在R中使用正则表达式从字符串中获取数字
所以正则表达式是我一直在努力学习的东西/从来没有花适当的时间学习。在本例中，我有一个R向量，其中包含以下格式的棒球数据：在R中使用正则表达式从字符串中获取数字,r,regex,R,Regex,所以正则表达式是我一直在努力学习的东西/从来没有花适当的时间学习。在本例中，我有一个R向量，其中包含以下格式的棒球数据： hit_vector = c("", "Batted ball speed <b>104 mph</b>; distance of <b>381 feet</b>; launch angle of <b>38 degrees</b>.", "Ball was hit at <b>67 mp
hit_vector = c("", "Batted ball speed <b>104 mph</b>; distance of <b>381
feet</b>; launch angle of <b>38 degrees</b>.",
"Ball was hit at <b>67 mph</b>.", "", "Ball left the bat at <b>107 mph</b> and traveled a distance of <b>412 feet</b>.",
"Batted ball speed <b>71 mph</b>.", "Ball left the bat at <b>94 mph</b> and traveled a distance of <b>287 feet</b>.",
"", "", "Batted ball speed <b>64 mph</b>.")
> hit_vector
[1] ""
[2] "Batted ball speed <b>104 mph</b>; distance of <b>381 feet</b>; launch angle of <b>38 degrees</b>."
[3] "Ball was hit at <b>67 mph</b>."
[4] ""
[5] "Ball left the bat at <b>107 mph</b> and traveled a distance of <b>412 feet</b>."
[6] "Batted ball speed <b>71 mph</b>."
[7] "Ball left the bat at <b>94 mph</b> and traveled a distance of <b>287 feet</b>."
[8] ""
[9] ""
[10] "Batted ball speed <b>64 mph</b>."
编辑2：我不确定每个统计数据会有多少位数。例如，英里/小时可以超过100（3位），也可以小于10（1位）。从
stringrstrudata.frame(
speed=str_extract(hit_vector, "(\\d+)(?=\\s+mph)"),
distance=str_extract(hit_vector, "(\\d+)(?=\\s+feet)"),
degrees=str_extract(hit_vector, "(\\d+)(?=\\s+degrees)")
)
# speed distance degrees
# 1 <NA> <NA> <NA>
# 2 104 381 38
# 3 67 <NA> <NA>
# 4 <NA> <NA> <NA>
# 5 107 412 <NA>
# 6 71 <NA> <NA>
# 7 94 287 <NA>
# 8 <NA> <NA> <NA>
# 9 <NA> <NA> <NA>
# 10 64 <NA> <NA>
data.frame(
速度=str_提取（命中向量，（\\d+（=\\s+mph）），
距离=str_提取（命中向量，“（\\d+（=\\s+英尺）”），
度=str\u提取（命中向量，“（\\d+（=\\s+度）”）
)
#速度距离度
# 1
# 2 104 381 38
# 3 67
# 4
# 5 107 412
# 6 71
# 7 94 287
# 8
# 9
# 10 64
\\d\\d+（？=）\\s+mph英尺度的模式，而不捕获这些字符串。使用基本r:
read.table(text=gsub("\\D+"," ",hit_vector),fill=T,blank.lines.skip = F)
V1 V2 V3
1 NA NA NA
2 104 381 38
3 67 NA NA
4 NA NA NA
5 107 412 NA
6 71 NA NA
7 94 287 NA
8 NA NA NA
9 NA NA NA
10 64 NA NA
在这里，只需删除所有非数字的内容，即\\D+
，然后读取数据，使用FILL=T
且不跳过
考虑到您在下面的评论，我们需要重新整理我们的数据：
hit_vector1=c(hit_vector,"traveled a distance of <b>412 feet</b>.")
#Take the numbers together with their respective measurements.
a=gsub(".*?(\\d+).*?(mph|feet|degree).*?"," \\1 \\2",hit_vector1)
#Remove the </b>
b=sub("<[/]b>.","",a)
## Any element that does not contain the measurements, invoke an NA
fun=function(x){y=-grep(x,b);b<<-replace(b,y,paste(b[y],NA,x))}
invisible(sapply(c("mph","feet","degrees"),fun))
## Break the line after each measurement and read in a table format
e=gsub("([a-z])\\s","\\1\n",b)
unstack(read.table(text=e))
degrees feet mph
1 NA NA NA
2 38 381 104
3 NA NA 67
4 NA NA NA
5 NA 412 107
6 NA NA 71
7 NA 287 94
8 NA NA NA
9 NA NA NA
10 NA NA 64
11 NA 412 NA
hit_vector1=c（hit_vector，“移动了412英尺的距离”）
#将这些数字与其各自的测量值一起记录。
a=gsub（“.*？（\\d+）.*”（英里/小时英尺/度）。*？”，“\\1\\2”，点击向量1）
#移除
b=子（“.”，“，a）
##任何不包含测量值的元素都会调用NA
fun=函数（x）{y=-grep（x，b）；b如果你不介意用红墨水：
library(tidyverse)
tibble(x=hit_vector) %>%
separate(x,c("speed","distance","degrees"),"</b>") %>%
mutate_all(parse_number)
# # A tibble: 10 x 3
# speed distance degrees
# <dbl> <dbl> <dbl>
# 1 NA NA NA
# 2 104 381 38
# 3 67 NA NA
# 4 NA NA NA
# 5 107 412 NA
# 6 71 NA NA
# 7 94 287 NA
# 8 NA NA NA
# 9 NA NA NA
# 10 64 NA NA
库（tidyverse）
TIBLE（x=命中向量）%>%
分离（x，c（“速度”、“距离”、“度”），”）%>%
全部变异（解析编号）
##tibble:10 x 3
#速度距离度
#
#1NA NA NA
# 2 104 381 38
#367NA
#4娜娜娜娜
#5107412NA
#6 71 NA
#794287 NA
#8NA NA NA
#9娜娜娜娜
#1064NA
在baseR
中还有一个（使用）：
我对你的评价太高了。谢谢你的资源，真的很感激！你需要小心，第二排有104381和38@Onyambu谢谢，这是个好消息，我已经更新了answer@Jan谢谢，你第二次告诉我：）为了简洁起见接受了这个答案，但这个和下面的答案只使用了基本的r are都很好。谢谢。这很好，但是如果hit_向量中有一行只有距离（英尺）数据，比如“行驶了412英尺的距离”，这种方法会将412放在第一列（英里/小时），而不是第二列parse_number
推送警告，删除所有非数字文本，并返回准确的数字。绝妙提示！
hit_vector1=c(hit_vector,"traveled a distance of <b>412 feet</b>.")
#Take the numbers together with their respective measurements.
a=gsub(".*?(\\d+).*?(mph|feet|degree).*?"," \\1 \\2",hit_vector1)
#Remove the </b>
b=sub("<[/]b>.","",a)
## Any element that does not contain the measurements, invoke an NA
fun=function(x){y=-grep(x,b);b<<-replace(b,y,paste(b[y],NA,x))}
invisible(sapply(c("mph","feet","degrees"),fun))
## Break the line after each measurement and read in a table format
e=gsub("([a-z])\\s","\\1\n",b)
unstack(read.table(text=e))
degrees feet mph
1 NA NA NA
2 38 381 104
3 NA NA 67
4 NA NA NA
5 NA 412 107
6 NA NA 71
7 NA 287 94
8 NA NA NA
9 NA NA NA
10 NA NA 64
11 NA 412 NA
library(tidyverse)
tibble(x=hit_vector) %>%
separate(x,c("speed","distance","degrees"),"</b>") %>%
mutate_all(parse_number)
# # A tibble: 10 x 3
# speed distance degrees
# <dbl> <dbl> <dbl>
# 1 NA NA NA
# 2 104 381 38
# 3 67 NA NA
# 4 NA NA NA
# 5 107 412 NA
# 6 71 NA NA
# 7 94 287 NA
# 8 NA NA NA
# 9 NA NA NA
# 10 64 NA NA
# list of patterns
patterns <- c("(\\d+)(?=\\s*mph)", "(\\d+)(?=\\s*feet)", "(\\d+)(?=\\s*degrees)")
results <- lapply(patterns, function(pattern) {
unlist(lapply(hit_vector, function(item) {
result <- as.numeric(regmatches(item, regexpr(pattern, item, perl = TRUE)))
if (identical(result, numeric(0))) return(NA)
else return(result)
}))
})
# build the dataframe from the list
df <- as.data.frame(do.call(cbind, results))
colnames(df) <- c("speed", "distance", "degrees")
result <- lapply(hit_vector, function(string) {
unlist(lapply(patterns, function(pattern) {
result <- as.numeric(regmatches(string, regexpr(pattern, string, perl = TRUE)))
if (identical(result, numeric(0))) return(NA)
else return(result)
}))
})
df <- as.data.frame(do.call(rbind, result2))
colnames(df) <- c("speed", "distance", "degrees", "raw")
speed distance degrees
1 NA NA NA
2 104 381 38
3 67 NA NA
4 NA NA NA
5 107 412 NA
6 71 NA NA
7 94 287 NA
8 NA NA NA
9 NA NA NA
10 64 NA NA