我有一个由其他函数创建的data.frame,这些函数接受.xlsx文件的列表,并读取所有工作簿和包含的工作表。
结果就是这样一个不错的数据框:
df<-data.frame(
file.name <-c(“C:/R/Folder1/WB1.xlsx”,
“C:/R/Folder1/WB2.xlsx,”,”C:/R/Folder1/WB2.xlsx”, “C:/R/Folder2/WB1.xlsx”, “C:/R/Folder2/WB1.xls”),
data<-list(df1,df2,df3,df4,df5))
虽然我能够检索(嵌套)数据帧,但我丢失了所需的相应文件位置。
在取消嵌套时,是否有一种方法可以将数据框中的相应行和paste()保留为一列?
*很抱歉输入错误。发表在SO应用程序上。
更新(现在我在PC前面)
可复制的示例:
数据:
df1<-data.frame(V1=c(sample(900:970,6)),
V2=c(sample(LETTERS[1:6],6)))
df2<-data.frame(V1=sample(750:780,6),
V2=sample(LETTERS[8:16],6))
df3<-data.frame(V1=sample(200:250,6),
V2=sample(LETTERS[10:20],6),
V3=sample(2300:5821,6))
df4<-data.frame(V1=sample(396:480,6),
V2=sample(LETTERS,6))
df5<-data.frame(V1=sample(50:100,6),
V2=sample(LETTERS,6))
df6<-data.frame(V1=sample(200:250,6),
V2=sample(LETTERS,6),
V3=sample(letters,6))
my.list <- list(df1,df2,df3,df4,df5,df6)
mydf<-data.frame(
files=c("C:/Folder1/Data/File1.xlsx","C:/Folder1/Data/File2.xlsx",
"C:/Folder1/Data/File3.xlsx","C:/Folder2/Data/File1.xlsx",
"C:/Folder2/Data/File2.xlsx","C:/Folder2/Data/File3.xlsx"))
mydf$data<-my.list
尝试进行嵌套时-由于出现了data.frames列表中的观察值和变量不同(第2列),我遇到了以下问题:
y<-unnest(mydf, data)
Error: Column `V3` can't be converted from integer to factor
In addition: Warning messages:
1: In bind_rows_(x, .id) : Unequal factor levels: coercing to character
2: In bind_rows_(x, .id) :
binding character and factor vector, coercing into character vector
3: In bind_rows_(x, .id) :
binding character and factor vector, coercing into character vector...
其他功能的结果
#tidyverse
y<-mydf %>% unnest(data)
Error: Column `V3` can't be converted from integer to factor
In addition: Warning messages:
1: In bind_rows_(x, .id) : Unequal factor levels: coercing to character
y<-mydf %>%
+ unnest(data) %>%
+ group_by(files) %>%
+ mutate(
+ data = flatten_chr(data),
+ data_colname = str_c("data_", row_number())
+ ) %>% # or just as.character
+ spread(data_colname, data)
Error: Column `V3` can't be converted from integer to factor
In addition: Warning messages:
1: In bind_rows_(x, .id) : Unequal factor levels: coercing to character
添加利用功能将.xlsx和所有工作表拉入-如example所示:
library(tidyverse)
library(readxl)
dir_path1 <- "~/File1/Data/Qtr1"
dir_path2 <- "~/File1/Data/Qtr2"
dir_path3 <- "~/File1/Data/Qtr3"
dir_path4 <- "~/File1/Data/Qtr4"
re_file <- ".xlsx"
read_sheets <- function(dir_path1, file){
xlsx_file <- paste0(dir_path1, file)
xlsx_file %>%
excel_sheets() %>%
set_names() %>%
map_df(read_excel, path = xlsx_file, .id = 'sheet_name') %>%
mutate(file_name = file) %>%
select(file_name, sheet_name, everything())
}
df <- list.files(dir_path, re_file) %>%
map_df(~ read_sheets(dir_path, .))
返回:
# A tibble: 15 x 5
file_name sheet_name col1
<chr> <chr> <dbl>
1 Q1_File1.xlsx Sheet1 1
2 Q1_File1.xlsx Sheet2 1
3 Q1_File2.xlsx Sheet1 1
...
但是,与示例数据不同(如链接中所示),返回的数据(col1)是数据帧的列表。
答案 0 :(得分:1)
问题与df3的数字代表V3
而df6的数字代表V3
有关。您可以:
df3$V3
或df6$V3
此外,要消除警告,您可以使用stringsAsFactors = FALSE
创建data.frame,也可以使用tibble()
代替data.frame()
,因为这是小标题的默认行为。
编辑:要更好地执行选项2,可以使用下面的代码为每个变量添加前缀。
my.list2 <- lapply(my.list, function(x) sapply(x, function(y) paste0(class(y), names(y))))
, function(x)
{
x%>%
rename_if(is.numeric, ~paste0('num', .x))%>%
rename_if(is.character, ~paste0('char', .x))%>%
rename_if(is.factor, ~paste0('fact', .x))
}
)
这是选项2,仅适用于因子警告:
df1<-data.frame(V1=c(sample(900:970,6)),
V2=c(sample(LETTERS[1:6],6)))
df2<-data.frame(V1=sample(750:780,6),
V2=sample(LETTERS[8:16],6))
df3<-data.frame(V1=sample(200:250,6),
V2=sample(LETTERS[10:20],6),
V4=sample(2300:5821,6)) #used to be V3
df4<-data.frame(V1=sample(396:480,6),
V2=sample(LETTERS,6))
df5<-data.frame(V1=sample(50:100,6),
V2=sample(LETTERS,6))
df6<-data.frame(V1=sample(200:250,6),
V2=sample(LETTERS,6),
V3=sample(letters,6))
my.list <- list(df1,df2,df3,df4,df5,df6)
mydf<-data.frame(
files=c("C:/Folder1/Data/File1.xlsx","C:/Folder1/Data/File2.xlsx",
"C:/Folder1/Data/File3.xlsx","C:/Folder2/Data/File1.xlsx",
"C:/Folder2/Data/File2.xlsx","C:/Folder2/Data/File3.xlsx"))
mydf$data<-my.list
unnest(mydf, data)
files V1 V2 V4 V3
1 C:/Folder1/Data/File1.xlsx 951 A NA <NA>
2 C:/Folder1/Data/File1.xlsx 932 F NA <NA>
3 C:/Folder1/Data/File1.xlsx 908 B NA <NA>
4 C:/Folder1/Data/File1.xlsx 953 C NA <NA>
5 C:/Folder1/Data/File1.xlsx 929 E NA <NA>
6 C:/Folder1/Data/File1.xlsx 928 D NA <NA>
7 C:/Folder1/Data/File2.xlsx 778 K NA <NA>
8 C:/Folder1/Data/File2.xlsx 771 H NA <NA>
9 C:/Folder1/Data/File2.xlsx 757 M NA <NA>
10 C:/Folder1/Data/File2.xlsx 773 P NA <NA>
11 C:/Folder1/Data/File2.xlsx 759 N NA <NA>
12 C:/Folder1/Data/File2.xlsx 765 O NA <NA>
13 C:/Folder1/Data/File3.xlsx 236 M 3964 <NA>
14 C:/Folder1/Data/File3.xlsx 214 O 5241 <NA>
...truncated