I decreased the sampling interval to reduce the base size from 40,000 to 10,000 so that I could then use the DBScan routine.
Now another problem has arisen: I want to analyze the "Noisy Samples" points and I need to calculate the distance to the nearest cluster, ie (a) the distance to the nearest point and know (b) which cluster this point belongs to . I believe these data are available because the algorithm calculates this distance, but only marks the point that has that distance greater than the EPS as "Noisy Samples". I believe the routine needs to be changed because it has only the output attributes "core_sample_indices_", "components_" and "labels_" are available. Can you help me? Att., Mauricio Reis 2018-05-18 19:29 GMT-03:00 Shane Grigsby <shane.grig...@colorado.edu>: > Hi Mauricio, > You can also use OPTICS in DBSCAN mode. The pull request is here if you'd > like to clone it: > > https://github.com/scikit-learn/scikit-learn/pull/1984 > > Running ~40,000 points in three dimensions takes about a minute. See the > example page here for how to do the DBSCAN extraction: > > https://github.com/espg/scikit-learn/blob/2eac9fbf67b2715e11 > fdedfbb63bcdb56a80e216/examples/cluster/plot_optics.py > > Cheers, > Shane > > On 05/17, Mauricio Reis wrote: > >> I'm not used to the terms used here. So I understood that the package had >> memory management, which was removed. But you could make the code >> available >> with memory management implementations. Is it?! :-) >> The problem is that I do not know what I would do with the code, because I >> only know how to work with the SciKitLearn package ready. :-( >> >> Att., >> Mauricio Reis >> >> 2018-05-16 20:33 GMT-03:00 Joel Nothman <joel.noth...@gmail.com>: >> >> Implemented in a previous version of #10280 >>> <https://github.com/scikit-learn/scikit-learn/pull/10280>, but removed >>> for now to simplify reviews >>> <https://github.com/scikit-learn/scikit-learn/pull/10280#pul >>> lrequestreview-95622713>. >>> If others would like to review #10280, I'm happy to follow up with the >>> changes requested here, which have already been implemented by Aman >>> Dalmia >>> and myself. >>> >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn@python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >>> >>> >>> > _______________________________________________ >> scikit-learn mailing list >> scikit-learn@python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > > > -- > *PhD candidate & Research Assistant* > *Cooperative Institute for Research in Environmental Sciences (CIRES)* > *University of Colorado at Boulder* > _______________________________________________ > scikit-learn mailing list > scikit-learn@python.org > https://mail.python.org/mailman/listinfo/scikit-learn >
_______________________________________________ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn
