read.csv() error: more columns than column names
read.csv() error: more columns than column names
我正在尝试输入 CSV 文件，但出现以下错误：
associatedata <- read.csv("AssociatedSpeciesID_1.csv", header=TRUE, fileEncoding = 'UTF-8-BOM') %>% mutate_all(na_if, "")
Error in read.table(file = file, header = header, sep = sep, quote = quote, :
more columns than column names
这是下面的 CSV：我找不到列数不匹配的地方。我已经尝试了其他问题的通用解决方案，但没有任何效果。
ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
header 有 13 个字段，所有其他记录有 15 个，检查它我们发现每个数据行的末尾有两个尾随逗号。
count.fields("abc.csv", sep = ",")
## [1] 13 15 15 15 15
1) 如果我们删除尾随的两个逗号，那么它就可以工作了。 （你可能不需要 strip.white 但它被添加是因为最后注释中的代码缩进了 4 个空格以满足 SO。它不会受到伤害。）
L <- "abc.csv" |>
readLines() |>
sub(pattern = ",,$", replacement = "")
DF <- read.csv(text = L, strip.white = TRUE)
给予
> str(DF)
'data.frame': 4 obs. of 13 variables:
$ ObjectID : int 1 2 3 4
$ GlobalID : chr "54e33e7c-1ff1-464f-8872-df027fcfe8ec" "68420bc9-d6c6-4d7f-a149-7306399ce5c1" "88a6807b-b00c-4e58-84bb-4e8cb61409ae" "9fc8ea4a-e197-42cc-bd75-614d5b106364"
$ AssociatedSpeciesKnown : chr "known" "known" "unknown" "known"
$ Associates : chr "Amelanchier utahensis" "NewSpecies" "" "Artemisia nova"
$ NewAssociate : chr "" "Genus species" "" ""
$ UnknownSpecies_Description: chr "" "" "ritiidiwjjviern bg" ""
$ AssociatedSpeciesAbundance: chr "Few" "Occasional" "Common" "Common"
$ Coflowering : chr "no" "yes" "no" "no"
$ ParentGlobalID : chr "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "ea9eb086-89c2-4aa5-a2f6-95519cd35a58"
$ CreationDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Creator : chr "ejob_BLM" "ejob_BLM" "ejob_BLM" "ejob_BLM"
$ EditDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Editor : chr "ejob" "ejob" "ejob" "ejob"
2) 或者，如果 sed 在您的路径上，则：
read.csv(pipe("sed -e s/,,$// abc.csv"), strip.white = TRUE)
3)这也行。
DF <- read.csv("abc.csv", header = FALSE, skip = 1, strip.white = TRUE)[1:13]
names(DF) <- read.table("abc.csv", sep = ",", strip.white = TRUE, nrows = 1)
备注
根据问题生成文件。
Lines <- "ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
"
cat(Lines, file = "abc.csv")
我正在尝试输入 CSV 文件，但出现以下错误：
associatedata <- read.csv("AssociatedSpeciesID_1.csv", header=TRUE, fileEncoding = 'UTF-8-BOM') %>% mutate_all(na_if, "")
Error in read.table(file = file, header = header, sep = sep, quote = quote, :
more columns than column names
这是下面的 CSV：我找不到列数不匹配的地方。我已经尝试了其他问题的通用解决方案，但没有任何效果。
ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
header 有 13 个字段，所有其他记录有 15 个，检查它我们发现每个数据行的末尾有两个尾随逗号。
count.fields("abc.csv", sep = ",")
## [1] 13 15 15 15 15
1) 如果我们删除尾随的两个逗号，那么它就可以工作了。 （你可能不需要 strip.white 但它被添加是因为最后注释中的代码缩进了 4 个空格以满足 SO。它不会受到伤害。）
L <- "abc.csv" |>
readLines() |>
sub(pattern = ",,$", replacement = "")
DF <- read.csv(text = L, strip.white = TRUE)
给予
> str(DF)
'data.frame': 4 obs. of 13 variables:
$ ObjectID : int 1 2 3 4
$ GlobalID : chr "54e33e7c-1ff1-464f-8872-df027fcfe8ec" "68420bc9-d6c6-4d7f-a149-7306399ce5c1" "88a6807b-b00c-4e58-84bb-4e8cb61409ae" "9fc8ea4a-e197-42cc-bd75-614d5b106364"
$ AssociatedSpeciesKnown : chr "known" "known" "unknown" "known"
$ Associates : chr "Amelanchier utahensis" "NewSpecies" "" "Artemisia nova"
$ NewAssociate : chr "" "Genus species" "" ""
$ UnknownSpecies_Description: chr "" "" "ritiidiwjjviern bg" ""
$ AssociatedSpeciesAbundance: chr "Few" "Occasional" "Common" "Common"
$ Coflowering : chr "no" "yes" "no" "no"
$ ParentGlobalID : chr "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "9fc6b840-8584-4045-b69f-f0e9488a1f06" "ea9eb086-89c2-4aa5-a2f6-95519cd35a58"
$ CreationDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Creator : chr "ejob_BLM" "ejob_BLM" "ejob_BLM" "ejob_BLM"
$ EditDate : chr "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:55:46 PM" "1/7/2022 3:56:26 PM"
$ Editor : chr "ejob" "ejob" "ejob" "ejob"
2) 或者，如果 sed 在您的路径上，则：
read.csv(pipe("sed -e s/,,$// abc.csv"), strip.white = TRUE)
3)这也行。
DF <- read.csv("abc.csv", header = FALSE, skip = 1, strip.white = TRUE)[1:13]
names(DF) <- read.table("abc.csv", sep = ",", strip.white = TRUE, nrows = 1)
备注
根据问题生成文件。
Lines <- "ObjectID,GlobalID,AssociatedSpeciesKnown,Associates,NewAssociate,UnknownSpecies_Description,AssociatedSpeciesAbundance,Coflowering,ParentGlobalID,CreationDate,Creator,EditDate,Editor
1,54e33e7c-1ff1-464f-8872-df027fcfe8ec,known,Amelanchier utahensis,,,Few,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
2,68420bc9-d6c6-4d7f-a149-7306399ce5c1,known,NewSpecies,Genus species,,Occasional,yes,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
3,88a6807b-b00c-4e58-84bb-4e8cb61409ae,unknown,,,ritiidiwjjviern bg,Common,no,9fc6b840-8584-4045-b69f-f0e9488a1f06,1/7/2022 3:55:46 PM,ejob_BLM,1/7/2022 3:55:46 PM,ejob,,
4,9fc8ea4a-e197-42cc-bd75-614d5b106364,known,Artemisia nova,,,Common,no,ea9eb086-89c2-4aa5-a2f6-95519cd35a58,1/7/2022 3:56:26 PM,ejob_BLM,1/7/2022 3:56:26 PM,ejob,,
"
cat(Lines, file = "abc.csv")