Occurence Rate

Archived notebook using Python and R

Notes

It is hard to remove duplicate events when combining multiple datasets with different τ. So when using the combined dataset, the occurence rate would be overestimated.

Code
using DrWatson
@quickactivate
include(srcdir("main.jl"))
easy_save (generic function with 2 methods)
Code
j_events_taus = load_taus(60:-10:20)
┌ Warning: automatically converting Arrow.Timestamp with precision = NANOSECOND to `DateTime` which only supports millisecond precision; conversion may be lossy; to avoid converting, pass `Arrow.Table(source; convert=false)
└ @ Arrow /Users/zijin/.julia/packages/Arrow/5pHqZ/src/eltypes.jl:273
Number of events: 26274
Number of events: 28333
Number of events: 30669
Number of events: 34057
Number of events: 38498
5×2 DataFrame
Row tau nrow
Int64 Int64
1 20 38498
2 30 27886
3 40 21342
4 50 17995
5 60 14302