From 771145faf7c36820401cbbcdd37687d9c1cf3af6 Mon Sep 17 00:00:00 2001 From: Your Name Date: Sun, 19 Jul 2020 19:08:16 +0200 Subject: [PATCH] actor_merger: added mult='first' to metadata join for parties_actors to deal with duplicate partyIds (see 50Plus, Conservatives and Labour) --- R/actor_merger.R | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/R/actor_merger.R b/R/actor_merger.R index 46722e9..dbe679f 100644 --- a/R/actor_merger.R +++ b/R/actor_merger.R @@ -160,7 +160,7 @@ actor_merger <- function(df, actors_meta, actor_groups = NULL) { actor.first = first(sentence_id), actor.occ = .N ), by = c('id','ids')] - parties_actors <- actors_meta[parties_actors, on = c('ids')][!is.na(id),.(ids = str_c(ids,"_mfsa"), (.SD)), .SDcols = -c('ids')] + parties_actors <- actors_meta[parties_actors, on = c('ids'), mult = 'first'][!is.na(id),.(ids = str_c(ids,"_mfsa"), (.SD)), .SDcols = -c('ids')] ## Generate party aggregations (mfs) parties <- df[str_ends(ids,'_f') | str_ends(ids,'_s'),.(