dfm_gen: remove multicore, update merger() code
elasticizer: changed filenaming scheme for dump option
merger: Fixed bug where an NA lemma would cause the entire document to become NA. Now the NA lemmas are filtered out before merging
ud_update: removed parallel processing, changed script to save bulk updates in .Rds files instead of sending them straight away
cv_generator: generate folds for nested cv
dfm_gen: added optional lowercasing parameter
estimator: estimate model and performance based on parameters
feat_select: select features based on textstat_keyness
metric_gen: convert output from estimator to model performance metrics
modelizer: updated for new pipeline
modelizer_old: old model pipeline
out_parser: now correctly exported
dfm_gen: added old junk codes for recoding, and removed deprecated ngrams parameter from dfm function
class_update: removed dfm_words parameter, which is replaced by the force = T parameter in predict(), training/model idf is now applied to unseen data
DESCRIPTION: added quanteda.textmodels as new dependency, since these have been separated from base quanteda 2.0.0 onwards
merger: Added custom clean option (sometimes not cleaning is preferred, even with lemmas)
merger, out_parser: Updated regex for filtering out non-words to also include email addresses (containing both @ and .)
out_parser: function to parse raw text output into a single field, either from _source or highlight fields
dupe_detect: updated function to use 'ver' parameter for versioning
Erik de Vries
Your Name