我正在合并近 3.000 个 csv 文件，删除重复的行，并编写一个新的 csv 数据文件。为此，我使用了以下代码：
#Grab our list of filenames
filenames <- list.files(path = ".", pattern='^.*\\.csv$')
#Read.csv function
my.read.csv <- function(fnam) { read.csv(fnam, header=FALSE, skip=1, sep=';', col.names=c('ID','tweet','author','local.time','extra'), colClasses=rep('character', 5))}
#Read all the files into one data.frame
my.df <- do.call("rbind", lapply(filenames, my.read.csv)) length(my.df[,1])
#Remove the duplicate tweets
my.new.df <- my.df[!duplicated(paste(my.df$tweet, my.df$author)),]
length(my.new.df[,1])
#Write new dataframe as a .csv file
write.csv(my.new.df, file =paste("Dataset", ".csv"))
尽管该函数做了它应该做的事情，但输出文件很混乱。原始的 csv 文件都具有以下结构：
tweet author local.time
2012-06-05 00:01:45 @A (A1): Cruijff z'n (...)#bureausport. A (A1) 05-06-12 00:01
2012-06-05 00:01:41 @B (B1): Welterusten #BureauSport B (B1) 05-06-12 00:01
2012-06-05 00:01:38 @C (C1): Echt (...) #bureausport C (C1) 05-06-12 00:01
2012-06-05 00:01:38 @D (D1): LOL. #bureausport D (D1) 05-06-12 00:01
但是输出文件具有以下结构：
,"ID","tweet","author","local.time","extra"
1,"2012-06-05 00:01:45 @A (A1): Cruijff z'n (...)#bureausport.","@A (A1)","05-06-12 00:01"
2,"2012-06-05 00:01:41 @B (B1): Welterusten #BureauSport","@B (B1)","05-06-12 00:01"
3,"2012-06-05 00:01:38 @C (C1): Echt (...) #bureausport","Aliceislovely (Alice Luyben)","05-06-12 00:01"
4,"2012-06-05 00:01:38 @D (D1): LOL. #bureausport","@D (D1)","05-06-12 00:01"
因此，它将数据显示为字符串而不是列。我希望你能帮我调整代码（上图），使输出文件具有与原始（输入）csv 文件相同的列结构。
顺便说一句，以下代码用于创建 csv 文件：
library(XML) # htmlTreeParse
twitter.search <- "Keyword"
QUERY <- URLencode(twitter.search)
# Set time loop (in seconds)
d_time = 300
number_of_times = 3000
for(i in 1:number_of_times){
tweets <- NULL
tweet.count <- 0
page <- 1
read.more <- TRUE
while (read.more)
{
# construct Twitter search URL
URL <- paste('http://search.twitter.com/search.atom?q=',QUERY,'&rpp=100&page=', page, sep='')
# fetch remote URL and parse
XML <- htmlTreeParse(URL, useInternal=TRUE, error = function(...){})
# Extract list of "entry" nodes
entry <- getNodeSet(XML, "//entry")
read.more <- (length(entry) > 0)
if (read.more)
{
for (i in 1:length(entry))
{
subdoc <- xmlDoc(entry[[i]]) # put entry in separate object to manipulate
published <- unlist(xpathApply(subdoc, "//published", xmlValue))
published <- gsub("Z"," ", gsub("T"," ",published) )
# Convert from GMT to central time
time.gmt <- as.POSIXct(published,"GMT")
local.time <- format(time.gmt, tz="Europe/Amsterdam")
title <- unlist(xpathApply(subdoc, "//title", xmlValue))
author <- unlist(xpathApply(subdoc, "//author/name", xmlValue))
tweet <- paste(local.time, " @", author, ": ", title, sep="")
entry.frame <- data.frame(tweet, author, local.time, stringsAsFactors=FALSE)
tweet.count <- tweet.count + 1
rownames(entry.frame) <- tweet.count
tweets <- rbind(tweets, entry.frame)
}
page <- page + 1
read.more <- (page <= 15) # Seems to be 15 page limit
}
}
names(tweets)
# top 15 tweeters
#sort(table(tweets$author),decreasing=TRUE)[1:15]
write.table(tweets, file=paste("Twitts - ", format(Sys.time(), "%a %b %d %H_%M_%S %Y"), ".csv"), sep = ";")
Sys.sleep(d_time)
} # end if