update to latest version

.Rhistory

@@ -1,281 +1,175 @@
-load(file = "tweets_untagged.RData")
-setwd("~/Dokumente/Uni/Aktuell/BA-Arbeit/uni-ba-issuecomp")
-results_files <- "matched-ids/all.csv"
-load(file = "tweets_untagged.RData")
-View(issues)
-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 <- ""
-View(results)
-rm(r, results_temp, results_files)
-results <- results[!duplicated(results), ]
-names(results) <- c("date", "id_str", "issue", "tags")
-results <- results[order(results$id_str), ]
-row.names(results) <- NULL
-for(r in 1:nrow(results)) {
-curdate <- as.character(results$date[r])
-curid <- as.character(results$id_str[r])
-curissue <- as.character(results$issue[r])
-curtag <- as.character(results$tags[r])
-cat("Sorting match", r, "of 53383 \n")
-# Update issue counter (date and issue)
-issues[issues[, "date"] == curdate, curissue] <- issues[issues[, "date"] == curdate, curissue] + 1
-# Update tweet dataframe (id, issue and tags)
-oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
-tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ",")
-oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
-tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ",")
-}
-curdate
-curissue
-issues[issues[, "date"] == curdate, curissue]
-issueheads
-issuelist <- readLines("issues-v2.xml")
-issues <- data.frame(date = drange)
-issuelist <- readLines("issues-v2.xml")
-issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
-issuelist <- xmlToList(issuelist)
-issueheads <- names(issuelist)
-issues[issueheads] <- 0
-tweets$issue <- ""
-tweets$tags <- ""
-for(r in 1:nrow(results)) {
-curdate <- as.character(results$date[r])
-curid <- as.character(results$id_str[r])
-curissue <- as.character(results$issue[r])
-curtag <- as.character(results$tags[r])
-cat("Sorting match", r, "of 53383 \n")
-# Update issue counter (date and issue)
-issues[issues[, "date"] == curdate, curissue] <- issues[issues[, "date"] == curdate, curissue] + 1
-# Update tweet dataframe (id, issue and tags)
-oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
-tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ",")
-oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
-tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ",")
-}
-results[33170,]
-results[33171,]
-results$date[33170]
-results$date[33170] <- "2014-08-21"
-for(r in 33170:nrow(results)) {
-curdate <- as.character(results$date[r])
-curid <- as.character(results$id_str[r])
-curissue <- as.character(results$issue[r])
-curtag <- as.character(results$tags[r])
-cat("Sorting match", r, "of 53383 \n")
-# Update issue counter (date and issue)
-issues[issues[, "date"] == curdate, curissue] <- issues[issues[, "date"] == curdate, curissue] + 1
-# Update tweet dataframe (id, issue and tags)
-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, ",")
-}
-save(tweets, file="tweets_tagged.RData")
-write.csv(tweets, file="tweets.csv")
-save(issues, file="issues.RData")
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.text = element_text(size = 18))
+g_perday
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 18))
+g_perday
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 12))
+g_perday
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 13))
+g_perday
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14, face="plain")) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 13))
+g_perday
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 13))
+g_perday
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie") +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 13))
+g_entrop
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")# +
+#   theme(legend.title = element_text(size=14)) +
+#   theme(legend.text = element_text(size=12)) +
+#   theme(axis.title = element_text(size = 13))
+g_entrop
+detach("package:ggplot2", unload=TRUE)
+library("ggplot2", lib.loc="/usr/lib/R/site-library")
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")# +
+#   theme(legend.title = element_text(size=14)) +
+#   theme(legend.text = element_text(size=12)) +
+#   theme(axis.title = element_text(size = 13))
+g_entrop
+theme()
 require(stringr)
 require(reshape2)
 require(ggplot2)
 require(vars)
-drop_s <- which(str_detect(names(issues), "^s"))
-drop_i <- which(str_detect(names(issues), "^i"))
-issues_i <- issues[,-drop_s]
-issues_s <- issues[,-drop_i]
-issues_i$total <- rowSums(issues_i[2:ncol(issues_i)])
-issues_i$entropy <- 0
-for(r in 1:nrow(issues_i)) {
-curtotal <- as.numeric(issues_i$total[r])
-curp <- 0
-for(c in 2:ncol(issues_i)) {
-curcount <- as.numeric(issues_i[r,c])
-curp[c] <- curcount / curtotal
-}
-curp <- curp [2:length(curp)-2]
-curdrop <- which(curp==0)
-curp <- curp[-curdrop]
-issues_i$entropy[r] <- sum(-1 * curp * log(curp))
-}
-issues_s$total <- rowSums(issues_s[2:ncol(issues_s)])
-issues_s$entropy <- 0
-for(r in 1:nrow(issues_s)) {
-curtotal <- as.numeric(issues_s$total[r])
-curp <- 0
-for(c in 2:ncol(issues_s)) {
-curcount <- as.numeric(issues_s[r,c])
-curp[c] <- curcount / curtotal
-}
-curp <- curp [2:length(curp)-2]
-curdrop <- which(curp==0)
-curp <- curp[-curdrop]
-issues_s$entropy[r] <- sum(-1 * curp * log(curp))
-}
-stats_total <- data.frame(date=drange)
-stats_total$tpd <- 0
-stats_total$ipd <- issues_i$total
-stats_total$spd <- issues_s$total
-# Total number of tweets per day over time
-for(r in 1:length(drange)) {
-stats_total$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"])
-}
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
+theme()
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")# +
+#   theme(legend.title = element_text(size=14)) +
+#   theme(legend.text = element_text(size=12)) +
+#   theme(axis.title = element_text(size = 13))
+g_entrop
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")
+g_entrop
+g_perday <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
 geom_line()+
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation"))
+g_perday
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")
+g_entrop
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
 geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
+g_entrop
 stats_entropy <- data.frame(date=drange)
 stats_entropy$entropy <- issues_i$entropy
 stats_entropy <- melt(stats_entropy, id="date")
-g1 <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
 geom_line() +
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-test <- VAR(issues[,2:32], p=1, type="none")
-View(issues_i)
-View(issues_s)
-View(issues)
-test <- VAR(issues[,2:44], p=1, type="none")
-VAR(issues_s[,2:23], p=1, type=c("const", "trend", "both", "none"), season=NULL, exogen = issues_i[2:22])
-plot(irf(test, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
-rm(c_correct, c_curissue, c_errcode, c_errid, c_errissue, c_error1, c_error2, c_errors)
-rm(c_issues, c_issuelist, c_issueheads)
-rm(c_errtags, c_errtext, c_result, c_tag, c_tmp, c_tweets)
-require(stringr)
-require(XML)
-readYN <- function(question) {
-n <- readline(prompt=question)
-n <- as.character(n)
-return(n)
-}
-checkIssue <- function(string, issuelist) {
-status <- any(str_detect(string, issuelist))
-return(status)
-}
-checkAllIssues <- function(string, issuelist) {
-status <- NULL
-for(i in 1:length(string)) {
-if(checkIssue(string[i], issuelist)) {
-status[i] <- TRUE
-}
-else {
-cat("Issue",string[i],"does not exist. Please try again.\n")
-status[i] <- FALSE
-}
-}
-return(status)
-}
-View(tweets)
-c_tweets <- read.csv("tweets.csv", colClasses="character")
-for(r in 1:nrow(c_tweets)) {
-curtext <- as.character(c_tweets$text[r])
-if(str_detect(curtext, "\"")) {
-c_tweets$text[r] <- str_replace(curtext, "\"", "")
-}
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie")
+g_entrop
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie") +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 13))
+g_entrop
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie") +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 14))
+g_entrop
+g_perday <- 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) +
+xlab("Zeitraum") + ylab("Tweets pro Tag") +
+scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 14))
+g_perday
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+geom_line() +
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie") +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 14))
+g_entrop
+acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene"))
+acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats
+acc_parties$twitter <- 0
+for(p in 1:nrow(acc_parties)) {
+acc_parties$twitter[p] <- round(nrow(acc_df[acc_df$party == as.character(acc_parties$party[p]), ]) / 280 * 100)
 }
-c_tweets$X <- NULL
-c_issues <- data.frame(date = drange)
-c_issuelist <- xmlToList("issues-v2.xml")
-c_issueheads <- names(issuelist)
-c_issues[issueheads] <- 0
-source("issuecomp-codingsample-function.R")
-require(stringr)
-curtext
-curtext <- str_replace_all(curtext, "#", "")
-curtext <- str_replace_all(curtext, "-", " ")
-curtext
-curtext
-str_replace_all(curtext, "[^[:alnum:]]", "")
-str_replace_all(curtext, "[^[:alnum:]\s]", "")
-str_replace_all(curtext, "[^[:alnum:]\\s]", "")
-str_replace_all(curtext, "[^[:alnum:]^\\s]", "")
-str_replace_all(curtext, "[^[:alnum:]^\\S]", "")
-str_replace_all(curtext, "[^[:alnum:]][^\\s]", "")
-str_replace_all(curtext, "[^[:alnum:]][^\\S]", "")
-str_replace_all(curtext, "[^[:alnum:]][^[:blank]]", "")
-str_replace_all(curtext, "[^[:alnum:]][^[:blank:]]", "")
-str_replace_all(curtext, "[^[:alnum:]]", "")
-str_replace_all(curtext, "\\W", "")
-str_replace_all(curtext, "[\\W|\\S]", "")
-str_replace_all(curtext, "(\\W|\\S)", "")
-str_replace_all(curtext, "\\W|\\S", "")
-str_replace_all(curtext, "\\W", "")
-str_replace_all(curtext, "[\\W\\S]", "")
-str_replace_all(curtext, "[\\S\\W]", "")
-str_replace_all(curtext, "[\\s\\W]", "")
-str_replace_all(curtext, "[\\W\\s]", "")
-str_replace_all(curtext, "[\\W\s]", "")
-str_replace_all(curtext, "[\\Ws]", "")
-str_replace_all(curtext, "[\\W]", "")
-str_replace_all(curtext, "\\W", "")
-str_replace_all(curtext, "\\W|\\S", "")
-str_replace_all(curtext, "\\W|\\s", "")
-str_replace_all(curtext, "[^[:alnum:]]", "")
-str_replace_all(curtext, "[^[:alnum:] ]", "")
-str_replace_all(curtext, "[^[:alnum:]\\s]", "")
-str_replace_all(curtext, "[^[:alnum:] ]", "")
-curtext
-curtext <- "liebe @cdu, wir finden #Steuer gut, aber die KFZ-Steuer nicht!"
-curtext <- str_replace_all(curtext, "-", " ")
-curtext <- str_replace_all(curtext, "[^[:alnum:] ]", "")
-curtext
-curtext <- "liebe @cdu, wir finden #Steuer gut, aber die KFZ--Steuer nicht!"
-curtext <- str_replace_all(curtext, "-", " ")
-curtext <- str_replace_all(curtext, "[^[:alnum:] ]", "")
-curtext
-str_replace_all(curtext, "  ", " ")
-smartPatternMatch
-require(vars)
+require(jsonlite)
 require(stringr)
-adf1 <- summary(ur.df(issues))
-issues
-summary(issues)
-summary(issues[2:44])
-summary(issues[2:44], digits = 2)
-adf1 <- summary(ur.df(issues[, 2:44]), type ="trend", lags=1)
-data("Canda")
-data("Canada")
-class(Canada)
-class(issues)
-view(Canada)
-View(Canada)
-as.ts(issues)
-issues_ts <- as.ts(issues)
-class(issues_ts)
-View(issues_ts)
-View(issues)
-adf1 <- summary(ur.df(issues_ts[, 2:44]), type ="trend", lags=1)
-adf1 <- summary(ur.df(issues_ts[, 2]), type ="trend", lags=1)
-adf1 <- summary(ur.df(issues_ts[, 2], type ="trend", lags=1))
-adf1 <- summary(ur.df(issues_ts[, 2:44], type ="trend", lags=1))
-adf1 <- summary(ur.df(issues_ts[, 2], type ="trend", lags=1))
-adf1
-adf1 <- summary(ur.df(issues_ts[, 3], type ="trend", lags=1))
-adf1
-adf1 <- summary(ur.df(issues_ts[, 2], type ="none", lags=1))
-adf1
-adf1 <- summary(ur.df(issues_ts[, 2], type ="trend", lags=1))
-adf1
-summary(ur.df(issues_ts[, 2], type ="none", lags=1))
-VARselect(issues_ts[2:44], lag.max = 8, type = "both")
-VARselect(issues_ts[1:44], lag.max = 8, type = "both")
-VARselect(issues[1:44], lag.max = 8, type = "both")
-VARselect(issues[2:44], lag.max = 8, type = "both")
-VARselect(issues_ts[2:44], lag.max = 8, type = "both")
-VARselect(issues[2:44], lag.max = 8, type = "none")
-VARselect(issues[2:44], lag.max = 8, type = "trend")
-VARselect(issues[2:44], lag.max = 8, type = "const")
-VARselect(issues[2:44], lag.max = 8, type = "both")
-test <- VAR(issues[,2:44], p=1, type="both")
-# VAR(issues_s[,2:23], p=1, type=c("const", "trend", "both", "none"), season=NULL, exogen = issues_i[2:22])
-plot(irf(test, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
-summary(ur.df(issues_ts[, 2], type ="both", lags=1))
-summary(ur.df(issues_ts[, 2], type ="none", lags=1))
-test <- VAR(issues_ts[,2:44], p=1, type="both")
-plot(irf(test, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
+require(devtools)
+require(RTwitterAPI)
 acc_df <- read.csv("MdB-twitter.csv")
 delrow <- NULL
 for(r in 1:nrow(acc_df)) {
@@ -288,225 +182,331 @@ acc_df <- acc_df[-delrow, ]
 rm(delrow, r, acc)
 acc_df$row.names <- NULL
 row.names(acc_df) <- NULL
-View(acc_df)
-View(c_tweets)
+acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene"))
+acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats
+acc_parties$twitter <- 0
+for(p in 1:nrow(acc_parties)) {
+acc_parties$twitter[p] <- round(nrow(acc_df[acc_df$party == as.character(acc_parties$party[p]), ]) / 280 * 100)
+}
+pie(acc_parties$btw13, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T,
+main = "Seats of parties in the parliament")
+pie(acc_parties$twitter, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T,
+main = "Percentage of parties' MdBs of all Twitter accounts")
+pie(acc_parties$btw13, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T)
+View(acc_parties)
+pie(acc_parties$btw13, col=c("black", "red", "purple", "green"),
+labels = c("CDU/CSU (49.3%)", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T)
+pie(acc_parties$btw13, col=c("black", "red", "purple", "green"),
+labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Die LINKE (10,1%)", "Bündnis 90/Grüne(10.0%)"),
+clockwise = T)
+acc_parties <- data.frame(party = c("cducsu", "spd", "gruene", "linke"))
+acc_parties$btw13 <- c(49.3, 30.6, 10.0, 10.1) # seats of party / 631 seats
+acc_parties$twitter <- 0
+for(p in 1:nrow(acc_parties)) {
+acc_parties$twitter[p] <- round(nrow(acc_df[acc_df$party == as.character(acc_parties$party[p]), ]) / 280 * 100)
+}
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Bündnis 90/Grüne(10.0%)", "Die LINKE (10,1%)"),
+clockwise = T)
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"),
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Bündnis 90/Grüne(10,0%)", "Die LINKE (10,1%)"),
+clockwise = T)
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Bündnis 90/Grüne(10,0%)", "Die LINKE (10,1%)"),
+clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 90)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 180)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 270)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 360)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 20)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 20)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T, init.angle = 90)
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Bündnis 90/Grüne(10,0%)", "Die LINKE (10,1%)"),
+clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"),
+labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"),
+clockwise = T)
+2359 / 200 * 100
+issues_ts <- as.ts(issues[,2:44])
+VARselect(issues_ts, lag.max = 5, type = "both")
+vIssues <- VAR(issues_ts, p=5, type="both")
+vIssues <- VAR(issues_ts, p=1, type="both")
+issues_ts <- as.ts(issues)
+VARselect(issues[2:44], lag.max = 8, type = "both")
+summary(ur.df(issues_ts[, 2], type ="none", lags=1))
+VARselect(issues_ts, lag.max = 5, type = "both")
+issues_ts <- as.ts(issues[,2:44])
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+VARselect(issues_ts, lag.max = 5, type = "both")
+summary(ur.df(issues_ts[, 2], type ="none", lags=1))
+ur.df(issues_ts[, 2], type ="none", lags=1)
+head(issues_ts)
+issues_ts$i1.macro
+issues_ts[, "i1.macro"]
+summary(ur.df(issues_ts[, "i1.macro"], type ="none", lags=1))
+ncol(issues_ts)
+for(i in 2:ncol(issues_ts)) {
+summary(ur.df(issues_ts[, i], type ="none", lags=1))
+}
+cat(summary(ur.df(issues_ts[, "i1.macro"], type ="none", lags=1)))
+paste(summary(ur.df(issues_ts[, "i1.macro"], type ="none", lags=1)))
+i
+summary(ur.df(issues_ts[, i], type ="none", lags=1))
+summary(ur.df(issues_ts[, 1], type ="none", lags=1))
+summary(ur.df(issues_ts[, 2], type ="none", lags=1))
+summary(ur.df(issues_ts[, 1], type ="none", lags=1))
+summary(ur.df(issues_ts[, 1], type ="none", lags=1))
+names(issues_ts)
+issues_ts[1,]
+summary(ur.df(issues_ts[, 1], type ="none", lags=1))
+summary(ur.df(issues_ts[, 2], type ="none", lags=1))
+summary(ur.df(issues_ts[, 43], type ="none", lags=1))
+summary(ur.df(issues_ts[, 43], type ="trend", lags=1))
+summary(ur.df(issues_ts[, 43], type ="none", lags=1))
+summary(ur.df(issues_ts[, 1], type ="none", lags=1))
+ur.df(issues_ts[, 1], type ="none", lags=1)
+for(i in 2:ncol(issues_ts)) {
+ur.df(issues_ts[, i], type ="none", lags=1)
+}
+ur.df(issues_ts[, i], type ="none", lags=1)
+test <- ur.df(issues_ts[, i], type ="none", lags=1)
+test
+for(i in 2:ncol(issues_ts)) {
+test <- ur.df(issues_ts[, i], type ="none", lags=1)
+cat(test)
+}
+class(test)
+as.character(test)
+for(i in 2:ncol(issues_ts)) {
+test[i] <- ur.df(issues_ts[, i], type ="none", lags=1)
+}
+ur.df(issues_ts[, 1], type ="none", lags=1)
+ur.df(issues_ts[, sprintf("%s", c(1,2,3))], type ="none", lags=1)
+ur.df(issues_ts[, sprintf("%i", c(1,2,3))], type ="none", lags=1)
+ur.df(issues_ts[, 2], type ="none", lags=1)
+ur.df(issues_ts[, 3], type ="none", lags=1)
+i <- 0
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+i
 issueheads
-length(issueheads)
-issuelist
-length(issuelist)
-length(issuelist[*])
-length(issuelist[[*]])
-length(issuelist[1:43])
-length(issuelist[1)
-length(issuelist[1])
-length(issuelist[2])
-length(issuelist[[1]])
-length(issuelist[[2]])
-length(issuelist[[70]])
-length(issuelist[[43]])
-length(issuelist[[44]])
-length(issuelist[[1:43]])
-length(issuelist[[1-43]])
 length(issuelist[[2]])
-test <- 0
-num <- 0
-for(i in 1:length(issuelist)) {
-j <- length(issuelist[[i]])
-num <- num + j
-rm(j)
+# List all issues in one row
+for(i in 1:length(issueheads)) {
+cat(issueheads[i], "\n")
 }
-num
-drop_s <- which(str_detect(names(issues), "^s"))
-drop_i <- which(str_detect(names(issues), "^i"))
-issues_i <- issues[,-drop_s]
-issues_s <- issues[,-drop_i]
+vIssues <- VAR(issues_ts, p=1, type="both")
+issues_ts[1:20,1]
+issues_ts[,1]
+issues_ts[1,]
+issues_ts[1:21,]
+issues_ts[,1:21]
+issues_ts[1,1:21]
+issues_ts[1,22:43]
+issues_ts[1,22:44]
+issues_ts[1,22:43]
+plot(irf(vIssues, impulse = names(issues_ts[1:21]), response = names(issues_i[22:43])))
 require(stringr)
-drop_s <- which(str_detect(names(issues), "^s"))
-drop_i <- which(str_detect(names(issues), "^i"))
-issues_i <- issues[,-drop_s]
-issues_s <- issues[,-drop_i]
-issues_i$total <- rowSums(issues_i[2:ncol(issues_i)])
-issues_i$entropy <- 0
-for(r in 1:nrow(issues_i)) {
-curtotal <- as.numeric(issues_i$total[r])
-curp <- 0
-for(c in 2:ncol(issues_i)) {
-curcount <- as.numeric(issues_i[r,c])
-curp[c] <- curcount / curtotal
-}
-curp <- curp [2:length(curp)-2]
-curdrop <- which(curp==0)
-curp <- curp[-curdrop]
-issues_i$entropy[r] <- sum(-1 * curp * log(curp))
-}
-issues_s$total <- rowSums(issues_s[2:ncol(issues_s)])
-issues_s$entropy <- 0
-for(r in 1:nrow(issues_s)) {
-curtotal <- as.numeric(issues_s$total[r])
+require(reshape2)
+require(ggplot2)
+require(vars)
+vIssues
+plot(irf(vIssues, impulse = names(issues_ts[1:21]), response = names(issues_i[22:43])))
+plot(irf(vIssues, impulse = names(issues_ts[1:21]), response = names(issues_ts[22:43])))
+issues_s
+names(issues_s)
+names(issues_s[2:23])
+names(issuesi[2:22])
+names(issues_i[2:22])
+plot(irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
+plot(irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
+plot(irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
+irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22]))
+vIRF <- irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22]))
+summary(vIRF)
+vIRF$irf
+vIRF$boot
+vIRF$ortho
+vIRF$Lower
+vIRF$irf[1]
+vIRF$irf["s.boko"]
+summary(issues$hk)
+summary(issues$s.hk)
+summary(issues$s.nsa)
+summary(issues$s.gaza)
+summary(issues$s.boko)
+summary(issues$s.ebola)
+summary(issues$s.edathy)
+summary(issues$s.ferguson)
+summary(issues$s.gurlitt)
+summary(issues$s.is)
+summary(issues$s.pegida)
+summary(issues$s.schumi)
+summary(issues$s.tebartz)
+summary(issues$s.wm)
+summary(issues$s.wulff)
+plot(vIRF)
+names(issues)
+summary(issues[2:44])
+plot(vIRF)
+plot(vIRF, x=300, y=200)
+plot(vIRF, res = 300)
+plot(vIRF[1])
+plot(vIRF$irf[1])
+summary(issues[2:44])
+ur.df(issues_ts[, i], type ="none", lags=1)
+summary(ur.df(issues_ts[, i], type ="none", lags=1))
+summary(ur.df(issues_ts[,30], type ="none", lags=1))
+summary(issues[2])
+stats_entropy
+names(issues)
+issues_bak <- issues
+issues$total <- rowSums(issues[2:ncol(issues)])
+issues$entropy <- 0
+names(issues)
+issues$total <- rowSums(issues[2:ncol(issues)])
+issues$entropy <- 0
+for(r in 1:nrow(issues)) {
+curtotal <- as.numeric(issues$total[r])
 curp <- 0
-for(c in 2:ncol(issues_s)) {
-curcount <- as.numeric(issues_s[r,c])
+for(c in 2:ncol(issues)) {
+curcount <- as.numeric(issues[r,c])
 curp[c] <- curcount / curtotal
 }
 curp <- curp [2:length(curp)-2]
 curdrop <- which(curp==0)
 curp <- curp[-curdrop]
-issues_s$entropy[r] <- sum(-1 * curp * log(curp))
-}
-stats_total <- data.frame(date=drange)
-stats_total$tpd <- 0
-stats_total$ipd <- issues_i$total
-stats_total$spd <- issues_s$total
-# Total number of tweets per day over time
-for(r in 1:length(drange)) {
-stats_total$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"])
+issues$entropy[r] <- sum(-1 * curp * log(curp))
 }
-stats_melt <- melt(stats_total, id="date")
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line()+
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-require(ggplot2)
-stats_melt <- melt(stats_total, id="date")
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line()+
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line()+
-geom_smooth(size=1,formula = y ~ x, method="lm", se=FALSE, color=1)
-g1
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line()+
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-# Visuals for entropy in time series
 stats_entropy <- data.frame(date=drange)
-stats_entropy$entropy <- issues_i$entropy
-stats_entropy <- melt(stats_entropy, id="date")
-require(reshape2)
-stats_melt <- melt(stats_total, id="date")
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line()+
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-stats_entropy <- data.frame(date=drange)
-stats_entropy$entropy <- issues_i$entropy
+stats_entropy$entropy <- issues$entropy
 stats_entropy <- melt(stats_entropy, id="date")
-g1 <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
+g_entrop <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
 geom_line() +
-geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1)
-g1
-g1 <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) +
-geom_line() +
-geom_smooth(size=1,formula = y ~ x, method="lm", se=FALSE, color=1)
-g1
-vIssues <- VAR(issues_ts[,2:44], p=1, type="both")
-require(vars)
-VARselect(issues_ts, lag.max = 8, type = "both")
-vIssues <- VAR(issues_ts[,2:44], p=1, type="both")
-VARselect(issues_ts, lag.max = 16, type = "both")
-VARselect(issues_ts, lag.max = 4, type = "both")
-VARselect(issues_ts, lag.max = 5, type = "both")
-VARselect(issues_ts, lag.max = 6, type = "both")
-VARselect(issues_ts, lag.max = 5, type = "both")
-names(issues_ts)
-issues_ts
-issues_ts[2:44]
-issues_ts <- as.ts(issues[,2:44])
-issues_ts[1:1]
-issues_ts[,1]
-issues_ts[1,1]
-issues_ts2,1]
-issues_ts[2,1]
-issues_ts <- as.ts(issues[,2:44])
-VARselect(issues_ts, lag.max = 5, type = "both")
-VARselect(issues_ts, lag.max = 8, type = "both")
-VARselect(issues_ts, lag.max = 7, type = "both")
-VARselect(issues_ts, lag.max = 5, type = "both")
-vIssues <- VAR(issues_ts[,2:44], p=5, type="both")
-vIssues <- VAR(issues_ts, p=5, type="both")
-plot(irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
-require(stringr)
-require(XML)
-c_errors <- read.csv("issuecomp-codingsample-error.csv", header = F, sep=",", colClasses="character")
-names(c_errors) <- c("str_id", "code", "issue", "tags", "text")
-for(r in 1:nrow(c_errors)) {
-c_errcode <- as.character(c_errors$code[r])
-c_errissue <- as.character(c_errors$issue[r])
-c_errtags <- as.character(c_errors$tags[r])
-c_errtext <- as.character(c_errors$text[r])
-c_errid <- as.character(c_errors$str_id[r])
-cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
-source("issuecomp-codingsample-function2.R")
-}
-for(r in 1:nrow(c_errors)) {
-c_errcode <- as.character(c_errors$code[r])
-c_errissue <- as.character(c_errors$issue[r])
-c_errtags <- as.character(c_errors$tags[r])
-c_errtext <- as.character(c_errors$text[r])
-c_errid <- as.character(c_errors$str_id[r])
-cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
-source("issuecomp-codingsample-function2.R")
-}
-issueheads
-for(i in 1:length(issueheads)) {paste(issueheads[i])}
-for(i in 1:length(issueheads)) {cat(issueheads[i], "\n")}
-for(r in 1:nrow(c_errors)) {
-c_errcode <- as.character(c_errors$code[r])
-c_errissue <- as.character(c_errors$issue[r])
-c_errtags <- as.character(c_errors$tags[r])
-c_errtext <- as.character(c_errors$text[r])
-c_errid <- as.character(c_errors$str_id[r])
-cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
-source("issuecomp-codingsample-function2.R")
-}
-for(r in 1:nrow(c_errors)) {
-c_errcode <- as.character(c_errors$code[r])
-c_errissue <- as.character(c_errors$issue[r])
-c_errtags <- as.character(c_errors$tags[r])
-c_errtext <- as.character(c_errors$text[r])
-c_errid <- as.character(c_errors$str_id[r])
-cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
-source("issuecomp-codingsample-function2.R")
-}
-c_errors <- read.csv("issuecomp-codingsample-error.csv", header = F, sep=",", colClasses="character")
-names(c_errors) <- c("str_id", "code", "issue", "tags", "text")
-for(r in 1:nrow(c_errors)) {
-c_errcode <- as.character(c_errors$code[r])
-c_errissue <- as.character(c_errors$issue[r])
-c_errtags <- as.character(c_errors$tags[r])
-c_errtext <- as.character(c_errors$text[r])
-c_errid <- as.character(c_errors$str_id[r])
-cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
-source("issuecomp-codingsample-function2.R")
-}
-c_tmp <- read.csv("issuecomp-codingsample-error1.csv", header = F, colClasses="character")
-names(c_tmp) <- c("str_id", "all", "wrong", "tagged", "text")
-c_error1 <- c_tmp[, c("wrong", "tagged", "all", "text")]
-c_tmp <- read.csv("issuecomp-codingsample-error2.csv", header = F, colClasses="character")
-names(c_tmp) <- c("str_id", "all", "missing", "tagged", "text")
-c_error2 <- c_tmp[, c("missing", "text", "tagged", "all")]
-View(c_error2)
-summary(ur.df(issues_ts[, 2], type ="none", lags=1))
-require(vars)
-summary(ur.df(issues_ts[, 2], type ="none", lags=1))
-stability(vIssues)
-stability(vIssues[2:])
-stability(vIssues[2:44])
-plot(stability(vIssues))
-class(vIssues)
-summary(vIssues)
-plot(stability(vIssues[2]))
-plot(stability(vIssues), nc=2)
-plot(stability(vIssues), h=0.15)
-stability(vIssues)
-efp(formula = formula, data = data, type = type, h = h, dynamic = dynamic,
-rescale = rescale)
-plot(stability(vIssues), h=0.15)
-plot(stability(vIssues, h=0.15))
-plot(stability(vIssues, h=0.15, rescale = TRUE))
-plot(stability(vIssues, h=0.15, rescale = TRUE), nc=2)
-par("mar")
-par(mar=c(1,1,1,1))
-plot(stability(vIssues, h=0.15, rescale = TRUE), nc=2)
+geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+xlab("Zeitraum") + ylab("Entropie") +
+scale_colour_discrete(name  = "", labels = "Entropie") +
+theme(legend.title = element_text(size=14)) +
+theme(legend.text = element_text(size=12)) +
+theme(axis.title = element_text(size = 14))
+g_entrop
+View(issues)
+summary(issues$entropy)
+summary(issues$total)
+stats_total
+summary(issues[2:44])

.gitignore

@@ -6,3 +6,4 @@ issuecomp-analysis.log
 issuecomp-codingsample-correct.csv
 issuecomp-codingsample-error.csv
 issuecomp-codingsample-error2.csv
+twitter-api-credentials.txt

issuecomp-2-analysis.R

@@ -21,7 +21,7 @@ drange <- date_start + days(0:drange)
 # Import issues and prepare everything
 # Will only be filled after the large categorisation loop
 issues <- data.frame(date = drange)
-issuelist <- readLines("issues-v2.xml")
+issuelist <- readLines("issues-v3.xml")
 issuelist <- str_replace_all(string = issuelist, pattern = ".*<!-- .+ -->", "")
 issuelist <- xmlToList(issuelist)
 issueheads <- names(issuelist)

issuecomp-3-calc.R

@@ -7,7 +7,7 @@ require(vars)
 drop_s <- which(str_detect(names(issues), "^s"))
 drop_i <- which(str_detect(names(issues), "^i"))
 issues_i <- issues[,-drop_s]
-issues_s <- issues[,-drop_i]
+issues <- issues[,-drop_i]
 
 # #
 # ENTROPY
@@ -15,7 +15,6 @@ issues_s <- issues[,-drop_i]
 # Entropy non-sensational issues
 issues_i$total <- rowSums(issues_i[2:ncol(issues_i)])
 issues_i$entropy <- 0
-
 for(r in 1:nrow(issues_i)) {
   curtotal <- as.numeric(issues_i$total[r])
   curp <- 0
@@ -30,71 +29,102 @@ for(r in 1:nrow(issues_i)) {
 }
 
 # Entropy sensational issues
-issues_s$total <- rowSums(issues_s[2:ncol(issues_s)])
-issues_s$entropy <- 0
+issues$total <- rowSums(issues[2:ncol(issues)])
+issues$entropy <- 0
+for(r in 1:nrow(issues)) {
+  curtotal <- as.numeric(issues$total[r])
+  curp <- 0
+  for(c in 2:ncol(issues)) {
+    curcount <- as.numeric(issues[r,c])
+    curp[c] <- curcount / curtotal
+  }
+  curp <- curp [2:length(curp)-2]
+  curdrop <- which(curp==0)
+  curp <- curp[-curdrop]
+  issues$entropy[r] <- sum(-1 * curp * log(curp))
+}
 
-for(r in 1:nrow(issues_s)) {
-  curtotal <- as.numeric(issues_s$total[r])
+# Entropy overall
+issues$total <- rowSums(issues[2:ncol(issues)])
+issues$entropy <- 0
+for(r in 1:nrow(issues)) {
+  curtotal <- as.numeric(issues$total[r])
   curp <- 0
-  for(c in 2:ncol(issues_s)) {
-    curcount <- as.numeric(issues_s[r,c])
+  for(c in 2:ncol(issues)) {
+    curcount <- as.numeric(issues[r,c])
     curp[c] <- curcount / curtotal
   }
   curp <- curp [2:length(curp)-2]
   curdrop <- which(curp==0)
   curp <- curp[-curdrop]
-  issues_s$entropy[r] <- sum(-1 * curp * log(curp))
+  issues$entropy[r] <- sum(-1 * curp * log(curp))
 }
 
 
-# Compare total tweets vs. total issue findings
+
+# Compare total tweets vs. total sensational & total unsensational
 stats_total <- data.frame(date=drange)
 stats_total$tpd <- 0
 stats_total$ipd <- issues_i$total
-stats_total$spd <- issues_s$total
+stats_total$spd <- issues$total
 # Total number of tweets per day over time
 for(r in 1:length(drange)) {
   stats_total$tpd[r] <- length(tweets[tweets[, "created_at"] == drange[r], "id_str"])
 }
 
+# VISUALS: Tweets per day vs. sensational vs. general findings
 stats_melt <- melt(stats_total, id="date")
-g1 <- ggplot(data = stats_melt, aes(x=date,y=value,colour=variable, group=variable)) + 
+g_perday <- 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
+  geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+  xlab("Zeitraum") + ylab("Tweets pro Tag") + 
+  scale_colour_discrete(name  = "Tweets", labels = c("Gesamt", "Allgemein", "Sensation")) + 
+  theme(legend.title = element_text(size=14)) + 
+  theme(legend.text = element_text(size=12)) + 
+  theme(axis.title = element_text(size = 14))
+g_perday
 
 # Visuals for entropy in time series
 stats_entropy <- data.frame(date=drange)
-stats_entropy$entropy <- issues_i$entropy
+stats_entropy$entropy <- issues$entropy
 
 stats_entropy <- melt(stats_entropy, id="date")
 
-g1 <- ggplot(data = stats_entropy, aes(x=date,y=value,colour=variable, group=variable)) + 
+g_entrop <- ggplot(data = stats_entropy, 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
+  geom_smooth(size=1,formula = y ~ x, method="loess", se=FALSE, color=1) +
+  xlab("Zeitraum") + ylab("Entropie") + 
+  scale_colour_discrete(name  = "", labels = "Entropie") + 
+  theme(legend.title = element_text(size=14)) + 
+  theme(legend.text = element_text(size=12)) + 
+  theme(axis.title = element_text(size = 14))
+g_entrop
 
 
 
 # VAR ---------------------------------------------------------------------
 
 # test <- VAR(issues[,2:32], p=1, type=c("const", "trend", "both", "none"), season=NULL, exogen = NULL, lag.max = NULL, ic = c("AIC", "HQ", "SC", "FPE"))
-# test <- VAR(issues_i[,2:22], p=1, type="none", exogen = issues_s[,2:3])
-# test <- VAR(issues_s[,2:11], p=1, type="none")
-# VAR(issues_s[,2:23], p=1, type=c("const", "trend", "both", "none"), season=NULL, exogen = issues_i[2:22])
+# test <- VAR(issues_i[,2:22], p=1, type="none", exogen = issues[,2:3])
+# test <- VAR(issues[,2:11], p=1, type="none")
+# VAR(issues[,2:23], p=1, type=c("const", "trend", "both", "none"), season=NULL, exogen = issues_i[2:22])
 
 issues_ts <- as.ts(issues[,2:44])
+
+# Tests
 VARselect(issues_ts, lag.max = 5, type = "both")
-vIssues <- VAR(issues_ts, p=5, type="both")
+i <- 0
+i <- i + 1
+ur.df(issues_ts[, i], type ="none", lags=1)
+summary(issues[2:44])
 
-plot(irf(vIssues, impulse = names(issues_s[2:23]), response = names(issues_i[2:22])))
 
-capture.output(print(summary(test), prmsd=TRUE, digits=1), file="out.txt")
+# VAR and IRF
+vIssues <- VAR(issues_ts, p=1, type="both")
+vIRF <- irf(vIssues, impulse = names(issues[2:23]), response = names(issues_i[2:22]))
+plot(vIRF)
 
-# Tests
-issues_ts <- as.ts(issues)
-VARselect(issues[2:44], lag.max = 8, type = "both")
-summary(ur.df(issues_ts[, 2], type ="none", lags=1))
+# capture.output(print(summary(test), prmsd=TRUE, digits=1), file="out.txt")
 
 # SOME TESTS --------------------------------------------------------------
 
@@ -116,16 +146,18 @@ rm(g1, r)
 
 
 # Show party percentage of twitter users
-acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene"))
-acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats
+acc_parties <- data.frame(party = c("cducsu", "spd", "gruene", "linke"))
+acc_parties$btw13 <- c(49.3, 30.6, 10.0, 10.1) # seats of party / 631 seats
 acc_parties$twitter <- 0
 for(p in 1:nrow(acc_parties)) {
   acc_parties$twitter[p] <- round(nrow(acc_df[acc_df$party == as.character(acc_parties$party[p]), ]) / 280 * 100)
 }
-pie(acc_parties$btw13, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T,
-    main = "Seats of parties in the parliament")
-pie(acc_parties$twitter, col=c("black", "red", "purple", "green"), labels = c("CDU/CSU", "SPD", "Die LINKE", "Bündnis 90/Grüne"), clockwise = T,
-    main = "Percentage of parties' MdBs of all Twitter accounts")
+pie(acc_parties$btw13, col=c("black", "red", "green", "purple"), 
+    labels = c("CDU/CSU (49,3%)", "SPD (30,6%)", "Bündnis 90/Grüne(10,0%)", "Die LINKE (10,1%)"), 
+    clockwise = T)
+pie(acc_parties$twitter, col=c("black", "red", "green", "purple"), 
+    labels = c("CDU/CSU (36%)", "SPD (30%)", "Bündnis 90/Grüne(19%)", "Die LINKE (15%)"), 
+    clockwise = T)
 
 rm(acc_parties, p)
 
@@ -152,6 +184,11 @@ ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_sm
 
 # POSSIBLY USEFUL CODE ----------------------------------------------------
 
+# List all issues in one row
+for(i in 1:length(issueheads)) {
+  cat(issueheads[i], "\n")
+}
+
 # Limits of list
 length(issuelist)
 length(issuelist[[2]])

twitter-api-credentials.txt

@@ -1,5 +0,0 @@
-# 1. line: consumer key, 2. consumer secret, 3. oauth token, 4. oauth secret
-c9Ob2fWNSONMC0mA2JlNaeRke
-cZ3Il2hmbLgK0Lc57mj5kUvymjVdsmZKYwKOGHR3NhCpvWgEOI
-1007025684-RFxCDFc4OPkt02bASmdci00TB4jgaPjfqxLRT58
-rvfv8MgexFKTqrPNSoGrdrZVNhV4fTJb2Bgz249nbvKNg

twitter-api-credentials.txt.sample

@@ -0,0 +1,5 @@
+# 1. line: consumer key, 2. consumer secret, 3. oauth token, 4. oauth secret
+xxxxxxxxxxxxxxxxxxxx
+xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+xxxxxxxxxxxxxxxxxxxxxxxxxxxxx

ur.df-testvalues.txt

@@ -0,0 +1,22 @@
+i1.macro  & -5,869 & s.nsa  & -7,3292 \\
+i2.civil  & -4,4172 & s.is  & -7,762 \\
+i3.health  & -9,5973 & s.ebola  & -6,1723 \\
+i4.agrar  & -8,5183 & s.edathy  & -7,0335 \\
+i5.labor  & -7,523 & s.ukraine  & -5,6195 \\
+i6.edu  & -6,4374 & s.hk  & -6,7599 \\
+i7.env  & -7,1426 & s.mh17  & -6,1481 \\
+i8.energy  & -7,3613 & s.gaza  & -5,3861 \\
+i10.trans  & -5,6718 & s.ferguson  & -8,8098 \\
+i12.law  & -5,9882 & s.boko  & -10,4431 \\
+i13.social  & -6,7765 & s.pegida  & -6,3831 \\
+i14.house  & -8,9577 & s.schumi  & -12,4947 \\
+i15.finance  & -5,9094 & s.mh370  & -7,8991 \\
+i16.defense  & -6,9535 & s.esc  & -11,6332 \\
+i17.science  & -5,9651 & s.wulff  & -12,4189 \\
+i18.trade  & -7,6121 & s.tebartz  & -12,6301 \\
+i19.ib  & -3,8057 & s.gurlitt  & -10,7665 \\
+i20.pubadmin  & -6,7123 & s.hoen  & -9,3721 \\
+i21.publand  & -9,9521 & s.pistorius  & -13,435 \\
+i24.stateadm  & -13,435 & s.philae  & -12,7024 \\
+i25.reuni  & -5,2011 & s.wm  & -8,7283 \\
+ &  & s.sotschi  & -8,2339 \\