added coding sample tests
This commit is contained in:
@@ -176,19 +176,22 @@ tweets <- tweets[order(tweets$created_at), ]
|
||||
|
||||
# Finally delete every tweet not from 2014 (2013 or 2015)
|
||||
delrow <- NULL
|
||||
pb <- txtProgressBar(min = 0, max = nrow(tweets), style = 3)
|
||||
for(r in 1:nrow(tweets)) {
|
||||
if(format(tweets$created_at[r], "%Y") != "2014") {
|
||||
delrow <- c(delrow, r)
|
||||
}
|
||||
setTxtProgressBar(pb, r)
|
||||
curtext <- as.character(tweets$text[r])
|
||||
curtext <- str_replace_all(curtext, "$", " ")
|
||||
curtext <- str_replace_all(curtext, "http://.+?\\s", "URL ")
|
||||
tweets$text[r] <- curtext
|
||||
}
|
||||
tweets <- tweets[-delrow, ]
|
||||
rm(delrow, r)
|
||||
|
||||
|
||||
# Convert dates to omit (unnecessary) time
|
||||
tweets$created_at <- format(tweets$created_at, "%Y-%m-%d")
|
||||
|
||||
save(tweets, file="tweets.RData")
|
||||
save(tweets, file="tweets_untagged.RData")
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user