splitting files, adding entropy test

issuecomp-2-analysis.R

@@ -55,7 +55,7 @@ foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
   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)
+    #     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, "#", "")
@@ -67,7 +67,7 @@ foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
       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]
@@ -93,7 +93,7 @@ foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
         } 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
@@ -104,19 +104,19 @@ foreach(d = 1:nrow(issues), .packages = c("stringr"), .combine=rbind) %dopar% {
         curtag <- curtag[1]
         
         if(tags_found == TRUE) {
-#           # Raise number of findings on this day for this issue by 1
+          #           # Raise number of findings on this day for this issue by 1
-#           issues[d,curissue] <- issues[d,curissue] + 1
+          #           issues[d,curissue] <- issues[d,curissue] + 1
-#           
+          #           
-#           # Add issue and first matched tag of tweet to tweets-DF
+          #           # Add issue and first matched tag of tweet to tweets-DF
-#           oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
+          #           oldissue <- tweets[tweets[, "id_str"] == curid, "issue"]
-#           tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
+          #           tweets[tweets[, "id_str"] == curid, "issue"] <- str_c(oldissue, curissue, ";")
-#           oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
+          #           oldtag <- tweets[tweets[, "id_str"] == curid, "tags"]
-#           tweets[tweets[, "id_str"] == curid, "tags"] <- str_c(oldtag, curtag, ";")
+          #           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)
+          #           cat(paste("Match!\n"), file="issuecomp-analysis.log", append=TRUE)
-#           data.frame(date=curdate, issue=curissue)
+          #           data.frame(date=curdate, issue=curissue)
           break   # next issue, no more tags from same issue
         }
         else {
@@ -182,60 +182,6 @@ for(r in 1:nrow(results)) {
 # SAVING ------------------------------------------------------------------
 
 save(tweets, file="tweets_tagged.RData")
+save(issues, file="issues.RData")
 
 
-
-# SOME TESTS --------------------------------------------------------------
-
-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"])
-}
-
-stats_melt <- melt(stats, 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
-
-rm(g1, r)
-
-
-# Show party percentage of twitter users
-acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene"))
-acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats
-acc_parties$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")
-
-rm(acc_parties, p)
-
-
-# VISUALS -----------------------------------------------------------------
-
-
-# Level: days
-issues_melt <- melt(issues,id="date")
-ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_line(size=1)
-ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_smooth(size=1,method="loess",formula = y ~ x, se=FALSE)
-
-
-
-# POSSIBLY USEFUL CODE ----------------------------------------------------
-
-# Limits of list
-length(issuelist)
-length(issuelist[[2]])
-
-# Select all tweets from current day in drange
-tweets_curday <- tweets[tweets[, "created_at"] == drange[5], ]
-# Is column a issue counting column?
-str_detect(names(issues[2]), "^issue")

issuecomp-3-calc.R

@@ -0,0 +1,130 @@
+require(stringr)
+require(reshape2)
+require(ggplot2)
+require(vars)
+
+# Create dataframes with only non-sensational (i) and sensational (s) issue columns
+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]
+
+# #
+# ENTROPY
+# #
+# 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$total[r])
+  curp <- 0
+  for(c in 2:ncol(issues_i)) {
+    curcount <- as.numeric(issues_i[r,c])
+    curp[c] <- curcount / curtotal
+  }
+  curp <- curp [2:length(curp)-2]
+  curdrop <- which(curp==0)
+  curp <- curp[-curdrop]
+  issues_i$entropy[r] <- sum(-1 * curp * log(curp))
+}
+
+# Entropy sensational issues
+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))
+}
+
+
+# Compare total tweets vs. total issue findings
+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"])
+}
+
+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
+
+# 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")
+
+g1 <- 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
+
+# SOME TESTS --------------------------------------------------------------
+
+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"])
+}
+
+stats_melt <- melt(stats, 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
+
+rm(g1, r)
+
+
+# Show party percentage of twitter users
+acc_parties <- data.frame(party = c("cducsu", "spd", "linke", "gruene"))
+acc_parties$btw13 <- c(49.3, 30.6, 10.1, 10.0) # seats of party / 631 seats
+acc_parties$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")
+
+rm(acc_parties, p)
+
+
+# VISUALS -----------------------------------------------------------------
+
+
+# Level: days
+issues_melt <- melt(issues,id="date")
+ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_line(size=1)
+ggplot(issues_melt,aes(x=date,y=value,colour=variable,group=variable)) + geom_smooth(size=1,method="loess",formula = y ~ x, se=FALSE)
+
+
+
+# POSSIBLY USEFUL CODE ----------------------------------------------------
+
+# Limits of list
+length(issuelist)
+length(issuelist[[2]])
+
+# Select all tweets from current day in drange
+tweets_curday <- tweets[tweets[, "created_at"] == drange[5], ]
+# Is column a issue counting column?
+str_detect(names(issues[2]), "^issue")