使用R将数据框写入文本文件时，我一直收到奇怪的输出。我使用write.csv()，write.csv2()和write.table()时遇到了同样的问题。
我有一个data.frame，我是通过使用data.frame将多个rbind()绑定在一起创建的，这些data.frame之前是较大> dim(extract)
[1] 1001 16
> extract[1:5,2:16]
latitude longitude WordCount English Common Tagalog Bikol Cebuano Hiligaynon Ilocano Kapampangan Pangasinense Waray Zam Spanish
20 20.45164941 121.9671742 7 1 0 0 3 0 0 0 0 0 0 0 0
77 20.45164941 121.9671742 7 1 0 0 3 0 0 0 0 0 0 0 0
106 20.45164941 121.9671742 7 1 0 0 3 0 0 0 0 0 0 0 0
48670 20.45164941 121.9671742 7 1 0 0 3 0 0 0 0 0 0 0 0
94831 8.19183664 124.17909375 13 8 2 0 3 0 0 0 0 0 0 0 0
的子集。它被称为＆＃34; extract＆＃34;，我试图将每一列但第一个（大文本字符串）写入txt文件。
> write.csv(extract[,2:16], 'extract 6-30.txt', row.names=FALSE)
当我这样做时
> write.csv(extract[1:5,2:16], 'extract 6-29.txt', row.names=FALSE)
我的表将前两项纬度和经度视为列，然后为表中的每个项目的列中的每个项目连接列表。所以，例如：
"latitude","longitude","WordCount","English","Common","Tagalog","Bikol","Cebuano","Hiligaynon","Ilocano","Kapampangan","Pangasinense","Waray","Zam","Spanish"
"20.45164941","121.9671742",c(7, 7, 7, 7, 13),c(1, 1, 1, 1, 8),c(0, 0, 0, 0, 2),c(0, 0, 0, 0, 0),c(3, 3, 3, 3, 3),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0)
"20.45164941","121.9671742",c(7, 7, 7, 7, 13),c(1, 1, 1, 1, 8),c(0, 0, 0, 0, 2),c(0, 0, 0, 0, 0),c(3, 3, 3, 3, 3),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0)
"20.45164941","121.9671742",c(7, 7, 7, 7, 13),c(1, 1, 1, 1, 8),c(0, 0, 0, 0, 2),c(0, 0, 0, 0, 0),c(3, 3, 3, 3, 3),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0)
"20.45164941","121.9671742",c(7, 7, 7, 7, 13),c(1, 1, 1, 1, 8),c(0, 0, 0, 0, 2),c(0, 0, 0, 0, 0),c(3, 3, 3, 3, 3),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0)
"8.19183664","124.17909375",c(7, 7, 7, 7, 13),c(1, 1, 1, 1, 8),c(0, 0, 0, 0, 2),c(0, 0, 0, 0, 0),c(3, 3, 3, 3, 3),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0),c(0, 0, 0, 0, 0)
产生以下文本文件：
> dput(extract[1:5,2:16])
structure(list(latitude = c("20.45164941", "20.45164941", "20.45164941",
"20.45164941", "8.19183664"), longitude = c("121.9671742", "121.9671742",
"121.9671742", "121.9671742", "124.17909375"), WordCount = structure(list(
WordCount = c(7L, 7L, 7L, 7L, 13L)), .Names = "WordCount", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), English = structure(list(
English = c(1L, 1L, 1L, 1L, 8L)), .Names = "English", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Common = structure(list(
Common = c(0L, 0L, 0L, 0L, 2L)), .Names = "Common", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Tagalog = structure(list(
Tagalog = c(0L, 0L, 0L, 0L, 0L)), .Names = "Tagalog", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Bikol = structure(list(
Bikol = c(3L, 3L, 3L, 3L, 3L)), .Names = "Bikol", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Cebuano = structure(list(
Cebuano = c(0L, 0L, 0L, 0L, 0L)), .Names = "Cebuano", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Hiligaynon = structure(list(
Hiligaynon = c(0L, 0L, 0L, 0L, 0L)), .Names = "Hiligaynon", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Ilocano = structure(list(
Ilocano = c(0L, 0L, 0L, 0L, 0L)), .Names = "Ilocano", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Kapampangan = structure(list(
Kapampangan = c(0L, 0L, 0L, 0L, 0L)), .Names = "Kapampangan", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Pangasinense = structure(list(
Pangasinense = c(0L, 0L, 0L, 0L, 0L)), .Names = "Pangasinense", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Waray = structure(list(
Waray = c(0L, 0L, 0L, 0L, 0L)), .Names = "Waray", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Zam = structure(list(
Zam = c(0L, 0L, 0L, 0L, 0L)), .Names = "Zam", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame"), Spanish = structure(list(
Spanish = c(0L, 0L, 0L, 0L, 0L)), .Names = "Spanish", row.names = c("20",
"77", "106", "48670", "94831"), class = "data.frame")), .Names = c("latitude",
"longitude", "WordCount", "English", "Common", "Tagalog", "Bikol",
"Cebuano", "Hiligaynon", "Ilocano", "Kapampangan", "Pangasinense",
"Waray", "Zam", "Spanish"), row.names = c(20L, 77L, 106L, 48670L,
94831L), class = "data.frame")
我遗失了一些争论吗？我尝试使用和不使用row.names，以及使用带有各种不同分隔符的write.table。我感谢您的帮助，如果您有更多问题请与我联系。我相信它可能与数据框的创建方式有关。很抱歉，如果已经提出这个问题，但我遇到的这个具体问题很难找到。
编辑： 所以使用dput yield：
> summary(extract)
alltweets.text latitude
Grabe. Kasanok masungbatan nu ana nakaturog nak idin. 1AM kano ngamin idin. Haha. \xed\xa0\xbd\xed\xb1\x8a\xed\xa0\xbd\xed\xb1\x8a : 9 Length:1001
@MitchyyWong mejo mejo lang pud hahaha ikaw ang hinfi talaga ba haha labyu : 8 Class :character
#EvictLoisa nakaka inis panoorin sa tv screen di na maganda tingnan palayasin nayan ngaung saturday! #PBBStopAndStare : 8 Mode :character
Lionel Messi for breakfast! \xed\xa0\xbd\xed\xb8\x9c Happy Monday.. #ARG vs #BIH #WorldCup2014 : 8
ngano lami man kaayo ang kan.on oy? ilabi nag parisan ug bulad ug ginamos. ginoo ko tabang! : 8
"@IndayBanat: Ang taong pinakamahirap tanggalin sa isipan mo, ay yong taong kahit hindi kayo pero pinapasaya ka at binubuo ang araw mo." \xed\xa0\xbd\xed\xb8\xad: 7
(Other) :953
longitude WordCount.WordCount English.English Common.Common Tagalog.Tagalog Bikol.Bikol Cebuano.Cebuano Hiligaynon.Hiligaynon Ilocano.Ilocano
Length:1001 Min. : 3.000000 Min. : 0.000000 Min. : 0.000000 Min. :0.000000 Min. :0.00000 Min. :0.000000 Min. :0.000000 Min. :0.000000
Class :character 1st Qu.: 9.000000 1st Qu.: 1.000000 1st Qu.: 2.000000 1st Qu.:0.000000 1st Qu.:0.00000 1st Qu.:0.000000 1st Qu.:0.000000 1st Qu.:0.000000
Mode :character Median :12.000000 Median : 2.000000 Median : 4.000000 Median :1.000000 Median :0.00000 Median :0.000000 Median :0.000000 Median :0.000000
Mean :12.384615 Mean : 2.298701 Mean : 4.074925 Mean :1.599401 Mean :0.07992 Mean :0.418581 Mean :0.140859 Mean :0.305694
3rd Qu.:15.000000 3rd Qu.: 3.000000 3rd Qu.: 6.000000 3rd Qu.:3.000000 3rd Qu.:0.00000 3rd Qu.:0.000000 3rd Qu.:0.000000 3rd Qu.:0.000000
Max. :22.000000 Max. :15.000000 Max. :13.000000 Max. :7.000000 Max. :4.00000 Max. :5.000000 Max. :4.000000 Max. :4.000000
Kapampangan.Kapampangan Pangasinense.Pangasinense Waray.Waray Zam.Zam Spanish.Spanish
Min. :0.00000 Min. :0.000000 Min. : 0.000000 Min. :0 Min. :0.000000
1st Qu.:0.00000 1st Qu.:0.000000 1st Qu.: 0.000000 1st Qu.:0 1st Qu.:0.000000
Median :0.00000 Median :0.000000 Median : 0.000000 Median :0 Median :0.000000
Mean :0.26973 Mean :0.076923 Mean : 0.818182 Mean :0 Mean :0.367632
3rd Qu.:0.00000 3rd Qu.:0.000000 3rd Qu.: 1.000000 3rd Qu.:0 3rd Qu.:1.000000
Max. :8.00000 Max. :5.000000 Max. :10.000000 Max. :0 Max. :5.000000
总结：
> extract$alltweets.text[1:10]
[1] Helo #Payi!! #lobster!! #happyfiesta diptan!! \xed\xa0\xbc\xed\xbe\x89\xed\xa0\xbc\xed\xbe\x8a\xed\xa0\xbd\xed\xb8\x8d\xed\xa0\xbd\xed\xb1\x8c @ Diptan, Basco,Batanes http://t.co/rZy4QlIwxW
[2] Helo #Payi!! #lobster!! #happyfiesta diptan!! \xed\xa0\xbc\xed\xbe\x89\xed\xa0\xbc\xed\xbe\x8a\xed\xa0\xbd\xed\xb8\x8d\xed\xa0\xbd\xed\xb1\x8c @ Diptan, Basco,Batanes http://t.co/rZy4QlIwxW
[3] Helo #Payi!! #lobster!! #happyfiesta diptan!! \xed\xa0\xbc\xed\xbe\x89\xed\xa0\xbc\xed\xbe\x8a\xed\xa0\xbd\xed\xb8\x8d\xed\xa0\xbd\xed\xb1\x8c @ Diptan, Basco,Batanes http://t.co/rZy4QlIwxW
[4] Helo #Payi!! #lobster!! #happyfiesta diptan!! \xed\xa0\xbc\xed\xbe\x89\xed\xa0\xbc\xed\xbe\x8a\xed\xa0\xbd\xed\xb8\x8d\xed\xa0\xbd\xed\xb1\x8c @ Diptan, Basco,Batanes http://t.co/rZy4QlIwxW
[5] Here is what's cooking at Gloria's Lechon in Iligan City! Who wants lechon manok? @ Gloria's Lechon http://t.co/9gxv4GxgIW
[6] Here is what's cooking at Gloria's Lechon in Iligan City! Who wants lechon manok? @ Gloria's Lechon http://t.co/9gxv4GxgIW
[7] "@PBBabscbn: Pindot, pindot lang! Pindot, pindot lang! #PBBStopAndStare"
[8] "@PBBabscbn: Pindot, pindot lang! Pindot, pindot lang! #PBBStopAndStare"
[9] @eyyyorange dae pwede duman. Crowded na duman ta dakulon na boarders. Dae ngani ko duman makaadal tultol ta maribok. Inda matxt na lang ako
[10] Pindot pindot lang..pindot pindot pindot lang xD hahahahahaha
92162 Levels: ⃣ phones are the best \xed��\xed�\u008a _beown eyes tells his soul\nxo xo http://t.co/vzbMmzgdk7 ...
字符串列的示例：
{{1}}
答案 0 :(得分：1)
如评论中所示，您的问题归因于data.frame的结构。如果你无法解决问题的根源，你应该能够用以下方法解决它：
do.call(data.frame, extract) ## extract is the name of your original data frame
示例：
str(do.call(data.frame, extract))
# 'data.frame': 5 obs. of 15 variables:
# $ latitude : Factor w/ 2 levels "20.45164941",..: 1 1 1 1 2
# $ longitude : Factor w/ 2 levels "121.9671742",..: 1 1 1 1 2
# $ WordCount : int 7 7 7 7 13
# $ English : int 1 1 1 1 8
# $ Common : int 0 0 0 0 2
# $ Tagalog : int 0 0 0 0 0
# $ Bikol : int 3 3 3 3 3
# $ Cebuano : int 0 0 0 0 0
# $ Hiligaynon : int 0 0 0 0 0
# $ Ilocano : int 0 0 0 0 0
# $ Kapampangan : int 0 0 0 0 0
# $ Pangasinense: int 0 0 0 0 0
# $ Waray : int 0 0 0 0 0
# $ Zam : int 0 0 0 0 0
# $ Spanish : int 0 0 0 0 0
这是它应该是什么样子：
A <- tempfile()
write.csv(do.call(data.frame, extract), A)
readLines(A)
# [1] "\"\",\"latitude\",\"longitude\",\"WordCount\",\"English\",\"Common\",\"Tagalog\",\"Bikol\",\"Cebuano\",\"Hiligaynon\",\"Ilocano\",\"Kapampangan\",\"Pangasinense\",\"Waray\",\"Zam\",\"Spanish\""
# [2] "\"20\",\"20.45164941\",\"121.9671742\",7,1,0,0,3,0,0,0,0,0,0,0,0"
# [3] "\"77\",\"20.45164941\",\"121.9671742\",7,1,0,0,3,0,0,0,0,0,0,0,0"
# [4] "\"106\",\"20.45164941\",\"121.9671742\",7,1,0,0,3,0,0,0,0,0,0,0,0"
# [5] "\"48670\",\"20.45164941\",\"121.9671742\",7,1,0,0,3,0,0,0,0,0,0,0,0"
# [6] "\"94831\",\"8.19183664\",\"124.17909375\",13,8,2,0,3,0,0,0,0,0,0,0,0"