You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

97 lines
2.9 KiB

require(stringr)
require(XML)
# FUNCTIONS ---------------------------------------------------------------
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)
}
# SAMPLE OUT/INPUT --------------------------------------------------------
# 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$X <- NULL
# Read all issues from XML file
c_issues <- data.frame(date = drange)
c_issuelist <- xmlToList("issues-v2.xml")
c_issueheads <- names(issuelist)
c_issues[issueheads] <- 0
# Run through as many tweets as wished to mark them as correct or incorrect
source("issuecomp-codingsample-function.R")
rm(c_err, c_result, c_samid, c_samno,c_samtags,c_samissue,c_samtext,c_yn)
# Now go through tweets/tags marked as false
# Exit codes:
# 0 = Correct tagging
# 1 = At least one tag was incorrect
# 2 = At least one tag was missing
# 3 = Both 1 and 2
c_errors <- read.csv("issuecomp-codingsample-error.csv", header = F, sep=",", colClasses="character")
names(c_errors) <- c("str_id", "code", "issue", "tags", "text")
for(r in 1:nrow(c_errors)) {
c_errcode <- as.character(c_errors$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")
}
# 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