ongoing categorisation

This commit is contained in:
2015-02-23 02:06:01 +01:00
parent d7de9dda0c
commit eaffcf3db2
4 changed files with 446 additions and 363 deletions
+337 -337
View File
@@ -1,340 +1,3 @@
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,"\";",curissue,";",curtag), curfile, append = TRUE)
cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
# 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", "e")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(4)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
cat(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$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,"\";",curissue,";",curtag), curfile, append = TRUE)
cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
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)
stopCluster(cl)
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
library(foreach)
library(doParallel)
source("issuecomp-functions.R")
load(file = "tweets_untagged.RData")
# Create date range
date_start <- as.Date("2014-01-01")
date_end <- as.Date("2014-12-31")
drange <- as.integer(date_end - date_start)
drange <- date_start + days(0:drange)
# 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$tags <- ""
tagexpand <- c("", "s", "n", "en", "er", "e")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(4)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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,"\";",curissue,";",curtag), curfile, append = TRUE)
cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
# 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", "e")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(4)
registerDoParallel(cl)
df<-foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
cat(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$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,"\";",curissue,";",curtag), curfile, append = TRUE)
cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
df
# 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 <- ""
@@ -510,3 +173,340 @@ else {
} # /for issuelist
} # /for tweets_curday
} # /for drange
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
library(foreach)
library(doParallel)
# 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", "e")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(4)
registerDoParallel(cl)
foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
# cat(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$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,"\";",curissue,";",curtag), curfile, append = TRUE)
# cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
stopCluster(cl)
drange
drange[40]
drange[50]
View(issues)
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
library(foreach)
library(doParallel)
drange[70]
drange[80]
drange[90]
cl<-makeCluster(4)
registerDoParallel(cl)
foreach(d = 51:90, .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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,"\";",curissue,";",curtag), curfile, append = TRUE)
# cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
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)
stopCluster(cl)
drange[121]
cl<-makeCluster(4)
registerDoParallel(cl)
foreach(d = 91:120, .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
# cat(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$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,"\";",curissue,";",curtag), curfile, append = TRUE)
# cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
stopCluster(cl)
drange[102]
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
library(foreach)
library(doParallel)
cl<-makeCluster(4)
registerDoParallel(cl)
foreach(d = 101:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(paste(as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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(paste("Starting tweet", t, "of",as.character(curdate),"\n"), file="issuecomp-analysis.log", append=TRUE)
# 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,"\";",curissue,";",curtag), curfile, append = TRUE)
# cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
# data.frame(date=curdate, issue=curissue)
break # next issue, no more tags from same issue
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
+4 -4
View File
@@ -21,8 +21,8 @@ drange <- date_start + days(0:drange)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
#unlink(id_folder, recursive = TRUE)
#dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- readLines("issues.xml")
@@ -37,10 +37,10 @@ tagexpand <- c("", "s", "n", "en", "er", "e")
# Parallelisation
writeLines(c(""), "issuecomp-analysis.log")
cl<-makeCluster(4)
cl<-makeCluster(3)
registerDoParallel(cl)
foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
foreach(d = 101:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
#for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
+105 -22
View File
@@ -3,25 +3,108 @@
2014-01-02
2014-01-03
2014-01-04
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
Match!
2014-01-05
2014-01-06
2014-01-07
2014-01-08
2014-01-09
2014-01-10
2014-01-11
2014-01-12
2014-01-13
2014-01-14
2014-01-15
2014-01-16
2014-01-17
2014-01-18
2014-01-19
2014-01-20
2014-01-21
2014-01-22
2014-01-23
2014-01-24
2014-01-25
2014-01-26
2014-01-27
2014-01-28
2014-01-29
2014-01-30
2014-01-31
2014-02-01
2014-02-02
2014-02-03
2014-02-04
2014-02-05
2014-02-06
2014-02-07
2014-02-08
2014-02-09
2014-02-10
2014-02-11
2014-02-12
2014-02-13
2014-02-14
2014-02-15
2014-02-16
2014-02-17
2014-02-18
2014-02-19
2014-02-20
2014-02-21
2014-02-22
2014-02-23
2014-02-20
2014-02-21
2014-02-22
2014-02-23
2014-02-24
2014-02-25
2014-02-26
2014-02-27
2014-02-28
2014-03-01
2014-03-02
2014-03-03
2014-03-04
2014-03-05
2014-03-06
2014-03-07
2014-03-08
2014-03-09
2014-03-10
2014-03-11
2014-03-12
2014-03-13
2014-03-14
2014-03-15
2014-03-16
2014-03-17
2014-03-18
2014-03-19
2014-03-20
2014-03-21
2014-03-22
2014-03-23
2014-03-24
2014-03-25
2014-03-26
2014-03-27
2014-03-28
2014-03-29
2014-03-30
2014-03-31
2014-04-01
2014-04-02
2014-04-03
2014-04-04
2014-04-05
2014-04-06
2014-04-07
2014-04-08
2014-04-09
2014-04-10
2014-04-11
2014-04-12
2014-04-13
2014-04-14
2014-04-15
BIN
View File
Binary file not shown.