added coding sample tests

issuecomp-analysis.R

@@ -6,6 +6,8 @@ require(stringr)
 
 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")
@@ -23,6 +25,8 @@ 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
@@ -36,8 +40,7 @@ for(d in 1:nrow(issues)) {
     # 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!)
@@ -61,8 +64,16 @@ for(d in 1:nrow(issues)) {
         # 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) {
-          #cat("Matched", curtag, "with", curtext,"\n")
+          # 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
         }
@@ -75,11 +86,19 @@ for(d in 1:nrow(issues)) {
   } # /for tweets_curday
 } # /for drange
 
+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)
 
 
+# SAVING ------------------------------------------------------------------
+
+
+row.names(tweets) <- NULL
+write.csv(tweets, "tweets.csv")
+save(tweets, file="tweets.RData")
 
 # 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)