My teacher asked me to help him with the codes for analyzing the results and reply to all of you. And here is the result page for this 2020 survey.
https://ntust-mitlab.github.io/go-rank-survey-2020/go-survey-results-2020
My teacher asked me since May, but I got lazy and only have time during the summer vacation.
It is my bad it got delayed for so long. Really really sorry 
This is the linear regression pairplot from various servers.
There are some pairs that almost have no common data points, so the linear regression didn’t work well.
This is the updated result for 2020 survey
I personally find the Taiwan offline community rank quite interesting, and probably quite accurate. There is a big gap between casual players, and those who actually played but are amateurs. And the 1d to 5d group competitions are pretty easy to advance. If you participate you will advance to 5d eventually.
Thank you @Claire_Su , awesome work.
There is something a little odd near the end of the table
do you think there is a little mistake or it is the result of people’s input?
It may be caused by Gaussian Process regression. The algorithm tries to fit a curve with the survey data distribution. In the OGS-EGF GPR graph, it shows the dip in the 4d-5d dan ranking.
the old GPR mean rank table
I tried a different set of parameters to relax the boundary limit
https://ntust-mitlab.github.io/go-rank-survey-2020/go-rank-survey-results-2020-gpr-relaxed#A-table-of-rounded-mean-ranks
The curve now is more smooth, but the rank variations and uncertainty of the prediction are also increased. It will be closer to linear regression than gaussian process regression.
the new relaxed-GPR mean rank table
