loop to something more R
Been using SO as a resource constantly for my work. Thanks for holding together such a great community.
I'm trying to do something kinda complex, and the only way I can think to do it right now is with a pair of nested for-loops (I know that's frowned upon in R)... I have records of three million-odd course enrollments: student UserID's paired with CourseID's. In each row, there's a bunch of data including start/end dates and scores and so forth. What I need to do is, for each enrollment, calculate the average score for that user across the courses she's taken before the course in the enrollment.
The code I'm using for the for-loop follows:
data$Mean.Prior.Score <- 0
for (i in as.numeric(rownames(data)) {
sum <- 0
count <- 0
for (j in as.numeric(rownames(data[data$UserID == data$UserID[i],]))) {
if (data$Course.End.Date[j] < data$Course.Start.Date[i]) {
sum <- sum + data$Score[j]
count <- count + 1
}
}
if (count != 0)
data$Mean.Prior.Score[i] <- sum / count
}
I'm pretty sure this would work, but it runs incredibly slowly... my data frame has over three million rows, but after a good 10 minutes of chugging, the outer loop has only run through 850 of the records. That seems way slower than the time complexity would suggest, especially given that each user has only 5 or 6 courses to her name on average.
Oh, and I should mention that I converted the date strings with as.POSIXct() before running the loop, so the date comparison step shouldn't be too terribly slow...
There's got to be a better way to do this... any suggestions?
Edit: As per mnel's request... finally got dput to play nicely. Had to add control = NULL . Here 'tis:
structure(list(Username = structure(1:20, .Label = c("100225",
"100226", "100228", "1013170", "102876", "105796", "106753",
"106755", "108568", "109038", "110150", "110200", "110350", "111873",
"111935", "113579", "113670", "117562", "117869", "118329"), class = "factor"),
User.ID = c(2313737L, 2314278L, 2314920L, 9708829L, 2325896L,
2315617L, 2314644L, 2314977L, 2330148L, 2315081L, 2314145L,
2316213L, 2317734L, 2314363L, 2361187L, 2315374L, 2314250L,
2361507L, 2325592L, 2360182L), Course.ID = c(2106468L, 2106578L,
2106493L, 5426406L, 2115455L, 2107320L, 2110286L, 2110101L,
2118574L, 2106876L, 2110108L, 2110058L, 2109958L, 2108222L,
2127976L, 2106638L, 2107020L, 2127451L, 2117022L, 2126506L
), Course = structure(c(1L, 7L, 10L, 15L, 11L, 19L, 4L, 6L,
3L, 12L, 2L, 9L, 17L, 8L, 20L, 18L, 13L, 16L, 5L, 14L), .Label = c("ACCT212_A",
"BIOS200_N", "BIS220_T", "BUSN115_A", "BUSN115_T", "CARD205_A",
"CIS211_A", "CIS275_X", "CIS438_S", "ENGL112_A", "ENGL112_B",
"ENGL227_K", "GM400_A", "GM410_A", "HUMN232_M", "HUMN432_W",
"HUMN445_A", "MATH100_X", "MM575_A", "PSYC110_Y"), class = "factor"),
Course.Start.Date = structure(c(1098662400, 1098662400, 1098662400,
1309737600, 1099267200, 1098662400, 1099267200, 1099267200,
1098662400, 1098662400, 1099267200, 1099267200, 1099267200,
1098662400, 1104105600, 1098662400, 1098662400, 1104105600,
1098662400, 1104105600), class = c("POSIXct", "POSIXt"), tzone = "GMT"),
Term.ID = c(12056L, 12056L, 12056L, 66282L, 12057L, 12056L,
12057L, 12057L, 12056L, 12056L, 12057L, 12057L, 12057L, 12056L,
13469L, 12056L, 12056L, 13469L, 12056L, 13469L), Term.Name = structure(c(2L,
2L, 2L, 4L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 3L, 2L,
2L, 3L, 2L, 3L), .Label = c("Fall 2004", "Fall 2004 Session A",
"Fall 2004 Session B", "Summer Session A 2011"), class = "factor"),
Term.Start.Date = structure(c(1L, 1L, 1L, 4L, 2L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 2L, 1L, 3L, 1L, 1L, 3L, 1L, 3L), .Label = c("2004-10-21",
"2004-10-28", "2004-12-27", "2011-06-26"), class = "factor"),
Score = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.125,
0, 0, 0, 0, 0), First.Course.Date = structure(c(1L, 1L, 1L,
4L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 3L, 1L, 1L, 3L,
1L, 3L), .Label = c("2004-10-25", "2004-11-01", "2004-12-27",
"2011-07-04"), class = "factor"), First.Term.Date = structure(c(1L,
1L, 1L, 4L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 3L, 1L,
1L, 3L, 1L, 3L), .Label = c("2004-10-21", "2004-10-28", "2004-12-27",
"2011-06-26"), class = "factor"), First.Timer = c(TRUE, TRUE,
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,
TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE), Course.Code = structure(c(1L,
6L, 9L, 13L, 9L, 17L, 4L, 5L, 3L, 10L, 2L, 8L, 15L, 7L, 18L,
16L, 11L, 14L, 4L, 12L), .Label = c("ACCT212", "BIOS200",
"BIS220", "BUSN115", "CARD205", "CIS211", "CIS275", "CIS438",
"ENGL112", "ENGL227", "GM400", "GM410", "HUMN232", "HUMN432",
"HUMN445", "MATH100", "MM575", "PSYC110"), class = "factor"),
Course.End.Date = structure(c(1L, 1L, 1L, 4L, 2L, 1L, 2L,
2L, 1L, 1L, 2L, 2L, 2L, 1L, 3L, 1L, 1L, 3L, 1L, 3L), .Label = c("2004-12-19",
"2005-02-27", "2005-03-26", "2011-08-28"), class = "factor")), .Names = c("Username",
"User.ID", "Course.ID", "Course", "Course.Start.Date", "Term.ID",
"Term.Name", "Term.Start.Date", "Score", "First.Course.Date",
"First.Term.Date", "First.Timer", "Course.Code", "Course.End.Date"
), row.names = c(NA, 20L), class = "data.frame")
I found that data.table worked well.
# Create some data.
library(data.table)
set.seed(1)
n=3e6
numCourses=5 # Average courses per student
data=data.table(UserID=as.character(round(runif(n,1,round(n/numCourses)))),course=1:n,Score=runif(n),CourseStartDate=as.Date('2000-01-01')+round(runif(n,1,365)))
data$CourseEndDate=data$CourseStartDate+round(runif(n,1,100))
setkey(data,UserID)
# test=function(CourseEndDate,Score,CourseStartDate) sapply(CourseStartDate, function(y) mean(Score[y>CourseEndDate]))
# I vastly reduced the number of comparisons with a better "test" function.
test2=function(CourseEndDate,Score,CourseStartDate) {
o.end = order(CourseEndDate)
run.avg = cumsum(Score[o.end])/seq_along(CourseEndDate)
idx=findInterval(CourseStartDate,CourseEndDate[o.end])
idx=ifelse(idx==0,NA,idx)
run.avg[idx]
}
system.time(data$MeanPriorScore<-data[,test2(CourseEndDate,Score,CourseStartDate),by=UserID]$V1)
# For three million courses, at an average of 5 courses per student:
# user system elapsed
# 122.06 0.22 122.45
Running a test to see if it looks the same as your code:
set.seed(1)
n=1e2
data=data.table(UserID=as.character(round(runif(n,1,1000))),course=1:n,Score=runif(n),CourseStartDate=as.Date('2000-01-01')+round(runif(n,1,365)))
data$CourseEndDate=data$CourseStartDate+round(runif(n,1,100))
setkey(data,UserID)
data$MeanPriorScore<-data[,test2(CourseEndDate,Score,CourseStartDate),by=UserID]$V1
data["246"]
# UserID course Score CourseStartDate CourseEndDate MeanPriorScore
#1: 246 54 0.4531314 2000-08-09 2000-09-20 0.9437248
#2: 246 89 0.9437248 2000-02-19 2000-03-02 NA
# A comparison with your for loop (slightly modified)
data$MeanPriorScore.old<-NA # Set to NaN instead of zero for easy comparison.
# I think you forgot a bracket here. Also, There is no need to work with the rownames.
for (i in seq(nrow(data))) {
sum <- 0
count <- 0
# I reduced the complexity of figuring out the vector to loop through.
# It will result in the exact same thing if there are no rownames.
for (j in which(data$UserID == data$UserID[i])) {
if (data$CourseEndDate[j] <= data$CourseStartDate[i]) {
sum <- sum + data$Score[j]
count <- count + 1
}
}
# I had to add "[i]" here. I think that is what you meant.
if (count != 0) data$MeanPriorScore.old[i] <- sum / count
}
identical(data$MeanPriorScore,data$MeanPriorScore.old)
# [1] TRUE
This seems to be what you want
library(data.table)
# create a data.table object
DT <- data.table(data)
# key by userID
setkeyv(DT, 'userID')
# for each userID, where the Course.End.Date < Course.Start.Date
# return the mean score
# This is too simplistic
# DT[Course.End.Date < Course.Start.Date,
# list(Mean.Prior.Score = mean(Score)) ,
# by = list(userID)]
As per @jorans comment, this will be more complex than the code above.
This is only an outline of what I think a solution might entail. I'm going to use plyr just to illustrate the steps needed, for simplicity.
Let's just restrict ourselves to the case of one student . If we can calculate this for one student, extending it with some sort of split-apply will be trivial.
So let's suppose we have scores for a particular student, sorted by course end date:
d <- sample(seq(as.Date("2011-01-01"),as.Date("2011-01-31"),by = 1),100,replace = TRUE)
dat <- data.frame(date = sort(d),val = rnorm(100))
First, I think you'd need to summarise this by date and then calculate the cumulative running mean:
dat_sum <- ddply(dat,.(date),summarise,valsum = sum(val),n = length(val))
dat_sum$mn <- with(dat_sum,cumsum(valsum) / cumsum(n))
Finally, you'd merge these values back into the original data with the duplicate dates:
dat_merge <- merge(dat,dat_sum[,c("date","mn")])
I could probably write something that does this in data.table using an anonymous function to do all those steps, but I suspect others may be better able to do something that will be concise and fast. (In particular, I don't recommend actually tackling this with plyr , as I suspect it will still be extremely slow.)
链接地址: http://www.djcxy.com/p/11082.html上一篇: MongoDB中的查询
下一篇: 循环到更多的R