【R语言】文件读写sum

R获取数据
三种途径：键盘 读取本地 数据库
view()
edit() fix()
#Reading file from Database
install.packages(“RODBC”)

读取文本文件

read.table()

read.table(‘file’, header = FALSE, sep = “”, quote = “”'",
dec = “.”, numerals = c(“allow.loss”, “warn.loss”, “no.loss”),
row.names, col.names, as.is = !stringsAsFactors,
na.strings = “NA”, colClasses = NA, nrows = -1,
skip = 0, check.names = TRUE, fill = !blank.lines.skip,
strip.white = FALSE, blank.lines.skip = TRUE,
comment.char = “#”,
allowEscapes = FALSE, flush = FALSE,
stringsAsFactors = FALSE,
fileEncoding = “”, encoding = “unknown”, text, skipNul = FALSE)

默认sep为空格分隔
注意首行header是否为列名
读取空间: skip~nrows
na.strings 指定文本中的缺失值
stringsAsFactors 是否将字符串读取为因子类型

> x <- read.table ("input.txt")
> x <- read.table ("input.csv",sep=",",header = T)
> head(x)
                  X  mpg cyl disp  hp drat    wt  qsec vs am gear carb
1         Mazda RX4 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2     Mazda RX4 Wag 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3        Datsun 710 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
4    Hornet 4 Drive 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
5 Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
6           Valiant 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

x <- read.table ("input.csv",sep=",",header = T,skip = 50,nrows = 100,
                 na.strings = " ")
x <- read.table ("input.csv",sep=",",header = T,skip = 50,nrows = 100,
                 stringsAsFactors = F)

其它读取纯文本文件函数如 read.csv()等都是简化了分隔符的子函数

读取剪切板 readClipboard()

面对非标准的文件格式：
readlines() – 同py 返回每行为字符串
scan 用于复杂格式文件的处理

> readLines('scan.txt')
 [1] "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6"
 [4] "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6"
 [7] "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6" "one\t2\t3\tfour\t5\t6"
[10] "one\t2\t3\tfour\t5\t6" "" 

> x <- scan("scan.txt",what=list (character(3),numeric(0),numeric(0)))
Read 20 records
> x <- scan("scan.txt",what=list (X1=character(3),X2=numeric(0),X3=numeric(0)))
Read 20 records
> x
$X1
 [1] "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four"
[11] "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four"

$X2
 [1] 2 5 2 5 2 5 2 5 2 5 2 5 2 5 2 5 2 5 2 5

$X3
 [1] 3 6 3 6 3 6 3 6 3 6 3 6 3 6 3 6 3 6 3 6

写入文本文件

write系列函数与read系列对应
与cat()函数类似，但不显示在屏幕上而是写入文件
数据框——write.table
csv格式——write.csv

> write.table (df,file='newfile.txt')
# quote
> write.table (df,file='newfile.txt',quote = FALSE)
# 行列名（若单列且无列名，默认为文件输入名）
> write.table (df,file='newfile.txt',row.names = FALSE,col.names = FALSE)
# sep
> write.table (df,file='newfile.txt',row.names = FALSE,col.names = FALSE,sep = ',')
# append
> write.table (df,file='newfile.txt',row.names = FALSE,col.names = FALSE,sep = ',',append = TRUE)

读写Excel文件

读取一个excel文件的最好方法是在excel中将其导出为一个逗号分隔文件（csv），并使用前文描述的方式将其导入到R中

也可以使用专门的R包
XLConnect包 读写文件

library(XLConnect)
# 读
#Two step Read Excel File
ex <- loadWorkbook ("data.xlsx")
edata <- readWorksheet(ex,1)
head(edata)
edata <- readWorksheet(ex,1,startRow=0,starCol=0,endRow=50,endCol=3)

#One step Read Excel File ###
readWorksheetFromFile ("data.xlsx",1,startRow=0,starCol=0,
                       endRow=50,endCol=3,header=TRUE)

# 写
#Four step Wtire Excel File
wb <- loadWorkbook("file.xlsx",create=TRUE)
createSheet(wb,"Sheet 1")
writeWorksheet(wb,data=mtcars,sheet = "Sheet 1")
saveWorkbook()

#One step Wtire Excel File ###
writeWorksheetToFile("file.xlsx",data = mtcars,sheet = "Sheet 1")
vignette("XLConnect")

xlsx包 读写文件

library(xlsx)

rdata <- read.xlsx("data.xlsx",sheetIndex=1,startRow = 1,endRow = 100)

write.xlsx(rdata,file = "rdata.xlsx",sheetName = "Sheet 1",append = F)
help(package="xlsx")

或者通过将excel数据赋值到剪贴板，在剪贴板读取
rio包

> library(rio)
> x <- import('clipboard', header=T)
> x
   mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
3 22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
4 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
5 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
6 18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
7 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
8 24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
9 22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
> class(x)
[1] "data.frame"
> str(x)
'data.frame':	9 obs. of  11 variables:
...

可以先试试这些包
不行的话还是通过csv导入