我正在尝试导入以下文件，并提取两个重复的数据部分。第一组以未使用的标题（第5行）和以“ES”第5行开头的实际标题开始。下一部分数据以未使用的标题（第13行）和以“LU”开头的实际标题（第14行）和更多变量名称开头。这些文件中有许多，并且每个文件都有不同长度的不同数量的EU和LS部分。我需要提取LS和EU数据以分离数据帧。不幸的是，文件是“按原样”传感器阵列，我不能改变它，并且不希望在excel中完成所有这些，但可能不得不这样做。在真实文件中，每个EU和LS集可能有数百行。
我已经尝试调整以下代码来索引EU部分，然后将其提取并清理它然后在LS部分完成相同但我甚至没有得到这个工作。部分原因是欧盟处于两个标题行。我确实看到了使用perl脚本的代码，但从未使用过那种语言。
lns = readLines("lake1.txt")
idx = grepl("EU", lns)
df = read.table(text=lns[!idx])
wd = diff(c(which(idx), length(idx) + 1)) - 1
df$label = rep(lns[idx], wd)
我不确定添加CSV文件示例的最佳方法，但这里是......
Garbage Text 1,,,,,,,,
Garbage Text 2,,,,,,,,
Garbage Text 3,,,,,,,,
,,,,,,,,
INTTIME ('sec'),SAMPLE ('sec'),ES_DARK ('uW/cm^2/nm'),ES_DARK ('uW/cm^2/nm'),ES_DARK ('uW/cm^2/nm'),CHECK (''),DATETAG (NONE),TIMETAG2 (NONE),POSFRAME (NONE)
ES,DELAY,344.83,348.23,351.62,SUM,NONE,NONE,COUNTS
0.032,0,0.35441789,-0.00060208,0.10290995,87,2017015,10:42:39,1
0.032,0,-0.36023974,-0.22242269,-0.09639,109,2017015,10:42:40,10
0.032,0,0.07552711,0.01524224,-0.16756855,91,2017015,10:42:48,41
,,,,,,,,11304
,,,,,,,,11312
,,,,,,,,
INTTIME ('sec'),SAMPLE ('sec'),LU ('uW/cm^2/nm/sr'),LU ('uW/cm^2/nm/sr'),LU ('uW/cm^2/nm/sr'),CHECK (''),DATETAG (NONE),TIMETAG2 (NONE),POSFRAME (NONE)
LU,DELAY,344.37,347.75,351.13,SUM,NONE,NONE,COUNTS
0.032,0,0.02288441,0.02891912,0.03595322,53,2017015,10:42:38,2
0.032,0,-0.00014323,0.00024047,0.00001585,212,2017015,10:42:38,6
0.032,0,0.00114258,0.00091736,-0.0000495,16,2017015,10:42:39,9
0.032,0,0.00020744,0.0004186,0.00027721,118,2017015,10:42:40,16
,,,,,,,,11310
,,,,,,,,
INTTIME ('sec'),SAMPLE ('sec'),ES ('uW/cm^2/nm'),ES ('uW/cm^2/nm'),ES ('uW/cm^2/nm'),CHECK (''),DATETAG (NONE),TIMETAG2 (NONE),POSFRAME (NONE)
ES,DELAY,344.83,348.23,351.62,SUM,NONE,NONE,COUNTS
0.032,0,56.7600789,59.43147464,62.83968564,186,2017015,10:42:38,3
0.032,0,56.27202003,59.52654061,62.86815706,29,2017015,10:42:38,4
,,,,,,,,11309
,,,,,,,,11311
,,,,,,,,
INTTIME ('sec'),SAMPLE ('sec'),LU ('uW/cm^2/nm/sr'),LU ('uW/cm^2/nm/sr'),LU ('uW/cm^2/nm/sr'),CHECK (''),DATETAG (NONE),TIMETAG2 (NONE),POSFRAME (NONE)
LU,DELAY,344.37,347.75,351.13,SUM,NONE,NONE,COUNTS
0.032,0,-0.00011611,-0.00039544,-0.00014584,3,2017015,10:42:42,20
0.032,0,-0.00032394,-0.00020563,-0.00020383,229,2017015,10:42:46,39
这就是两个数据帧最终应该是什么样子：
Dataframe 1
ES,DELAY,344.83,348.23,351.62,SUM,NONE,NONE,COUNTS
0.032,0,0.35441789,-0.00060208,0.10290995,87,2017015,10:42:39,1
0.032,0,-0.36023974,-0.22242269,-0.09639,109,2017015,10:42:40,10
0.032,0,0.07552711,0.01524224,-0.16756855,91,2017015,10:42:48,41
0.032,0,56.7600789,59.43147464,62.83968564,186,2017015,10:42:38,3
0.032,0,56.27202003,59.52654061,62.86815706,29,2017015,10:42:38,4
Dataframe 2
LU,DELAY,344.37,347.75,351.13,SUM,NONE,NONE,COUNTS
0.032,0,0.02288441,0.02891912,0.03595322,53,2017015,10:42:38,2
0.032,0,-0.00014323,0.00024047,0.00001585,212,2017015,10:42:38,6
0.032,0,0.00114258,0.00091736,-0.0000495,16,2017015,10:42:39,9
0.032,0,0.00020744,0.0004186,0.00027721,118,2017015,10:42:40,16
0.032,0,-0.00011611,-0.00039544,-0.00014584,3,2017015,10:42:42,20
0.032,0,-0.00032394,-0.00020563,-0.00020383,229,2017015,10:42:46,39
答案 0 :(得分：1)
您可以使用tidyverse工具解决此问题。
readr用于读/写csv文件
dplyr用于数据框操作
stringr用于字符串操作
library(readr)
library(dplyr)
library(stringr)
df_1 <- read_csv("test1.csv", col_names = FALSE, col_types = cols(.default = "c"), skip = 3)
首先删除缺少所有值的行，或删除除最后一行以外的所有行以及带有额外标题的行。
然后创建一个包含ES或LU值的新列，否则 NA ，然后使用tidyr::fill填充这些值。
然后将NONE的两列更改为DATE和TIME，因为稍后我们不希望两列具有相同的名称。
df_2 <- df_1 %>%
filter(!is.na(X1), !str_detect(X1, "INTTIME")) %>%
mutate(grp = if_else(X1 %in% c("ES", "LU"), X1, NA_character_)) %>%
tidyr::fill(grp, .direction = "down") %>%
mutate(X7 = str_replace(X7, "NONE", "DATE"),
X8 = str_replace(X8, "NONE", "TIME"))
df_2
#> # A tibble: 15 x 10
#> X1 X2 X3 X4 X5 X6 X7 X8 X9 grp
#> * <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 ES DELAY 344.83 348.23 351.62 SUM DATE TIME COUNTS ES
#> 2 0.032 0 0.35441789 -0.00060208 0.10290995 87 2017015 10:42:39 1 ES
#> 3 0.032 0 -0.36023974 -0.22242269 -0.09639 109 2017015 10:42:40 10 ES
#> 4 0.032 0 0.07552711 0.01524224 -0.16756855 91 2017015 10:42:48 41 ES
#> 5 LU DELAY 344.37 347.75 351.13 SUM DATE TIME COUNTS LU
#> 6 0.032 0 0.02288441 0.02891912 0.03595322 53 2017015 10:42:38 2 LU
#> 7 0.032 0 -0.00014323 0.00024047 0.00001585 212 2017015 10:42:38 6 LU
#> 8 0.032 0 0.00114258 0.00091736 -0.0000495 16 2017015 10:42:39 9 LU
#> 9 0.032 0 0.00020744 0.0004186 0.00027721 118 2017015 10:42:40 16 LU
#> 10 ES DELAY 344.83 348.23 351.62 SUM DATE TIME COUNTS ES
#> 11 0.032 0 56.7600789 59.43147464 62.83968564 186 2017015 10:42:38 3 ES
#> 12 0.032 0 56.27202003 59.52654061 62.86815706 29 2017015 10:42:38 4 ES
#> 13 LU DELAY 344.37 347.75 351.13 SUM DATE TIME COUNTS LU
#> 14 0.032 0 -0.00011611 -0.00039544 -0.00014584 3 2017015 10:42:42 20 LU
#> 15 0.032 0 -0.00032394 -0.00020563 -0.00020383 229 2017015 10:42:46 39 LU
现在对ES和LU中的每一个都可以过滤掉那些记录，然后删除新的grp列，然后使用第一行作为列名，然后删除那些列标题行，并写入新清理的csv文件。
df_es <- df_2 %>%
filter(grp == "ES") %>%
select(-grp) %>%
purrr::set_names(., .[1,]) %>%
filter(ES != "ES") %>%
write_csv("ES.csv")
df_es
#> # A tibble: 5 x 9
#> ES DELAY `344.83` `348.23` `351.62` SUM DATE TIME COUNTS
#> * <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 0.032 0 0.35441789 -0.00060208 0.10290995 87 2017015 10:42:39 1
#> 2 0.032 0 -0.36023974 -0.22242269 -0.09639 109 2017015 10:42:40 10
#> 3 0.032 0 0.07552711 0.01524224 -0.16756855 91 2017015 10:42:48 41
#> 4 0.032 0 56.7600789 59.43147464 62.83968564 186 2017015 10:42:38 3
#> 5 0.032 0 56.27202003 59.52654061 62.86815706 29 2017015 10:42:38 4
df_lu <- df_2 %>%
filter(grp == "LU") %>%
select(-grp) %>%
set_names(., .[1,]) %>%
filter(LU != "LU") %>%
write_csv("LU.csv")
df_lu
#> # A tibble: 6 x 9
#> LU DELAY `344.37` `347.75` `351.13` SUM DATE TIME COUNTS
#> * <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 0.032 0 0.02288441 0.02891912 0.03595322 53 2017015 10:42:38 2
#> 2 0.032 0 -0.00014323 0.00024047 0.00001585 212 2017015 10:42:38 6
#> 3 0.032 0 0.00114258 0.00091736 -0.0000495 16 2017015 10:42:39 9
#> 4 0.032 0 0.00020744 0.0004186 0.00027721 118 2017015 10:42:40 16
#> 5 0.032 0 -0.00011611 -0.00039544 -0.00014584 3 2017015 10:42:42 20
#> 6 0.032 0 -0.00032394 -0.00020563 -0.00020383 229 2017015 10:42:46 39