assign phase of the day to each date - but fast - r

Question

I want to compare an element within a list to intervals within a data frame and assign the respective interval to that element.
In my case I want to get a phase of the day (i.e. morning,day,evening,night) for a measurement. I found the R package 'suncalc' which creates the intervals for such phases and also have a solution to assign these phases of the day. BUT this is very slow and I wonder how to do this faster.
#make a list of different days and times
times<-seq.POSIXt(from=Sys.time(),
to=Sys.time()+2*24*60*60,length.out = 50)
#load the suncalc package
library(suncalc)
#a function to get a phase for one point in time
get.dayphase<-function(x){
phases<-getSunlightTimes(date=as.Date(x,tz=Sys.timezone()),
lat=52.52,lon=13.40,
tz=Sys.timezone())
if(x<phases$nightEnd)return("night_morning")
if(x>=phases$nightEnd&x<phases$goldenHourEnd)return("morning")
if(x>=phases$goldenHourEnd&x<phases$goldenHour)return("day")
if(x>=phases$goldenHour&x<phases$night)return("evening")
if(x>=phases$night)return("night_evening")
}
#use sapply to get a phase for each point in time of the list
df=data.frame(time=times,dayphase=sapply(times,get.dayphase))
the desired but slow result:
head(df)
time dayphase
1 2019-09-05 16:12:08 day
2 2019-09-05 17:10:55 day
3 2019-09-05 18:09:41 day
4 2019-09-05 19:08:28 evening
5 2019-09-05 20:07:14 evening
6 2019-09-05 21:06:01 evening
Basically, this is what I want. But it is too slow when I run it on a lot of points in time. getSunlightTimes() can also take a list of dates and returns a data table, but I have no idea how to handle this to get the desired result.
Thanks for your help

Answer 1

What is slowing your process down is most likely the sapply function, which is basically a hidden for loop.
To improve perform you need to vectorize your code. The getSunlightTimes can take vector of dates. Also, instead of using a series of if statements the case_when function from the dplyr package simplifies the code and should reduces the number of logic operations.
library(dplyr)
times<-seq.POSIXt(from=Sys.time(),
to=Sys.time()+2*24*60*60,length.out = 50)
library(suncalc)
#a function to get phases for all of the times
phases<-getSunlightTimes(as.Date(times),
lat=52.52,lon=13.40,
tz=Sys.timezone(),
keep = c("nightEnd", "goldenHourEnd", "goldenHour", "night"))
dayphase<-case_when(
times < phases$nightEnd ~ "night_morning",
times < phases$goldenHourEnd ~ "morning",
times < phases$goldenHour ~ "day",
times < phases$night ~ "evening",
TRUE ~ "night_evening"
)
This should provide a significant improvement. Additional performance improvements are possible, if you have a large number times on each day. If this is the case, calculate the phases dataframe once each day and then use this result as a lookup table for the individual times.