我有一个矢量:
keyword_list = [x.word for x in spark.read.load(file).collect()]
keep_words_udf = udf(lambda word_list: [ word for word in word_list if word in keyword_list], ArrayType(StringType()) )
我想获得每次运行相等值的开始和结束索引:
a <- c(1, 1, 0, 0, 1, 2, 0, 0)
答案 0 :(得分:12)
来自基地R的解决方案。
a <- c(1,1,0,0,1,2,0,0)
# Get run length encoding
b <- rle(a)
# Create a data frame
dt <- data.frame(number = b$values, lengths = b$lengths)
# Get the end
dt$end <- cumsum(dt$lengths)
# Get the start
dt$start <- dt$end - dt$lengths + 1
# Select columns
dt <- dt[, c("number", "start", "end")]
# Sort rows
dt <- dt[order(dt$number), ]
dt
# number start end
#2 0 3 4
#5 0 7 8
#1 1 1 2
#3 1 5 5
#4 2 6 6
这是一个使用with
来使代码更简洁的解决方案。
with(rle(a), data.frame(number = values,
start = cumsum(lengths) - lengths + 1,
end = cumsum(lengths))[order(values),])
# number start end
#2 0 3 4
#5 0 7 8
#1 1 1 2
#3 1 5 5
#4 2 6 6
答案 1 :(得分:2)
使用dplyr
rleid
和data.table
library(data.table)
library(dplyr)
a=c(1,1,0,0,1,2,0,0)
df=data.frame(number=c(1,1,0,0,1,2,0,0))
df$Id=data.table::rleid(df$number)
df$rowname=seq(1:length(a))
df%>%group_by(Id,number)%>%summarise(start=first(rowname),end=last(rowname))%>%arrange(number)
# Groups: Id [5]
Id number start end
<int> <dbl> <int> <int>
1 2 0 3 4
2 5 0 7 8
3 1 1 1 2
4 3 1 5 5
5 4 2 6 6
答案 2 :(得分:1)
在基础R中使用for循环的解决方案:
a <- c(1, 1, 0, 0, 1, 2, 0, 0)
start <- 1
res <- data.frame()
v <- c(a, -1) # add number that is different from all other numbers
for (index in 1:(length(v) - 1)) {
if (v[index] != v[index + 1]) {
res <- rbind(res,
data.frame(element = v[index], start = start, stop = index))
start <- index + 1
}
}
给出了:
element start stop
1 1 1 2
2 0 3 4
3 1 5 5
4 2 6 6
5 0 7 8