p209327/nlnieuws
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Peter Kleiweg
2026-06-30 23:58:14 +02:00
parent ce8ed07327
commit 73c21b4f8f
3 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md → README.admin.md
View File

@@ -12,7 +12,7 @@ query.sh
## 1. Verzamelen van berichten
Berichten van NieuwsNL in `NieuwsNL/yyyy/mm/dd/`
Berichten van NieuwsNL in `NieuwsNL/yyyy/mm/dd/` TODO
Overigen in `[A-Z]*/yyyy/ww/` (weeknummer)

1
README.user.md Normal file
View File

@@ -0,0 +1 @@
TODO

9
r/test-count.R
View File

@@ -1,5 +1,5 @@
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"))
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]
@@ -26,3 +26,8 @@ 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)