将数据从 .txt 文件导入 R

Question

我是 R 的新手，正在尝试将 .txt 文件转换为 R，请参阅下面的示例。非常感谢，如果我能找到传输数据的解决方案。

.txt 文件中的数据：

user_14:beneficiary_649,beneficiary_1312,beneficiary_1983,beneficiary_726,beneficiary_759,beneficiary_229,beneficiary_673,
user_13:beneficiary_1928,beneficiary_553,beneficiary_483,beneficiary_1127,beneficiary_2887
user_11:beneficiary_2158,beneficiary_871,beneficiary_1969,beneficiary_1120,beneficiary_185,beneficiary_2180

期望 R 中的输出为：

user_14                 user_13                  user_11
beneficiary_649     beneficiary_1928         beneficiary_2158
beneficiary_1312    beneficiary_553          beneficiary_871
beneficiary_1983    beneficiary_483          beneficiary_1969
beneficiary_726     beneficiary_1127         beneficiary_1120
beneficiary_759     beneficiary_2887         beneficiary_185
beneficiary_229     beneficiary_2180
beneficiary_673

Answer 1

一个可能的解决方案：

使用 readLines 读取数据。修复 Tidyverse 的功能将所有内容放在它的位置。

input <- readLines("text_file.txt") # read the data from the text file

df <- data.frame(input = input, stringsAsFactors = F) # store it in a data.frame

library(tidyr)
library(dplyr)

df %>% 
  separate(input, into = c("users", "data"), sep = ":") %>%  # split users and rest
  separate_rows(data, sep = ",") %>%  # build rows from data
  group_by(users) %>% # group by needed for creating row numbers per user
  mutate(rowid = row_number()) %>% # add row numbers
  spread(users, data, fill = "") # put data under the users, empty values as "" instead of NA

# A tibble: 7 x 4
  rowid user_11          user_13          user_14         
  <int> <chr>            <chr>            <chr>           
1     1 beneficiary_2158 beneficiary_1928 beneficiary_649 
2     2 beneficiary_871  beneficiary_553  beneficiary_1312
3     3 beneficiary_1969 beneficiary_483  beneficiary_1983
4     4 beneficiary_1120 beneficiary_1127 beneficiary_726 
5     5 beneficiary_185  beneficiary_2887 beneficiary_759 
6     6 beneficiary_2180 ""               beneficiary_229 
7     7 ""               ""               beneficiary_673 

Answer 2

在 base 中，您可以使用strsplit 拆分: 和,，然后查看最长的字符向量有多长，并使用NA 填充所有其他字符向量@987654325 @ 也会转置向量。

tt <- readLines(con=textConnection("user_14:beneficiary_649,beneficiary_1312,beneficiary_1983,beneficiary_726,beneficiary_759,beneficiary_229,beneficiary_673,
user_13:beneficiary_1928,beneficiary_553,beneficiary_483,beneficiary_1127,beneficiary_2887
user_11:beneficiary_2158,beneficiary_871,beneficiary_1969,beneficiary_1120,beneficiary_185,beneficiary_2180"))

tt <- strsplit(tt, ":|,")  #Split on : or ,
ttn <- max(sapply(tt, length))  #Get longest vector
tt <- sapply(tt, function(x) x[seq_len(ttn)]) #Fill up with NA and give per col
colnames(tt)  <- tt[1,] #Set colnames from first line
tt <- tt[-1,]  #Remove first line
tt
#     user_14            user_13            user_11           
#[1,] "beneficiary_649"  "beneficiary_1928" "beneficiary_2158"
#[2,] "beneficiary_1312" "beneficiary_553"  "beneficiary_871" 
#[3,] "beneficiary_1983" "beneficiary_483"  "beneficiary_1969"
#[4,] "beneficiary_726"  "beneficiary_1127" "beneficiary_1120"
#[5,] "beneficiary_759"  "beneficiary_2887" "beneficiary_185" 
#[6,] "beneficiary_229"  NA                 "beneficiary_2180"
#[7,] "beneficiary_673"  NA                 NA                

Answer 3

您可以使用strsplit() 获取列表：

DF <- read.table(stringsAsFactors = FALSE, sep=':', text=
"user_14:beneficiary_649,beneficiary_1312,beneficiary_1983,beneficiary_726,beneficiary_759,beneficiary_229,beneficiary_673,
user_13:beneficiary_1928,beneficiary_553,beneficiary_483,beneficiary_1127,beneficiary_2887
user_11:beneficiary_2158,beneficiary_871,beneficiary_1969,beneficiary_1120,beneficiary_185,beneficiary_2180")
L <- strsplit(DF$V2, ',')
names(L) <- DF$V1

Answer 4

以上所有答案都是正确的，但这里是我使用 base R 找到的更简单的替代方法：

# Just read in your data as a comma separated data frame
df <- read.table("link to your file", header = F, sep = ',', fill = T)
# The first column will contain both the user and the first "beneficiary" as they are separated by ":", so you need to split its values by ":"
k <- sapply(df[,1], function(x){strsplit(x, split = ":")[[1]]})
# Add the corrected first column to your data frame and transpose the data frame to have one column per user
df <- t(cbind(k[2,], df[,2:ncol(df)]))
# Provide the "user" as colnames
colnames(df) <- k[1,]
# I noticed that some lines in your text have a comma at the end, which introduces NAs. To remove them: 
df[is.na(df)] <- ""

Answer 5

感谢大家的尝试和建议：

我解决了问题并得到了我期望的确切数据表。在下面分享解决方案以供您查看以及是否有任何改进建议：

这是 users.txt 中的所有数据

user_14：beneficiary_649，beneficiary_1312，beneficiary_1983，beneficiary_726，beneficiary_759，beneficiary_229，beneficiary_673，beneficiary_2322，beneficiary_2598，beneficiary_1705，beneficiary_2743，beneficiary_220，beneficiary_977，beneficiary_1098，beneficiary_2891，beneficiary_1253，beneficiary_2065，beneficiary_1492，beneficiary_268，beneficiary_1991，beneficiary_684，beneficiary_1493，beneficiary_2294 ，beneficiary_73，beneficiary_1524，beneficiary_2349，beneficiary_2978，beneficiary_2575，beneficiary_2506，beneficiary_3051，beneficiary_612，beneficiary_617，beneficiary_1748，beneficiary_3031，beneficiary_2431，beneficiary_948，beneficiary_46，beneficiary_469，beneficiary_2047，beneficiary_1461，beneficiary_2549，beneficiary_2539，beneficiary_412，beneficiary_1615，beneficiary_2842，beneficiary_2228，beneficiary_2634，beneficiary_2534 ,受益人_358,受益人_1475,受益人_146,受益人_1971,受益人_1411,受益人_2395,受益人_1047,受益人_2062,受益人_2373,受益人_2328,受益人_1669,受益人iciary_2986，beneficiary_1040，beneficiary_248，beneficiary_1816，beneficiary_1465，beneficiary_133，beneficiary_2401，beneficiary_2626，beneficiary_1819，beneficiary_2864，beneficiary_1008，beneficiary_1101，beneficiary_2529，beneficiary_1487，beneficiary_787，beneficiary_2595，beneficiary_2947，beneficiary_2808，beneficiary_547，beneficiary_2113，beneficiary_825，beneficiary_396，beneficiary_2321，beneficiary_2512，beneficiary_72， beneficiary_90，beneficiary_957，beneficiary_1799，beneficiary_2787，beneficiary_277，beneficiary_2472，beneficiary_194，beneficiary_2521，beneficiary_760，beneficiary_558，beneficiary_2404，beneficiary_763，beneficiary_2466，beneficiary_1881，beneficiary_2483，beneficiary_107，beneficiary_1392，beneficiary_2558，beneficiary_557，beneficiary_1923，beneficiary_322，beneficiary_310，beneficiary_1655，beneficiary_226，beneficiary_527，受益人_2542,受益人_1372,受益人_142,受益人_1055,受益人_378,受益人_296,受益人_733,受益人_1755,受益人_1932,受益人_1989,受益人_1379，beneficiary_2199，beneficiary_1288，beneficiary_2877，beneficiary_1045，beneficiary_2613，beneficiary_2455，beneficiary_2503，beneficiary_706，beneficiary_1562，beneficiary_1446，beneficiary_247，beneficiary_1020，beneficiary_1250，beneficiary_777，beneficiary_2645，beneficiary_1850，beneficiary_2724，beneficiary_2192，beneficiary_715，beneficiary_1321，beneficiary_201，beneficiary_961，beneficiary_2802，beneficiary_414， beneficiary_1997，beneficiary_2760，beneficiary_82，beneficiary_2746，beneficiary_918，beneficiary_2386，beneficiary_729，beneficiary_3057，beneficiary_491，beneficiary_1190，beneficiary_1561，beneficiary_2744，beneficiary_923，beneficiary_1815，beneficiary_240，beneficiary_2016，beneficiary_2479，beneficiary_1692，beneficiary_1630，beneficiary_2899，beneficiary_965，beneficiary_2675，beneficiary_34，beneficiary_2226，beneficiary_550，受益人_1795,受益人_981,受益人_1934,受益人_2579,受益人_3012,受益人_2366,受益人_1684,受益人_2107,受益人_1249,受益人_2574,受益人y_1447，beneficiary_1052，beneficiary_219，beneficiary_357，beneficiary_2324，beneficiary_2791，beneficiary_2528，beneficiary_1066，beneficiary_2984，beneficiary_2559，beneficiary_767，beneficiary_1031，beneficiary_271，beneficiary_2278，beneficiary_15，beneficiary_463，beneficiary_917，beneficiary_1839，beneficiary_1048，beneficiary_2435，beneficiary_2441，beneficiary_1272，beneficiary_2056，beneficiary_993，beneficiary_371，受益人_2582,受益人_1476 user_13：beneficiary_1928，beneficiary_553，beneficiary_483，beneficiary_1127，beneficiary_2887，beneficiary_2184，beneficiary_1694，beneficiary_2276，beneficiary_1961，beneficiary_2994，beneficiary_781，beneficiary_1264，beneficiary_2001，beneficiary_1657，beneficiary_1065，beneficiary_636，beneficiary_1892，beneficiary_1091，beneficiary_2237，beneficiary_205，beneficiary_1699，beneficiary_2023，beneficiary_2767，beneficiary_104， beneficiary_157，beneficiary_1199，beneficiary_493，beneficiary_375，beneficiary_2614，beneficiary_1856，beneficiary_1177，beneficiary_3024，beneficiary_1185，beneficiary_1205，beneficiary_773，beneficiary_1508，beneficiary_2379，beneficiary_433，beneficiary_1801，beneficiary_33，beneficiary_510，beneficiary_2552，beneficiary_575，beneficiary_2492，beneficiary_2839，beneficiary_1033，beneficiary_1396，beneficiary_2281，beneficiary_41，受益人_677,受益人_2862,受益人_652,受益人_1582,受益人_2422,受益人_1599,受益人_2844,受益人_466,受益人_2639,受益人_984,受益人ry_407，beneficiary_1097，beneficiary_594，beneficiary_2073，beneficiary_2773，beneficiary_1504，beneficiary_3064，beneficiary_816，beneficiary_577，beneficiary_804，beneficiary_2148，beneficiary_949，beneficiary_2520，beneficiary_443，beneficiary_2453，beneficiary_408，beneficiary_554，beneficiary_754，beneficiary_2960，beneficiary_2344，beneficiary_1497，beneficiary_184，beneficiary_255，beneficiary_542，beneficiary_2004， beneficiary_692，beneficiary_89，beneficiary_1385，beneficiary_1814，beneficiary_2621，beneficiary_670，beneficiary_2022，beneficiary_24，beneficiary_2820，beneficiary_2958，beneficiary_1708，beneficiary_685，beneficiary_1552，beneficiary_420，beneficiary_2168，beneficiary_2209，beneficiary_2189，beneficiary_1474，beneficiary_2253，beneficiary_1159，beneficiary_2210，beneficiary_2537，beneficiary_177，beneficiary_1355，beneficiary_2092，受益人_2231,受益人_613,受益人_2227,受益人_520,受益人_2139,受益人_2742,受益人_720,受益人_770,受益人_1247,受益人_717 user_11：beneficiary_2158，beneficiary_871，beneficiary_1969，beneficiary_1120，beneficiary_185，beneficiary_2180，beneficiary_2120，beneficiary_1832，beneficiary_1470，beneficiary_2689，beneficiary_1679，beneficiary_769，beneficiary_2380，beneficiary_2999，beneficiary_1113，beneficiary_2932，beneficiary_1763，beneficiary_391，beneficiary_2381，beneficiary_650，beneficiary_419，beneficiary_1998，beneficiary_775，beneficiary_2590， beneficiary_2593，beneficiary_2042，beneficiary_2102，beneficiary_1765，beneficiary_1201，beneficiary_332，beneficiary_26，beneficiary_1273，beneficiary_799，beneficiary_79，beneficiary_2099，beneficiary_622，beneficiary_394，beneficiary_2830，beneficiary_934，beneficiary_1170，beneficiary_2297，beneficiary_3009，beneficiary_1278，beneficiary_1573，beneficiary_315，beneficiary_1610，beneficiary_1875，beneficiary_1899，beneficiary_88，受益人_560,受益人_508,受益人_1674,受益人_1490,受益人_1824,受益人_751,受益人_2122,受益人_936,受益人_132,受益人_2756,受益人_ 2246，beneficiary_561，beneficiary_2063，beneficiary_2600，beneficiary_2875，beneficiary_2333，beneficiary_3003，beneficiary_381，beneficiary_1528，beneficiary_1733，beneficiary_1316，beneficiary_573，beneficiary_2312，beneficiary_991，beneficiary_202，beneficiary_1858，beneficiary_17，beneficiary_2130，beneficiary_571，beneficiary_1631，beneficiary_2720，beneficiary_2132，beneficiary_1526，beneficiary_232，beneficiary_2444， beneficiary_1721，beneficiary_537，beneficiary_2408，beneficiary_1918，beneficiary_946，beneficiary_300，beneficiary_2049，beneficiary_768，beneficiary_1854，beneficiary_2028，beneficiary_319，beneficiary_1433，beneficiary_343，beneficiary_2897，beneficiary_61，beneficiary_1803，beneficiary_2400，beneficiary_2758，beneficiary_910，beneficiary_7，beneficiary_172，beneficiary_1503，beneficiary_453，beneficiary_69，beneficiary_823，受益人_986,受益人_2123,受益人_802 user_27：beneficiary_1003，beneficiary_1919，beneficiary_2304，beneficiary_2597，beneficiary_2242，beneficiary_2818，beneficiary_580，beneficiary_305，beneficiary_651，beneficiary_260，beneficiary_2071，beneficiary_1703，beneficiary_3052，beneficiary_2588，beneficiary_2860，beneficiary_2943，beneficiary_1293，beneficiary_2066，beneficiary_2191，beneficiary_1135，beneficiary_2084，beneficiary_994，beneficiary_2658，beneficiary_628， beneficiary_2313，beneficiary_2355，beneficiary_2730，beneficiary_1634，beneficiary_2159，beneficiary_974，beneficiary_3016，beneficiary_678，beneficiary_2665，beneficiary_1325，beneficiary_1598，beneficiary_1985，beneficiary_416，beneficiary_274，beneficiary_369，beneficiary_1802，beneficiary_3054，beneficiary_2648，beneficiary_663，beneficiary_960，beneficiary_2190，beneficiary_476，beneficiary_405，beneficiary_1256，beneficiary_85，受益人_1782,受益人_2949,受益人_947,受益人_1384,受益人_401,受益人_1026,受益人_2208,受益人_1304,受益人_1455,受益人_2198,受益人iary_2556，beneficiary_1871，beneficiary_449，beneficiary_1566，beneficiary_52，beneficiary_811，beneficiary_1859，beneficiary_559，beneficiary_1798，beneficiary_1067，beneficiary_494，beneficiary_2908，beneficiary_16，beneficiary_1940，beneficiary_94，beneficiary_2375，beneficiary_842，beneficiary_1976，beneficiary_1424，beneficiary_2221，beneficiary_1794，beneficiary_2982，beneficiary_2640，beneficiary_353，beneficiary_1565，受益人_195,受益人_1017,受益人_1458,受益人_1004,受益人_820,受益人_1187,受益人_1716,受益人_91,受益人_2478,受益人_1596,受益人_632,受益人_2382,受益人_1847,受益人_1847

#Get data file from .txt
usersDbase <- read.csv("C:/Users/users.txt", header=FALSE)

#naming column Automatically with a prefix and auto number
colnames(usersDbase) <- paste0("Ben", 1:ncol(usersDbase))

#Create AutoID as per row number
id <- rownames(usersDbase)
dwithID <- cbind(id=id, usersDbase)


#Split one column into two columns
df1 <- setNames(data.frame(do.call("rbind",strsplit(gsub("\\(|\\)|,","",dwithID$Ben1),split=" "))),c("User","Ben1"))

#pick specific column
library(dplyr)
dfc1<-select(df1,'User')

#remove Special Character

library(dplyr)
dfc11<-dfc1 %>%
  mutate_all(funs(gsub("[[:punct:]]", "", .)))

#Create AutoID as per rownumber
id <- rownames(dfc11)
dwithIDS <- cbind(id=id, dfc11)


#pick specific column
library(dplyr)
dfben1<-select(df1,'Ben1')


#Create AutoID as per rownumber
id <- rownames(dfben1)
dbenwithIDS <- cbind(id=id, dfben1)

# Merge
mergeUb1<-merge(dwithIDS, dbenwithIDS, dwithIDS = "id",dbenwithIDS= "id")

#pick all except column 1

library(dplyr)
dwithIDAll<-select(dwithID,-"Ben1")


#merge 

mergeall<-merge(mergeUb1, dwithIDAll, mergeUb1 = "id",dwithIDAll= "id")

#pick all except column 1

library(dplyr)
UsersClean<-select(mergeall,-"id") 

# Transpose data where first column will be taken as header

Finaldf = setNames(data.frame(t(UsersClean[,-1])), UsersClean[,1])

# Remove rowname
rownames(Finaldf) <- c()

#Remove all temporary data frame and values

rm(dbenwithIDS, df1, dfben1,dfc1,dfc11,dwithID,dwithIDAll,dwithIDS,mergeall,mergeUb1,UsersClean,usersDbase, "id")