New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MMHC Structure Estimator #721

Open
wants to merge 3 commits into
base: dev
from

Conversation

Projects
None yet
4 participants
@chrisittner
Contributor

chrisittner commented Aug 20, 2016

The MMHC algorithm for learning BN structure. MMHC consists in a constraint-based algorithm for BN skeleton learning (MMPC) and then uses score-based local search (hill climbing with tabu list) to orient the edges of the skeleton.

Implementation according to Algorithm 1, 2, and 3 in the paper. I will still add some of the perfomance optimizations from Section 6 of the paper.

-> This needs to be merged after PR #720, because it uses the test_conditional_independence-method from there. I'll rebase once #720 is merged. Until then tests will fail.

Reference

Tsamardinos et al., The max-min hill-climbing Bayesian network structure learning algorithm (2005),
http://www.dsl-lab.org/supplements/mmhc_paper/paper_online.pdf

@chrisittner chrisittner changed the title from [WIP] MMHC Structure Estimator to MMHC Structure Estimator Aug 20, 2016

def tearDown(self):
del self.data1
del self.est1

This comment has been minimized.

@yashu-seth

yashu-seth Aug 21, 2016

Member

@chrisittner I think tests for mmpc should also be added.

nodes = self.state_names.keys()
def is_independent(X, Y, Zs):

This comment has been minimized.

@yashu-seth

yashu-seth Aug 21, 2016

Member

@chrisittner Can't this also be moved to the base class like the test_conditional_independence method?

This comment has been minimized.

@chrisittner

chrisittner Aug 24, 2016

Contributor

Yep. Will fix.

@khalibartan

This comment has been minimized.

Member

khalibartan commented Sep 12, 2016

@chrisittner When will you finish up this work ?

@ankurankan ankurankan self-assigned this Nov 17, 2016

@ankurankan ankurankan referenced this pull request Nov 17, 2016

Open

Finish PR #721 #775

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment