current status

This commit is contained in:
2015-01-18 22:46:54 +01:00
parent ba40416197
commit 24f5b02221
6 changed files with 431 additions and 394 deletions
+386 -386
View File
@@ -1,389 +1,3 @@
source("issuecomp-codingsample-function2.R")
}
if(c_errcode == "1") {
#cat("Which issue is incorrect?\n")
repeat {
c_tag <- readYN("Which issue is incorrect?: ")
c_tag <- unlist(str_split(c_tag, ";"))
for(i in 1:length(c_tag)) {
if(checkIssue(c_tag[i], c_issueheads)) {status[i] <- TRUE} else {cat("Issue",c_tag[i],"does not exist. Please try again.\n")}
}
if(all(status)) {
break
}
}
if(c_errcode == "1") {
#cat("Which issue is incorrect?\n")
repeat {
c_tag <- readYN("Which issue is incorrect?: ")
c_tag <- unlist(str_split(c_tag, ";"))
for(i in 1:length(c_tag)) {
if(checkIssue(c_tag[i], c_issueheads)) {status[i] <- TRUE} else {cat("Issue",c_tag[i],"does not exist. Please try again.\n")}
}
if(all(status)) {
break
}
}
}
wdq
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
source("issuecomp-codingsample-function2.R")
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
checkAllIssues <- function(string, issuelist) {
string <- unlist(str_split(string, ";"))
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
}
test
checkAllIssues <- function(string, issuelist) {
string <- unlist(str_split(string, ";"))
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
test <- "issue.edathy"
checkAllIssues(test, c_issueheads)
test <- "issue.edathy"
checkAllIssues(test, c_issueheads)
rm(status)
checkAllIssues(test, c_issueheads)
checkAllIssues <- function(string, issuelist) {
status <- NULL
string <- unlist(str_split(string, ";"))
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
checkAllIssues(test, c_issueheads)
checkAllIssues("wdjqaowd", c_issueheads)
test <- checkAllIssues("wdjqaowd", c_issueheads)
test
test <- checkAllIssues("wdjqaow;wiqud", c_issueheads)
test
test <- checkAllIssues("wdjqaow;issue.edathy", c_issueheads)
test
checkAllIssues <- function(string, issuelist) {
status <- NULL
string <- unlist(str_split(string, ";"))
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
checkAllIssues <- function(string, issuelist) {
status <- NULL
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
c_errtags <- as.character(c_errors$tags[r])
c_errtext <- as.character(c_errors$text[r])
cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errtags, "\n", sep="")
source("issuecomp-codingsample-function2.R")
}
View(c_issues)
View(tweets)
tweets$tagged <- NULL
View(c_tweets)
View(tweets)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
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)){
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curtext <- str_replace_all(curtext, "$", " ")
curtext <- str_replace_all(curtext, "http://.+?\\s", "URL ")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issuelist)) {
curtags <- as.character(issuelist[[i]])
curissue <- names(issuelist)[i]
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
tags_found <- smartPatternMatch(curtext, curtag, curchars, curacro)
if(tags_found == 1) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
date_start <- as.Date("2014-01-01")
date_end <- as.Date("2014-12-31")
drange <- as.integer(date_end - date_start)
drange <- date_start + days(0:drange)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
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)){
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curtext <- str_replace_all(curtext, "$", " ")
curtext <- str_replace_all(curtext, "http://.+?\\s", "URL ")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issuelist)) {
curtags <- as.character(issuelist[[i]])
curissue <- names(issuelist)[i]
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
tags_found <- smartPatternMatch(curtext, curtag, curchars, curacro)
if(tags_found == 1) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
View(tweets)
View(tweets)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
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)){
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curtext <- str_replace_all(curtext, "$", " ")
curtext <- str_replace_all(curtext, "http://.+?\\s", "URL ")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issuelist)) {
curtags <- as.character(issuelist[[i]])
curissue <- names(issuelist)[i]
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
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
tags_found <- smartPatternMatch(curtext, curtag, curchars, curacro)
if(tags_found == 1) {
# 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)
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
View(tweets)
View(c_errors)
View(tweets)
readYN <- function(question) {
n <- readline(prompt=question)
n <- as.character(n)
return(n)
}
checkIssue <- function(string, issuelist) {
status <- any(str_detect(string, issuelist))
return(status)
}
checkAllIssues <- function(string, issuelist) {
status <- NULL
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
View(tweets)
View(tweets)
write.csv(tweets, "tweets.csv")
save(tweets, file="tweets.RData")
write.csv(tweets, "tweets.csv")
save(tweets, file="tweets.RData")
c_tweets <- read.csv("tweets.csv")
View(c_tweets)
c_tweets$X <- NULL
# Read all issues from XML file
c_issues <- data.frame(date = drange)
c_issuelist <- xmlToList("issues.xml")
c_issueheads <- names(issuelist)
c_issues[issueheads] <- 0
source("issuecomp-codingsample-function.R")
rm(c_err, c_result, c_samid, c_samno,c_samtags,c_samissue,c_samtext,c_yn)
rm(c_samtag)
rm(tweets_curday,curacro, curchars, curdate,curfile,curid,curissue,curtag,curtags,curtext,d,date_end,date_start,drange,i,id_folder,oldissue,oldtag,s,t,tags_found)
c_errors <- read.csv("issuecomp-codingsample-error.csv", header = F, sep=",", colClasses="character")
View(c_errors)
names(c_errors) <- c("str_id", "code", "issue", "tags", "text")
View(c_errors)
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$code[r])
@@ -510,3 +124,389 @@ acc_df <- acc_df[-delrow, ]
rm(delrow, r, acc)
acc_df$row.names <- NULL
row.names(acc_df) <- NULL
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
source("issuecomp-functions.R")
load("tweets.RData")
View(tweets)
View(tweets)
View(tweets)
date_start <- as.Date("2014-01-01")
date_start + days
date_start + days(1)
date_start + days(0)
date_start + days(0:2)
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)
curdate <- date_start + days(2)
curdate
tweets[tweets[, "created_at"] == curdate, "msg_id"]
View(tweets)
curdate
tweets[tweets[, "created_at"] == "2014-01-01", "msg_id"]
tweets[tweets[, "created_at"] == curdate, "id_str"]
drange
length(tweets[tweets[, "created_at"] == curdate, "id_str"])
length(tweets[tweets[, "created_at"] == curdate+1, "id_str"])
length(tweets[tweets[, "created_at"] == curdate+15, "id_str"])
stats <- data.frame(x=NULL)
View(stats)
stats <- data.frame(date=drange)
View(stats)
stats$tpd <- NULL
stats$tpd <- ""
stats$tpd <- NULL
stats$tpd[1] <- 2
View(stats)
stats$tpd[2] <- 3
View(stats)
stats$tpd <- ""
stats$tpd <- NULL
stats$tpd <- ""
stats$tpd[1] <- 2
View(tweets)
View(stats)
stats <- data.frame(date=drange)
stats$tpd <- ""
# Total number of tweets per day over time
for(r in 1:length(drange)) {
stats$tpd[r] <- length(tweets[tweets[, "created_at"] == curdate, "id_str"])
}
View(stats)
drange[2]
stats <- data.frame(date=drange)
stats$tpd <- ""
# Total number of tweets per day over time
for(r in 1:length(drange)) {
stats$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"])
}
View(stats)
plot.ts(x = stats$tpd, y=stats$date)
plot.ts(x = stats$date, y=stats$tpd)
g1 <- ggplot(stats, aes(date,tpd))
g1 <- g1 + geom_histogram(fill="steelblue", stat="identity")
g1 <- g1 + stat_smooth(size=1,colour="red",method="loess", se=FALSE)
g1 <- gg1 + ggtitle("Zeitliche Entwicklung von plötzlichen Medienfokussen") + xlab("Einzelne Monate") + ylab("Plötzliche Medienfokusse")
g1
g1 <- ggplot(stats, aes(date,tpd))
g1 <- g1 + geom_histogram(fill="steelblue", stat="identity")
g1
g1 <- g1 + stat_smooth(size=1,colour="red",method="loess", se=FALSE)
g1
g1 <- ggplot(stats, aes(date,tpd))
g1 <- g1 + geom_line()
g1
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd, color=black))
g1
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd, color="black"))
g1
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd))
g1
ggplot(stats, aes(date, tpd)) + geom_line() +
scale_x_date(format = "%b-%Y") + xlab("") + ylab("Daily Views")
ggplot(stats, aes(date, tpd)) + geom_line() +
scale_x_date() + xlab("") + ylab("Daily Views")
lapply(stats, class)
stats$tpd <- 0
lapply(stats, class)
stats <- data.frame(date=drange)
stats$tpd <- 0
# Total number of tweets per day over time
for(r in 1:length(drange)) {
stats$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"])
}
View(stats)
plot.ts(x = stats$date, y=stats$tpd)
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd))
g1
ggplot(stats, aes(date, tpd)) + geom_line() +
scale_x_date() + xlab("") + ylab("Daily Views")
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
stats_smooth(size=1,colour="red",method="loess", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
stat_smooth(size=1,colour="red",method="loess", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
stat_smooth(colour="red",method="loess", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
stat_smooth(colour="red",method="lm", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
geom_smooth(colour="red",method="lm", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
geom_smooth(colour="red",method="loess", se=FALSE)
g1
g1 <- ggplot() +
geom_line(data = stats, aes(x=date,y=tpd)) +
geom_smooth(size=1,colour="red",method="loess", se=FALSE)
g1
g1 <- g1 + geom_smooth(size=1,colour="red", method="loess", se=FALSE)
g1
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd))
g1 <- g1 + geom_smooth(size=1,colour="red", method="loess", se=FALSE)
g1
g1 <- ggplot() + geom_line(data = stats, aes(x=date,y=tpd))
g1
g1 + geom_smooth()
g1 + geom_smqwd
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd))
g1
g1 <- g1 + geom_smooth(size=1,colour="red", method="loess", se=FALSE)
g1
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd))
g1 <- g1 + geom_smooth(size=1,method="loess", se=FALSE)
g1
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd))
g1 <- g1 + geom_smooth(size=1,method="loess", se=FALSE, aes(group=1))
g1
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd)) +
geom_smooth(size=1,method="loess", se=FALSE, aes(group=1))
g1
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd)) +
geom_smooth(size=1,method="loess", se=FALSE, aes(x = date, y=tpd))
g1
geom_smooth(size=1,method="loess", se=FALSE)
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd)) +
geom_smooth(size=1,method="loess", se=FALSE)
g1
plot.ts(x = stats$date, y=stats$tpd)
g1 <- ggplot() + geom_point(data = stats, aes(x=date,y=tpd, color=group)) +
geom_smooth(size=1,method="loess", se=FALSE)
g1
install.packages(c("BH", "bibtex", "devtools", "dplyr", "httr", "jsonlite", "lazyeval", "manipulate", "RCurl", "ROAuth", "rstudioapi", "sp", "stringi"))
g1 <- ggplot(data = stats, aes(x=date,y=tpd, color=variable, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE)
g1
stats_melt <- melt(stats, id="date")
View(stats_melt)
View(stats_melt)
stats_melt <- melt(stats, id="date")
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color=variable, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE)
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color=1, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE)
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color=1, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, colors="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color=1, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color="black", group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,color="yellow", group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour="black", group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour="#FFFFFF", group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour="vqwdqw", group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=1, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color="red")
g1
g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
geom_line() +
geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
g1
require(lubridate)
require(XML)
require(ggplot2)
require(reshape2)
require(stringr)
source("issuecomp-functions.R")
rm(curdate)
rm(date_end, date_start)
rm(g1, r, )
rm(g1, r)
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
View(issues)
issuelist <- xmlToList("issues.xml")
issuelist
issueheads <- names(issuelist)
issueheads
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
View(issues)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
cat(as.character(curdate),"\n")
# Put all tweets from specific day in a temporary DF
tweets_curday <- tweets[tweets[, "created_at"] == curdate, ]
for(t in 1:nrow(tweets_curday)){
# Select tweet's text, make it lowercase and remove hashtag indicators (#)
curtext <- as.character(tweets_curday$text[t])
curtext <- str_replace_all(curtext, "#", "")
curid <- as.character(tweets_curday$id_str[t])
# Now test each single issue (not tag!)
for(i in 1:length(issuelist)) {
curtags <- as.character(issuelist[[i]])
curissue <- names(issuelist)[i]
curfile <- str_c(id_folder,"/",curissue,".csv")
# Now test all tags of a single issue
for(s in 1:length(curtags)) {
curtag <- curtags[s]
curchars <- nchar(curtag, type = "chars")
# Check if tag is an acronym. If so, ignore.case will be deactivated in smartPatternMatch
if(curchars <= 4) {
curacro <- checkAcronym(string = curtag, chars = curchars)
} else {
curacro <- FALSE
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
tags_found <- smartPatternMatch(curtext, curtag, curchars, curacro)
if(tags_found == 1) {
# Raise number of findings on this day for this issue by 1
issues[d,curissue] <- issues[d,curissue] + 1
# Add issue and first matched tag of tweet to tweets-DF
oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
# Add information to file for function viewPatternMatching
write(str_c(curdate,";\"",curid,"\";",curtag), curfile, append = TRUE)
break
}
else {
#cat("Nothing found\n")
}
} # /for curtags
} # /for issuelist
} # /for tweets_curday
} # /for drange
View(issues)
# MATCH TWEETS ------------------------------------------------------------
id_folder <- "matched-ids"
unlink(id_folder, recursive = TRUE)
dir.create(id_folder)
issues <- data.frame(date = drange)
issuelist <- xmlToList("issues.xml")
issueheads <- names(issuelist)
issues[issueheads] <- 0
tweets$issue <- ""
tweets$tags <- ""
for(d in 1:nrow(issues)) {
# Go through every day
curdate <- issues$date[d]
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)){
# 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(issuelist)) {
curtags <- as.character(issuelist[[i]])
curissue <- names(issuelist)[i]
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
}
# Match current tweet with tag. If >= 5 letters allow 1 changed letter, if >=8 letters allow 2 (Levenshtein distance)
tags_found <- smartPatternMatch(curtext, curtag, curchars, curacro)
if(tags_found == 1) {
# 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)
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)
View(issues)
save(issues, "issues.RData")
save(issues, file="issues.RData")
readYN <- function(question) {
n <- readline(prompt=question)
n <- as.character(n)
return(n)
}
checkIssue <- function(string, issuelist) {
status <- any(str_detect(string, issuelist))
return(status)
}
checkAllIssues <- function(string, issuelist) {
status <- NULL
for(i in 1:length(string)) {
if(checkIssue(string[i], issuelist)) {
status[i] <- TRUE
}
else {
cat("Issue",string[i],"does not exist. Please try again.\n")
status[i] <- FALSE
}
}
return(status)
}
require(stringr)
require(XML)