SUA Outsmarting Outbreaks Challenge
Helping Tanzania, United Republic of
$12 500 USD + AWS credits
Completed (almost 2 years ago)
Prediction
817 joined
390 active
Start
06 Dec 24
Close
31 Jan 25
Reveal
01 Feb 25
Column Clarification
Help · 18 Jan 2025, 19:01 · 5
I'm confused, why is the number of unique categories in the 'Category_Health_Facility_UUID' for the train data 4 while that of the test data is 107?
Interesting observation. One experiment to conduct is to do away with the column
Because the end values for one of them is incremental for some reason. Split by '-' and get rid of the last section before joining back, and you'll get the same 4 categories in the train set.
Valid !
Yeah, thanks. You were right.
The dataset is just confusing to me, some rows have the same values for all the columns. The ID,Location,Disease,Category_Health_Facility_UUID, latitude,longitude,month,year all have the same values for all the columns
Great Observation @da_. Category could indicate a classification or grouping, possibly related to the type or category of the health facility (e.g., hospital, clinic, dispensary).