#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
as.character(drange[i])
w <- sample(1:2, 1)
Sys.sleep(w)
}
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
cat(as.character(drange[i]))
}
print(Sys.time()-strt)
stopCluster(cl)
writeLines(c(""), "log.txt")
cat(as.character(drange[i]))
writeLines(c(""), "log.txt")
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
cat(as.character(drange[i]),"\n")
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
cat(as.character(drange[i]),"\n")
w <- sample(1:3, 1)
Sys.sleep(w)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
cat(as.character(drange[i]),"\n")
#   w <- sample(1:3, 1)
#   Sys.sleep(w)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
sink("log.txt", append=TRUE)
cat(as.character(drange[i]),"\n")
#   w <- sample(1:3, 1)
#   Sys.sleep(w)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:3, 1)
Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:10, 1)
Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:10, 1)
#Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
ls<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:10, 1)
#Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
View(data)
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
data<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:10, 1)
#Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
rm(ls)
data
#import packages
library(foreach)
library(doParallel)
#setup parallel backend to use 8 processors
cl<-makeCluster(3)
registerDoParallel(cl)
#start time
strt<-Sys.time()
writeLines(c(""), "log.txt")
#loop
df<-foreach(i = 1:length(drange)) %dopar% {
w <- sample(1:10, 1)
#Sys.sleep(w)
cat(paste("\n","Starting iteration",i,"\n"), file="log.txt", append=TRUE)
as.character(drange[i])
}
print(Sys.time()-strt)
stopCluster(cl)
df
view(df)
View(df)
# Parallelisation
writeLines(c(""), "log.txt")
cl<-makeCluster(3)
registerDoParallel(cl)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- readLines("issues.xml")
issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
issuelist <- xmlToList(issuelist)
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
tagexpand <- c("", "s", "n", "en", "er")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(3)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
sink("log.txt", append=TRUE)
cat(as.character(curdate),"\n")
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
cat("Starting tweet", t, "of",as.character(curdate),"\n")
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issueheads)) {
curissue <- issueheads[i]
curtags <- as.character(issuelist[[curissue]])
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Now expand the current tag by possible suffixes that may be plural forms
if(!curacro) {
for(e in 1:length(tagexpand)) {
curtag[e] <- str_c(curtag[1], tagexpand[e])
}
}
# Set Levenshtein distance depending on char length
if(curchars <= 4) {
curdistance <- 0
} else {
curdistance <- 1
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow also 1 (Levenshtein distance)
tags_found <- NULL
# Match the tweet with each variation of tagexpand
for(e in 1:length(curtag)) {
tags_found[e] <- smartPatternMatch(curtext, curtag[e], curdistance, curacro)
}
tags_found <- any(tags_found)
curtag <- curtag[1]
if(tags_found == TRUE) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
cat("Match!\n")
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
#rm(tweets_curday,curacro, curchars, curdate,curfile,curid,curissue,curtag,curtags,curtext,d,date_end,date_start,i,id_folder,oldissue,oldtag,s,t,tags_found)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- readLines("issues.xml")
issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
issuelist <- xmlToList(issuelist)
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
tagexpand <- c("", "s", "n", "en", "er")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(3)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues)) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
sink("log.txt", append=TRUE)
cat(as.character(curdate),"\n")
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
cat("Starting tweet", t, "of",as.character(curdate),"\n")
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issueheads)) {
curissue <- issueheads[i]
curtags <- as.character(issuelist[[curissue]])
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Now expand the current tag by possible suffixes that may be plural forms
if(!curacro) {
for(e in 1:length(tagexpand)) {
curtag[e] <- str_c(curtag[1], tagexpand[e])
}
}
# Set Levenshtein distance depending on char length
if(curchars <= 4) {
curdistance <- 0
} else {
curdistance <- 1
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow also 1 (Levenshtein distance)
tags_found <- NULL
# Match the tweet with each variation of tagexpand
for(e in 1:length(curtag)) {
tags_found[e] <- smartPatternMatch(curtext, curtag[e], curdistance, curacro)
}
tags_found <- any(tags_found)
curtag <- curtag[1]
if(tags_found == TRUE) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
cat("Match!\n")
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
#rm(tweets_curday,curacro, curchars, curdate,curfile,curid,curissue,curtag,curtags,curtext,d,date_end,date_start,i,id_folder,oldissue,oldtag,s,t,tags_found)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- readLines("issues.xml")
issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
issuelist <- xmlToList(issuelist)
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
tagexpand <- c("", "s", "n", "en", "er")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(3)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues), .packages = c("stringr")) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
sink("log.txt", append=TRUE)
cat(as.character(curdate),"\n")
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
cat("Starting tweet", t, "of",as.character(curdate),"\n")
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issueheads)) {
curissue <- issueheads[i]
curtags <- as.character(issuelist[[curissue]])
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Now expand the current tag by possible suffixes that may be plural forms
if(!curacro) {
for(e in 1:length(tagexpand)) {
curtag[e] <- str_c(curtag[1], tagexpand[e])
}
}
# Set Levenshtein distance depending on char length
if(curchars <= 4) {
curdistance <- 0
} else {
curdistance <- 1
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow also 1 (Levenshtein distance)
tags_found <- NULL
# Match the tweet with each variation of tagexpand
for(e in 1:length(curtag)) {
tags_found[e] <- smartPatternMatch(curtext, curtag[e], curdistance, curacro)
}
tags_found <- any(tags_found)
curtag <- curtag[1]
if(tags_found == TRUE) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
cat("Match!\n")
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
stopCluster(cl)
View(issues)
cl
df
View(data)
stopCluster(cl)