pymc-devs / pymc3 / 7664 / 2
87%
master: 87%

DEFAULT BRANCH: master
Ran
Files 139
Run time 4s
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst
coverage: 39.668% (-0.05%) from 39.717%
PYTHON_VERSION=2.7 FLOATX='float32' RUN_PYLINT="true" TESTCMD="--durations=10 --cov-append pymc3/tests/test_distributions_random.py pymc3/tests/test_shared.py pymc3/tests/test_smc.py pymc3/tests/test_sampling.py"

push

travis-ci

junpenglao 
Ordered Transform (#2637)

* initial commit of Ordered, courtesy @aseyboldt

* add composed transform (from @aseyboldt)

* add ordered logistic distr

* add test

* change from function to subclass of Categorical

* test passing on OrderedLogistic

* fix docs up

* fix to docstring

* starting transform tests

* ordered transform tests pass locally, need tests for composed transform

* fix OrderedLogistic import

* remove composed

* a little cleanup

* Remove extra the's (#2960)

* fix test, remove Composed Transform)

* Add release note

* Ordered transformed is not elementwise

* Fix Binomial when p=0 and x=0 (#2961)

* Fix Binomial when p=0 and x=0

Should return 0 not -inf

* Fix logpow(x=0,m=0) 

Fix logpow(x=0,m=0) where x and m have different shapes.

* Fix Jacobian det

- add test
- add namespace
- fix docstring example

* Extend to multiple dimension array version

* Add example

* PEP8 minor fix

* initial commit of Ordered, courtesy @aseyboldt

* add composed transform (from @aseyboldt)

* add ordered logistic distr

* add test

* change from function to subclass of Categorical

* test passing on OrderedLogistic

* fix docs up

* fix to docstring

* starting transform tests

* ordered transform tests pass locally, need tests for composed transform

* fix OrderedLogistic import

* remove composed

* a little cleanup

* fix test, remove Composed Transform)

* Add release note

* Ordered transformed is not elementwise

* Fix Jacobian det

- add test
- add namespace
- fix docstring example

* Extend to multiple dimension array version

* Add example

* PEP8 minor fix

* clearn up rebase error

* Bug fix

Also extend SumTo1 so that it works in multi-dimension

* dimension fix

make sure the return jacobian_det has the right dimension: 
- if the transformation is elementwise, return jacob_det should has the same dimension as the input
- ... (continued)

7387 of 18622 relevant lines covered (39.67%)

0.4 hits per line

Source Files on job 7664.2 (PYTHON_VERSION=2.7 FLOATX='float32' RUN_PYLINT="true" TESTCMD="--durations=10 --cov-append pymc3/tests/test_distributions_random.py pymc3/tests/test_shared.py pymc3/tests/test_smc.py pymc3/tests/test_sampling.py")