christian/hateimparlament
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

improve applause party parsing

Browse Source
This commit is contained in:
christian
2021-07-01 13:23:29 +02:00
parent f09cbac172
commit 2abb3467e8
2 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
R/helpers.R
+1
View File
@@ -1,4 +1,5 @@
`%$%` <- function(f, x) f(x) `%$%` <- function(f, x) f(x)
`%.%` <- function(f, g) function(...) f(g(...)) `%.%` <- function(f, g) function(...) f(g(...))
flip <- function(f) function(x, y) f(y, x)
clear_na <- function(xs) xs[!is.na(xs)] clear_na <- function(xs) xs[!is.na(xs)]
R/parse.R
+3 -1
View File
@@ -137,12 +137,14 @@ parse_rede <- function(rede_xml) {
comments = comments) comments = comments)
} }
fraktionspattern <- "BÜNDNIS 90/DIE GRÜNEN|CDU/CSU|AfD|SPD|DIE LINKE|FDP" fraktionspattern <- "BÜNDNIS(SES)?\\W*90/DIE\\W*GRÜNEN|CDU/CSU|AfD|SPD|DIE LINKE|FDP|LINKEN"
fraktionsnames <- c("BÜNDNIS 90/DIE GRÜNEN", "CDU/CSU", "AfD", "SPD", "DIE LINKE", "FDP")
parse_comment <- function(comment, rede_id, on_redner) { parse_comment <- function(comment, rede_id, on_redner) {
base <- c(rede_id = rede_id, on_redner = on_redner) base <- c(rede_id = rede_id, on_redner = on_redner)
str_extract_all(comment, fraktionspattern) %>% str_extract_all(comment, fraktionspattern) %>%
`[[`(1) %>% `[[`(1) %>%
sapply(partial(flip(head), 1) %.% agrep, x=fraktionsnames, max=0.2, value=T) %>%
str_c(collapse=",") -> str_c(collapse=",") ->
by by
# classify comment # classify comment