stijgers

r/test-count.R

@@ -0,0 +1,28 @@
+nw <- read.table('data/2026/algemeen-count-per-2026.23-1', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word"))
+od <- read.table('data/2026/algemeen-count-per-2026.22-4', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word"))
+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)

r/test-rang.R

@@ -0,0 +1,32 @@
+nw <- read.table('data/2026/algemeen-rang-per-2026.23-1', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word"))
+od <- read.table('data/2026/algemeen-rang-per-2026.22-4', sep="\t", quote="", encoding="utf-8", col.names=c("f", "word"))
+words <- unique(c(od$word, nw$word))
+o <- order(words)
+words <- words[o]
+n <- length(words)
+d <- data.frame(word=words, od=rep(NA, n), nw=rep(NA, 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]
+}
+
+d$nw[is.na(d$nw)] <- max(nw$f) + 2
+d$od[is.na(d$od)] <- max(od$f) + 2
+
+myplot <- function(values, labels, titel="", sub ="") {
+    y <- 1:length(values)
+    xx <- range(values)
+    plot(values, y, xlim=c(xx[1], xx[2] + (xx[2]-xx[1]) / 5), xlab="score", ylab="index", main=titel, sub=sub)
+    text(values, y, labels, pos=4)
+}
+
+nwn <- (d$nw - 1) / (max(nw$f) + 1)
+odn <- (d$od - 1) / (max(od$f) + 1)
+
+v <- odn - nwn
+o <- order(-v)
+myplot(v[o][1:40], words[o][1:40], titel="score op basis van genormaliseerde rang", "week 23 t.o.v. week 19 t/m 22")
+