Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
graphtool
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
38
Issues
38
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Operations
Operations
Environments
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Tiago Peixoto
graphtool
Commits
7fa7f12a
Commit
7fa7f12a
authored
Apr 17, 2017
by
Tiago Peixoto
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
inference.rst: Update docstrings
parent
f6921911
Pipeline
#306
passed with stage
in 174 minutes and 24 seconds
Changes
1
Pipelines
1
Hide whitespace changes
Inline
Sidebyside
Showing
1 changed file
with
14 additions
and
14 deletions
+14
14
doc/demos/inference/inference.rst
doc/demos/inference/inference.rst
+14
14
No files found.
doc/demos/inference/inference.rst
View file @
7fa7f12a
...
...
@@ 459,8 +459,8 @@ case of the `C. elegans` network we have
.. testoutput:: modelselection
:options: +NORMALIZE_WHITESPACE
Nondegreecorrected DL: 84
80.7594
...
Degreecorrected DL: 82
56.6074
...
Nondegreecorrected DL: 84
95.7603
...
Degreecorrected DL: 82
40.8139
...
Since it yields the smallest description length, the degreecorrected
fit should be preferred. The statistical significance of the choice can
...
...
@@ 486,7 +486,7 @@ fits. In our particular case, we have
.. testoutput:: modelselection
:options: +NORMALIZE_WHITESPACE
ln Λ: 2
24.1520
...
ln Λ: 2
54.9463
...
The precise threshold that should be used to decide when to `reject a
hypothesis <https://en.wikipedia.org/wiki/Hypothesis_testing>`_ is
...
...
@@ 513,12 +513,12 @@ example, for the American football network above, we have:
.. testoutput:: modelselection
:options: +NORMALIZE_WHITESPACE
Nondegreecorrected DL:
1733.525685
...
Degreecorrected DL:
1788.421052
...
ln Λ:
54.895367
...
Nondegreecorrected DL:
1733.5256
...
Degreecorrected DL:
1780.7525
...
ln Λ:
47.2268
...
Hence, with a posterior odds ratio of :math:`\Lambda \sim e^{
55
} \sim
10^{2
3
}` in favor of the nondegreecorrected model, it seems like the
Hence, with a posterior odds ratio of :math:`\Lambda \sim e^{
47
} \sim
10^{2
0
}` in favor of the nondegreecorrected model, it seems like the
degreecorrected variant is an unnecessarily complex description for
this network.
...
...
@@ 814,8 +814,8 @@ network as above.
.. testoutput:: nestedmodelaveraging
Change in description length:
18.71364
9...
Number of accepted vertex moves: 4
4580
Change in description length:
6.988
9...
Number of accepted vertex moves: 4
5597
Similarly to the the nonnested case, we can use
:func:`~graph_tool.inference.mcmc_equilibrate` to do most of the boring
...
...
@@ 1145,8 +1145,8 @@ approach for the same network, using the nested model.
.. testoutput:: modelevidence
Model evidence for deg_corr = True: 5
45.1999... (mean field), 713.7311...
(Bethe)
Model evidence for deg_corr = False: 5
49.6099... (mean field), 613.5343...
(Bethe)
Model evidence for deg_corr = True: 5
18.064521707 (mean field), 770.951332583
(Bethe)
Model evidence for deg_corr = False: 5
33.357785329 (mean field), 681.561365629
(Bethe)
The results are similar: If we consider the most accurate approximation,
the nondegreecorrected model possesses the largest evidence. Note also
...
...
@@ 1386,8 +1386,8 @@ above).
..
testoutput
::
missing

edges
likelihood

ratio
for
(
101
,
102
):
0.3
7
...
likelihood

ratio
for
(
17
,
56
):
0.6
2
...
likelihood

ratio
for
(
101
,
102
):
0.3
6
...
likelihood

ratio
for
(
17
,
56
):
0.6
3
...
From
which
we
can
conclude
that
edge
:
math
:`(
17
,
56
)`
is
more
likely
than
:
math
:`(
101
,
102
)`
to
be
a
missing
edge
.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment