Closed ahdilmore closed 3 years ago
Great idea!
On (Feb-22-21|11:37), Hazel Dilmore wrote:
@ahdilmore commented on this pull request.
- rounded_m2 = round(m2, 5)
- rounded_p_val = round(p_val, 5)
Sounds good! I think I would move this here: https://urldefense.com/v3/__https://github.com/biocore/emperor/pull/793/commits/4e8faf46a2ce4dc5424e3c1dc7f6368db659a9a6*diff-de5ac40c027777d003fcb3f1530a2f8f35df374f22ea0e3b48377493948d3048R107__;Iw!!Mih3wA!WwsobR0rYboTkxbnMDNYpVGrm28IWUYmlPGxR8C116pnGviU6Cea0iDWxgLHayg$
-- You are receiving this because you commented. Reply to this email directly or view it on GitHub: https://urldefense.com/v3/__https://github.com/qiime2/q2-diversity/pull/305*discussion_r580535255__;Iw!!Mih3wA!WwsobR0rYboTkxbnMDNYpVGrm28IWUYmlPGxR8C116pnGviU6Cea0iDWk6M0VQI$
Hi @ahdilmore! Is this ready for review? I didn't want step on your toes, in case you were still working on things.
Yes @thermokarst , this is ready for review. Thank you!
Addressing: https://github.com/qiime2/q2-diversity/issues/210
procrustes_analysis previously did not output the M^2 statistic or an associated p-value. This PR outputs disparity_results, of the new type M2Calc (which can be converted to a pandas dataframe), containing the M^2 value and the p-value of this statistic. The p-value is computed by calculating the M^2 value after switching the row order one input matrix in Monte Carlo simulations, then calculating the number of reordered matrices have a lower M^2 value than the true matrices.
The M^2 value and p-value can also be displayed in emperor via the info-attribute (see here): https://github.com/biocore/emperor/pull/793