Corrent status

issuecomp-codingsample.R

@@ -34,6 +34,13 @@ checkAllIssues <- function(string, issuelist) {
 
 # Read CSV of all tweets (with tags, if available)
 c_tweets <- read.csv("tweets.csv", colClasses="character")
+# Replace quotes because it may cause problems when saving and reading as CSV files
+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, "\"", "")
+  }
+}
 c_tweets$X <- NULL
 
 # Read all issues from XML file
@@ -66,10 +73,24 @@ for(r in 1:nrow(c_errors)) {
   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_errtags, "\n", sep="")
+  cat("===============\n\n[TWEET]: ",c_errtext,"\n[ISSUES]: ", c_errissue, " (", c_errtags, ")\n", sep="")
   source("issuecomp-codingsample-function2.R")
 }
 
 
+# Now import the error files in a human readable data frame to improve the issue database
 
+# All tweets with WRONG ISSUES
+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")]
 
+# All tweets with MISSING ISSUES
+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")]
+
+# All CORRECT tweets
+c_tmp <- read.csv("issuecomp-codingsample-correct.csv", header = F, colClasses="character")
+names(c_tmp) <- c("str_id", "status", "issue", "tags", "text")
+c_correct <- c_tmp