I’m curious how the “cbg_poi” column is calculated for POIs that cover several cbgs. Canals, for example, are very long and cross several cbgs. How is “cbg_poi” determined in this case?
@Youngjae_Won_Arizona_State_University SafeGraph provides latitude and longitude centroid in Places. This centroid is used to assign poi_cbg.
These lat and long tell us the general center of the POI. Canals are an edge case but the CBG in the poi_cbg column would show the CBG where the canal’s center is.
Got it, thank you! Could you also explain how the distance_from_home is calculated? Is it the distance between the POI centroid and the CBG centroid, or the distance between the two polygons’ nearest points?
Distance_from_home is the median distance from home to the POI in meters for the visitors we have identified a home location.
This is calculated by taking the haversine distance between the visitor’s home geohash-7 and the location of the POI for each visit. We then take the median of all of the home-POI distance pairs.
I understand, but each home-POI distance pair should be calculated to take the median. How is it calculated?
Can you clarify your question? I believe this section may answer your question.
I recommend taking a look at our docs which have detailed explanations about the columns in our various datasets.