You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Erik de Vries 16d02a055d sent_merger: Updated sentiment aggregation procedure. Now a dedicated actors_final.csv file is used as source of partyIds for individual actors, instead of the (deprecated) [partyId]_a ids that were previously provided as a result of the actor searches, or the (also deprecated) actor metadata provided in the ES actors database.		3 years ago
..
actorizer.R	actorizer: updated to account for token start offset in udpipe output. Sometimes, the first token in an article doesn't start at character position 1 (or 2 if the article starts with a whitespace), but at position 16 and possibly other positions.	4 years ago
bulk_writer.R	actorizer: add pre_tags and post_tags to argument list	6 years ago
class_update.R	removed multicore support, added parameters for dfm_gen	4 years ago
cv_generator.R	dupe_detect: Changed query from json to query_string style, and added filter for already detected duplicates	5 years ago
dfm_gen.R	removed multicore support, added parameters for dfm_gen	4 years ago
dupe_detect.R	dupe_detect: fix for quotation marks	5 years ago
elastic_update.R	elastic_update: added more debug output	4 years ago
elasticizer.R	elasticizer: update rbindlist implementation	4 years ago
estimator.R	removed multicore support, added parameters for dfm_gen	4 years ago
feat_select.R	revised modeling pipeline:	5 years ago
lemma_writer.R	remove meta_file argument	4 years ago
merger.R	merger: selecting only relevant columns	5 years ago
metric_gen.R	revised modeling pipeline:	5 years ago
modelizer.R	removed multicore support, added parameters for dfm_gen	4 years ago
modelizer_old.R	revised modeling pipeline:	5 years ago
out_parser.R	lemma_writer: updated to write metadata csv when dumping documents in ud format	4 years ago
preproc.R	estimator, modelizer, preproc: Removed experimental we-vector support, and disabled inefficiently implemented preproc.R	4 years ago
query_gen_actors.R	query_gen_actors: removed country argument, now reading country directly from actor data	4 years ago
query_string.R	dfm_gen: removed exceptions for NO summer codes	6 years ago
sent_merger.R	sent_merger: Updated sentiment aggregation procedure. Now a dedicated actors_final.csv file is used as source of partyIds for individual actors, instead of the (deprecated) [partyId]_a ids that were previously provided as a result of the actor searches, or the (also deprecated) actor metadata provided in the ES actors database.	3 years ago
sentencizer.R	removed sent_sum_pos/neg	4 years ago
ud_update.R	actorizer: totally revamped way of finding actors	5 years ago