-
Notifications
You must be signed in to change notification settings - Fork 186
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
Included ChemEnvFingerprint #86
Conversation
@@ -106,6 +106,26 @@ def test_op_site_fingerprint(self): | |||
self.assertAlmostEqual(int(1000 * ops[opsf.feature_labels().index( | |||
'bcc CN_8')] + 0.5), 955) | |||
|
|||
def test_chemenv_site_fingerprint(self): | |||
cefp = ChemEnvSiteFingerprint.from_preset('multi_weights') |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you change the multi_weights test to return something different from the simple test? e.g., a structure for which the local env is not perfect. Otherwise, the test cannot distinguish whether the multi-weight strategy is doing the right thing.
One simple way to do this is to distort the CsCl structure and then make sure that the simple strategy still gives 1 but the multi strategy gives a value between, say, 0.8 and 1
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(but not exactly 1 for the latter)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
a better way would be to actually add a distorted structure to the test files. This is probably going to come in handy for testing the other site/structure fingerprints as well.
I am just going to pull this for now since I'm doing the matminer release and add an issue for revising the test |
No description provided.