Closed aakankshaduggal closed 2 years ago
/assign @suppathak
@aakankshaduggal , Obfuscated files are uploaded in opf-datacatalog
bucket under the folder open-services-group/operate-first-data-science-community/meetup_attendees/
. Lmk if you have any feedback on it. Thanks :)
Thank you @suppathak for obfuscating the data and moving it to the opf-datacatalog bucket. Could you add an inference notebook for this data being stored in the opf-datacatalog
bucket? So we can further get started with some EDA on this data (https://github.com/aicoe-aiops/operate-first-data-science-community/issues/57)
Thanks @aakankshaduggal. I will add that. Here is an issue for it #58 .
@aakankshaduggal what would be the function of the "inference" notebook? I guess my question is, from what model is a prediction being inferred?
@MichaelClifford, by inference I did not mean a model inference, but a notebook that would confirm that the data is stored in ceph and can be used for further analysis.
After researching various methods to obfuscate attendee data and prototyping a PoC notebook for issue #27 by #33, we would now want to move forward with applying these techniques to the actual data.
The data for the meetup attendees' is generated using a google meet API and this information is shared with the organizer of the meetup after the meetup is ended. We would want to access this data and apply the researched methods for obfuscation and move this obfuscated data to a ceph s3 storage.
Acceptance Criteria -