34 lines
933 B
R
34 lines
933 B
R
nw <- read.table('data/2026/algemeen-allewoorden-2026.23-1', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word", "tags"))
|
|
od <- read.table('data/2026/algemeen-allewoorden-2026.22-4', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word", "tags"))
|
|
words <- unique(c(od$word, nw$word))
|
|
o <- order(words)
|
|
words <- words[o]
|
|
n <- length(words)
|
|
d <- data.frame(word=words, od=rep(0, n), nw=rep(0, n))
|
|
|
|
for (word in nw$word) {
|
|
d$nw[d$word==word] <- nw$f[nw$word==word]
|
|
}
|
|
for (word in od$word) {
|
|
d$od[d$word==word] <- od$f[od$word==word]
|
|
}
|
|
|
|
write.table(d, file="tmp.csv", quote=FALSE, sep="\t", row.names=FALSE, fileEncoding="utf-8")
|
|
|
|
####
|
|
|
|
oud <- d$od
|
|
nieuw <- d$nw
|
|
|
|
oud[oud == 0] <- 0.5
|
|
nieuw[nieuw == 0] <- 0.5
|
|
|
|
plot(log(oud), log(nieuw))
|
|
lines(log(range(oud)), log(range(nieuw)))
|
|
identify(log(oud), log(nieuw), labels=words)
|
|
|
|
|
|
#plot(oud, nieuw)
|
|
#lines(range(oud), range(nieuw))
|
|
#identify(oud, nieuw, labels=words)
|