R 基于外围计数的子集数据帧

我有一个如下所示的数据帧：

df <- data.frame(Site=rep(paste0('site', 1:5), 50),
           Month=sample(1:12, 50, replace=T),
           Count=(sample(1:1000, 50, replace=T)))

---

如果将计数1分配给site5，则其计数始终为a

数据。表

解决方案：

require(data.table)
set.seed(45)
df <- data.frame(Site=rep(paste0('site', 1:5), 50),
       Month=sample(1:12, 50, replace=T),
       Count=(sample(1:1000, 50, replace=T)))
df$Count[df$Site=='site5'] <- 1

dt <- data.table(df, key=c("Month", "Site"))
# set max.count per site+month
dt[, max.count := max(Count), by = list(Month)]
# get the site that is TRUE for all months it is present
d1 <- dt[, list(check = all(Count < .05 * max.count)), by = list(Month, Site)]
sites <- as.character(d1[, all(check == TRUE), by=Site][V1 == TRUE, Site])

dt.out <- dt[Site != sites][, max.count := NULL]
#       Site Month Count
#   1: site1     1   939
#   2: site1     1   939
#   3: site1     1   939
#   4: site1     1   939
#   5: site1     1   939
#  ---                  
# 196: site2    12   969
# 197: site2    12   684
# 198: site2    12   613
# 199: site2    12   969
# 200: site2    12   684

require（data.table）
种子（45）
df这里有一个
plyr
解决方案：

## df2$test is true if Count >= max(Count)*0.05 for this month
df2 <- ddply(df, .(Month), transform, test=Count>=(max(Count)*0.05))
## For each site, test$keep is true if at least one count is >= max(Count)*0.05 for this month
test <- ddply(df2, .(Site), summarise, keep=sum(test)>0)
## Subsetting
sites <- test$Site[test$keep]
df[df$Site %in% sites,]

###df2$如果计数>=max（计数）*0.05，则此月的测试为真
df2=（最大值（计数）*0.05））
##对于每个站点，如果本月至少有一个计数>=max（count）*0.05，则测试$keep为真
测试（0）
##子集
因此，删除count@RossAhmed所在站点的所有行，这应该可以做到。
df$Count[df$Site=='site2'] <- ceiling(seq(1, 1000, length.out=20))

require(data.table)
set.seed(45)
df <- data.frame(Site=rep(paste0('site', 1:5), 50),
       Month=sample(1:12, 50, replace=T),
       Count=(sample(1:1000, 50, replace=T)))
df$Count[df$Site=='site5'] <- 1

dt <- data.table(df, key=c("Month", "Site"))
# set max.count per site+month
dt[, max.count := max(Count), by = list(Month)]
# get the site that is TRUE for all months it is present
d1 <- dt[, list(check = all(Count < .05 * max.count)), by = list(Month, Site)]
sites <- as.character(d1[, all(check == TRUE), by=Site][V1 == TRUE, Site])

dt.out <- dt[Site != sites][, max.count := NULL]
#       Site Month Count
#   1: site1     1   939
#   2: site1     1   939
#   3: site1     1   939
#   4: site1     1   939
#   5: site1     1   939
#  ---                  
# 196: site2    12   969
# 197: site2    12   684
# 198: site2    12   613
# 199: site2    12   969
# 200: site2    12   684

## df2$test is true if Count >= max(Count)*0.05 for this month
df2 <- ddply(df, .(Month), transform, test=Count>=(max(Count)*0.05))
## For each site, test$keep is true if at least one count is >= max(Count)*0.05 for this month
test <- ddply(df2, .(Site), summarise, keep=sum(test)>0)
## Subsetting
sites <- test$Site[test$keep]
df[df$Site %in% sites,]