因此,經過挖掘並嘗試不同的事情,這裏是我想出了什麼和對我有用。這個提示有點令人費解,而詳細的巴士顯然給出了確切的結果。在試圖找到答案時,我學習了矢量化的想法(赦免我的德語口音),因爲生成矢量化代碼可以將計算結果的時間縮短到大約3分鐘,而在大約96小時之後我停止計算而沒有完成。
請注意,記錄日期列表(並非每個醫生都會完成他的班次記錄)是一個簡單日期的Excel表格。記錄的時間工作時間間隔列表是日期和時間,有人開始在一列中看到病人,並且在另一列中停止看到病人。下一行將是類似的開始和停止時間和日期。
所有在文本中的變量都在德國或者德國詞的縮寫,但我希望我的意見就足以理解發生了什麼事情。此外,很多代碼都是針對特定於我的情況的問題。
特別感謝用戶PhiSeu,誰與解決方案的不同方面幫助我user3507085。
#read dates
package(lubridate)
Daten<-read.csv2(„file.csv")
#convert start dates to POSIX
Daten$Beginn<-parse_date_time(Daten$Beginn,"dmy HM",tz="CET")
#prevent overlap by adding one second
Daten$Beginn<-Daten$Beginn+1
#convert end dates to POSIX
Daten$Ende<-parse_date_time(Daten$Ende,"dmy HM",tz="CET")
#remove empty rows
Daten<-na.omit(Daten)
#create intervals in which people worked
Daten$Intervall<-interval(Daten$Beginn,Daten$Ende)
#read dates on which people worked
doku<-read.csv2(„dates.csv「,header=FALSE)
doku<-parse_date_time(doku$V1,"%d.%m.%Y",tz="cet")
#create a start time of 09 A.M. for shifts
doku<-data.frame(cbind(doku,doku+32400))
#add column names
names(doku)<-c("Datum","Beginn")
#convert to POSIX
doku$Datum<-as.POSIXct(doku$Datum,origin="1970-01-01",tz="cet")
doku$Beginn<-as.POSIXct(doku$Beginn,origin="1970-01-01",tz="cet")
#Loop to create 15 min intervals for each documented shift spanning 24 hour against which actual working hours will be checked
begin <- as.POSIXct(doku$Beginn)
# copy begin time for loop
begin_new <- begin
# create duration object
aufl <- duration(15, "mins")
# count times for loop
times <- 24*60/15
# create dataframe with begin time
Intervall <- data.frame(begin,stringsAsFactors = FALSE)
for (i in 1:times){
cat("test",i,"\n")
# save old time for interval calculation
begin_start <- begin_new
# add 15 Minutes to original time
begin_new <- begin_new + aufl
cat(begin_new,"\n")
# create an interval object between
new_dur <- interval(begin_start,begin_new)
# bind to original dataframe
Intervall <- cbind(Intervall,new_dur)
}
# Add column names
vec_names <- paste0("v",c(1:(times+1)))
colnames(Intervall) <- vec_names
#create a matrix of the number of seconds worked in each of the above 15 intervals by checking the amount of intersection between 15 intervals and documented intervals of work
test<-vector()
Tabelle<-matrix(nrow=length(doku$Beginn),ncol=times)
Tabelle[is.na(Tabelle)]<-0
for (j in 1:length(doku$Beginn)){
for (k in 1:times){
test<-as.duration(intersect(Daten$Intervall,Intervall[j,k+1]))
test[is.na(test)]<-0
test<-sum(test)
Tabelle[j,k]<-test}}
#cadd start time to the above matrix
Ausw<-data.frame(cbind(Tabelle,begin))
#convert to POSIX
Ausw$begin<-as.POSIXct(Ausw$begin,origin="1970-01-01",tz="cet")
##analysis of data
#common to all days of the week
#create labels for 15 min intervals
Labels<-c("09","09:15","09:30","09:45","10","10:15","10:30","10:45","11","11:15","11:30","11:45","12","12:15","12:30","12:45","13","13:15","13:30","13:45","14","14:15","14:30","14:45","15","15:15","15:30","15:45","16","16:15","16:30","16:45","17","17:15","17:30","17:45","18","18:15","18:30","18:45","19","19:15","19:30","19:45","20","20:15","20:30","20:45","21","21:15","21:30","21:45","22","22:15","22:30","22:45","23","23:15","23:30","23:45","00","00:15","00:30","00:45","01","01:15","01:30","01:45","02","02:15","02:30","02:45","03","03:15","03:30","03:45","04","04:15","04:30","04:45","05","05:15","05:30","05:45","06","06:15","06:30","06:45","07","07:15","07:30","07:45","08","08:15","08:30","08:45")
##analysis for weekends
#how many percent people worked on average in any of the 15 min intervals on a saturday or sunday
Wochenende<-apply(Ausw[Ausw$wtag==c(1,7),1:times],MARGIN=2,FUN=sum)
Prozent<-Wochenende/length(Ausw$begin[Ausw$wtag==c(1,7)]) /as.numeric(aufl)*100
#add labels
names(Prozent)<-Labels
#plot as barplot and add axis labels
b=barplot(Prozent,axes = F,axisnames=F,main="Durchschnittliche Arbeitsbelastung am Wochenende",sub="über 100%: Übergabezeiten",xlab="Uhrzeit",ylab="Prozent")
axis(1,at=c(b[seq(1,length(Labels),4)],b[length(b)]+diff(b)[1]),labels = c(Labels[seq(1,length(Labels),4)],"09"))
axis(2,at=seq(0,160,25),las=2)
##analysos monday to friday
Woche<-apply(Ausw[Ausw$wtag==c(2,3,4,5,6),1:times],MARGIN=2,FUN=sum)
Prozent2<-Woche/length(Ausw$begin[Ausw$wtag==c(2,3,4,5,6)]) /as.numeric(aufl)*100
#add labels
names(Prozent2)<-Labels
#plot as barplot and add axis labels
b2=barplot(Prozent2,axes = F,axisnames=F,main="Durchschnittliche Arbeitsbelastung Montag - Freitag",,xlab="Uhrzeit",ylab="Prozent「,ylim=c(0,100))
axis(1,at=c(b2[seq(1,length(Labels),4)],b2[length(b2)]+diff(b2)[1]),labels = c(Labels[seq(1,length(Labels),4)],"09"))
axis(2,at=seq(0,160,25),las=2)
請發表你的最好的嘗試代碼。謝謝。 – lrnzcig
你能提供一些示例數據嗎? 'dput(head(Daten))'的輸出將非常有用,因爲它允許我們重現您的一些工作數據。 – jdobres