Undocumented parameters in dispersion #6183
Conversation
|
@rossbar What do you think? |
| If normalized is True (default), try out different values of alpha, b and, c to obtain maximum | ||
| performance of normalized dispersion. |
There was a problem hiding this comment.
In this case I think the best thing to do would be to explicitly describe how the parameters are used in the embeddedness normalization.
There was a problem hiding this comment.
" To strengthen the performance of a normalized dispersion, the nodes can be ranked by the order of the function, (disp(u, v) + b)α/(emb(u, v) + c). Searching over choices of alpha, b, and, c leads to maximum performance." How about this?
There was a problem hiding this comment.
I went ahead and pushed up a suggested wording which includes the calculation explicitly as you've proposed (with rst formatting).
There was a problem hiding this comment.
Great. Thanks for your help!
|
Thanks @Qudirah! |
:) |
* fixes networkx#6036 * test load centrality * test dispersion * test dispersion * dispersion test * test dispersion * bug-fixes-for-issue-6088 * deleted * bugfix for 6111 * Add suggestion for parameter description. Co-authored-by: Ross Barnowski <rossbar@berkeley.edu>
* fixes networkx#6036 * test load centrality * test dispersion * test dispersion * dispersion test * test dispersion * bug-fixes-for-issue-6088 * deleted * bugfix for 6111 * Add suggestion for parameter description. Co-authored-by: Ross Barnowski <rossbar@berkeley.edu>
* fixes networkx#6036 * test load centrality * test dispersion * test dispersion * dispersion test * test dispersion * bug-fixes-for-issue-6088 * deleted * bugfix for 6111 * Add suggestion for parameter description. Co-authored-by: Ross Barnowski <rossbar@berkeley.edu>
fixes for #6111