parallel works, now output in data frame

issuecomp-analysis.R

@@ -3,6 +3,8 @@ require(XML)
 require(ggplot2)
 require(reshape2)
 require(stringr)
+library(foreach)
+library(doParallel)
 
 source("issuecomp-functions.R")
 
@@ -34,22 +36,21 @@ tweets$tags <- ""
 tagexpand <- c("", "s", "n", "en", "er")
 
 # Parallelisation
-writeLines(c(""), "log.txt")  
+writeLines(c(""), "issuecomp-analysis.log")  
 cl<-makeCluster(3)
 registerDoParallel(cl)
 
-df<-foreach(d = 1:nrow(issues) %dopar% {
+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]
-  sink("log.txt", append=TRUE)  
-  cat(as.character(curdate),"\n")
+  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("Starting tweet", t, "of",as.character(curdate),"\n")
+    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, "#", "")
@@ -122,7 +123,7 @@ df<-foreach(d = 1:nrow(issues) %dopar% {
 } # /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)
 
 # SAVING ------------------------------------------------------------------