k-means so it can use sparse matrices.
|
2011-12-13 09:33:27 +00:00 |
|
|
Ryan Curtin
|
b34a12ccaa
|
Abstractize vector type.
|
2011-12-13 09:20:14 +00:00 |
|
|
Ryan Curtin
|
785a747777
|
Allow sparse vectors to be passed to metrics (this should get a bit of speedup).
Now we leave the computation up to Armadillo.
|
2011-12-13 08:59:08 +00:00 |
|
|
Ryan Curtin
|
ef3145515b
|
Why does this fix the test? I don't know, but there's not complete time to fix
it right now.
|
2011-12-13 08:35:27 +00:00 |
|
|
Ryan Curtin
|
be370b2347
|
Simpler swap_cols() and SpValProxy::operator=(SpValProxy&) to make it work.
|
2011-12-13 07:23:09 +00:00 |
|
|
Ryan Curtin
|
8dbc01d8aa
|
Retry the API change. This time it works...
|
2011-12-12 22:54:17 +00:00 |
|
|
Ryan Curtin
|
65eac72677
|
Copy code over from arma-sparse branch.
|
2011-12-12 19:30:39 +00:00 |
|
|
Ryan Curtin
|
acada435af
|
I had been approaching the wrong solution to the issue because they keep
bringing me drinks.
|
2011-12-12 19:13:17 +00:00 |
|
|
Ryan Curtin
|
ded6707e2f
|
Too much noise means I start doing things wrong.
|
2011-12-12 18:52:59 +00:00 |
|
|
Ryan Curtin
|
0788a8579f
|
These aren't necessary with Armadillo >= 2.4.0.
|
2011-12-12 18:44:34 +00:00 |
|
|
tekhnofiend
|
c7de3f45a1
|
updated lars_test to reflect changes to lars
|
2011-12-12 18:28:41 +00:00 |
|
|
tekhnofiend
|
04f2a9d0a5
|
LARS no longer has X and y as class members. They are passed into the main computation function DoLars
|
2011-12-12 18:28:26 +00:00 |
|
|
Ryan Curtin
|
685d46538e
|
API changes.
|
2011-12-12 16:44:48 +00:00 |
|
|
Ryan Curtin
|
ef07d033da
|
Refactor API to be consistent with RangeSearch.
|
2011-12-12 16:43:39 +00:00 |
|
|
Ryan Curtin
|
b3e0c0e320
|
Stop using unsafe_col().
|
2011-12-12 16:12:00 +00:00 |
|
|
Ajinkya Kale
|
11184bdda5
|
|
2011-12-12 10:47:10 +00:00 |
|
|
Ajinkya Kale
|
b557d834d4
|
got the implementation into hpp file to include it in the class def. This is need to make the templates work. Good article here which talk about why we need this http://www.comeaucomputing.com/techtalk/templates/#whylinkerror
|
2011-12-12 10:45:30 +00:00 |
|
|
Ryan Curtin
|
ab08da51cd
|
We can use regular .col() here since we abstracted away arma::vec.
|
2011-12-12 10:33:50 +00:00 |
|
|
Ryan Curtin
|
bdf2c0a694
|
A typedef so other types that depend on the matrix type can use it.
|
2011-12-12 10:15:30 +00:00 |
|
|
Ryan Curtin
|
000699634d
|
Abstract-ize HRectBound to accept arbitrary types of things.
|
2011-12-12 10:01:24 +00:00 |
|
|
Ryan Curtin
|
b2ce58259a
|
Templatize the matrix type.
|
2011-12-12 09:49:25 +00:00 |
|
|
Ryan Curtin
|
8ede0e9470
|
Convert u32 to uword for 2.4.0.
|
2011-12-12 09:32:31 +00:00 |
|
|
Ryan Curtin
|
803aa1a1c5
|
Add sparse support which can be patched into Armadillo if necessary.
|
2011-12-12 09:26:12 +00:00 |
|
|
Ryan Curtin
|
8b170d574a
|
Yeah, break everyone's build by requiring 2.4.0. It's for a good cause though.
|
2011-12-12 09:11:17 +00:00 |
|
|
Ajinkya Kale
|
ab715d86e5
|
and i present you <Kernel PCA>
|
2011-12-12 09:00:28 +00:00 |
|