我从一个没有考虑过数据分析的人那里继承了一个项目。因此，我有多个分隔符的输出数据文件，包括多种类型的大括号和不同程度的嵌入到组数据，以及用逗号分隔数字的逗号。在一些地方也有一些纯文本句子可供选择。
任何人都可以通过一种简单的方法帮助将嵌入式结构和描述转换为 R 中的数据框吗？
以下是一个示例：
[(3, None, 1), (1, 0.36, 1), (3, None, 1), (2, 0.41, 1), (5, 0.47, 1), (6, 0.36, 1), (2, 0.45, 1), (2, 0.36, 1), (4, 0.39, 1), (6, 0.34, 1), (1, 0.47, 1), (7, 0.44, 1), (4, 0.39, 1), (6, 0.38, 1), (9, 0.39, 1), (5, 0.37, 1), (8, 0.41, 1), (9, 0.38, 1), (1, 0.44, 1), (9, 0.38, 1), (4, 0.36, 1), (8, 0.41, 1), (7, 0.38, 1), (7, 0.41, 1), (7, 0.36, 1), (7, 0.39, 1), (9, 0.41, 1), (5, 0.36, 1), (8, 0.31, 1), (6, 0.38, 1), (1, 0.44, 1), (3, None, 1), (5, 0.59, 1), (7, 0.52, 1), (7, 0.44, 1), (7, 0.38, 1), (8, 0.34, 1), (9, 0.39, 1), (3, None, 1), (7, 0.44, 1), (7, 0.53, 1), (8, 0.36, 1), (3, 0.36, 0), (8, 0.34, 1), (5, 0.38, 1), (3, None, 1), (5, 0.52, 1), (3, None, 1), (9, 0.55, 1), (9, 0.36, 1), (4, 0.38, 1), (2, 0.73, 1), (9, 0.36, 1), (7, 0.44, 1), (4, 0.45, 1), (4, 0.62, 1), (9, 0.39, 1), (3, 0.31, 0), (1, 0.42, 1), (4, 0.34, 1), (5, 0.53, 1), (8, 0.34, 1), (3, None, 1), (8, 0.47, 1), (6, 0.39, 1), (1, 0.42, 1), (5, 0.53, 1), (1, 0.53, 1), (8, 0.62, 1), (1, 0.39, 1), (8, 0.44, 1), (8, 0.45, 1), (9, 0.38, 1), (1, 0.36, 1), (4, 0.38, 1), (6, 0.36, 1), (7, 0.36, 1), (9, 0.39, 1), (8, 0.41, 1), (8, 0.31, 1), (3, None, 1), (2, 0.36, 1), (4, 0.36, 1), (2, 0.31, 1), (9, 0.36, 1), (1, 0.31, 1), (4, 0.34, 1), (1, 0.56, 1), (7, 0.61, 1), (9, 0.38, 1), (3, None, 1), (1, 0.36, 1), (1, 0.53, 1), (5, 0.33, 1), (3, None, 1), (1, 0.39, 1), (6, 0.34, 1), (9, 0.33, 1), (4, 0.38, 1), (3, None, 1), (5, 0.44, 1), (2, 0.52, 1), (1, 0.42, 1), (6, 0.38, 1), (9, 0.33, 1), (4, 0.38, 1), (5, 0.31, 1), (6, 0.31, 1), (8, 0.31, 1), (2, 0.33, 1), (9, 0.33, 1), (1, 0.56, 1), (6, 0.38, 1), (3, None, 1), (7, 0.34, 1), (5, 0.34, 1), (2, 0.36, 1), (2, 0.47, 1), (3, None, 1), (2, 0.39, 1), (2, 0.36, 1), (6, 0.31, 1), (1, 0.53, 1), (5, 0.45, 1), (7, 0.42, 1), (5, 0.45, 1), (2, 0.39, 1), (2, 0.45, 1), (6, 0.36, 1), (2, 0.45, 1), (1, 0.39, 1), (1, 0.34, 1), (4, 0.39, 1), (2, 0.34, 1), (2, 0.31, 1), (3, 0.31, 0), (8, 0.39, 1), (6, 0.34, 1), (6, 0.31, 1), (5, 0.38, 1), (9, 0.34, 1), (7, 0.31, 1), (1, 0.33, 1), (4, 0.38, 1), (6, 0.38, 1), (5, 0.38, 1), (9, 0.38, 1), (2, 0.5, 1), (8, 0.44, 1), (8, 0.39, 1), (4, 0.38, 1), (5, 0.5, 1), (9, 0.48, 1), (2, 0.59, 1), (8, 0.41, 1), (7, 0.41, 1), (3, None, 1), (4, 0.5, 1), (4, 0.36, 1), (7, 0.38, 1), (5, 0.44, 1), (6, 0.34, 1), (6, 0.41, 1), (3, None, 1), (7, 0.39, 1), (6, 0.34, 1), (2, 0.34, 1), (9, 0.36, 1), (4, 0.36, 1), (5, 0.38, 1), (3, None, 1), (6, 0.36, 1), (5, 0.33, 1), (4, 0.44, 1), (7, 0.34, 1), (8, 0.48, 1), (6, 0.34, 1), (8, 0.38, 1), (3, None, 1), (4, 0.31, 1), (3, 0.31, 0)]
Percentage of correctly suppressed responses per five-target section:
[80, 80, 100, 80]
Average reaction time per five-target section:
[0.4, 0.43, 0.39, 0.39]
Percentage of correctly suppressed responses per ten-target section:
[80, 90]
Average reaction time per ten-target section:
[0.41, 0.39]
理想情况下，第一行将变为3列数据帧，第二行被忽略，第3行变为4整数向量等。
答案 0 :(得分：2)
使用readLines获取您的数据，然后使用gsub和strsplit对其进行排序：
#txt <- readLines(textConnection("<insert your text here>"))
#or probably more appropriately
txt <- readLines("filename.txt")
# remove labels
txt <- txt[-c(2,4,6,8)]
# remove first [ character
txt <- lapply(txt,function(x) substr(x,2,nchar(x)-1))
# reformat element 1
txt[[1]] <- gsub("[()]","",txt[[1]])
txt[[1]] <- gsub("None","0",txt[[1]])
txt[[1]] <- as.numeric(unlist(strsplit(txt[[1]],",")))
txt[[1]] <- data.frame(matrix(txt[[1]],ncol=3,byrow=TRUE))
# reformat elements 2-5
txt[2:5] <- lapply(txt[2:5],function(x) as.numeric(unlist(strsplit(x,","))))
结果：
txt
#[[1]]
# X1 X2 X3
#1 3 0.00 1
#2 1 0.36 1
#3 3 0.00 1
#4 2 0.41 1
#5 5 0.47 1
#6 6 0.36 1
# etc... etc...
#
#[[2]]
#[1] 80 80 100 80
#
#[[3]]
#[1] 0.40 0.43 0.39 0.39
#
#[[4]]
#[1] 80 90
#
#[[5]]
#[1] 0.41 0.39