View source: R/bt_estimate_news_leads.R
bt_estimate_news_leads | R Documentation |
Generates predictions for relevance using the most recent Mrs Hudson model.
bt_estimate_news_leads(
leads.core.news,
keep.results.ratio = 1,
binary.prediction = T,
return.both = F,
conf.cutoff = 0.5
)
leads.core.news |
A dataframe of leads in the standard format. Requires acting.agency, act.title.en, act.description.en |
keep.results.ratio |
what fraction of the results you want to keep. 1 = keep all, 0 = discard all. the ones with lowest relevance prob will be discarded. If set to 1, the conf.cutoff value will be used to determine the binary.prediction. |
binary.prediction |
return results as a binary prediction or as their raw 0 ~ 1 confidence values. |
return.both |
return both binary and raw.score in a list. |
conf.cutoff |
threshold score for a doc to qualify as 'relevant', lower tends to mean more recall and less precision |
A vector of Mrs. Hudson's predictions.
www.globaltradealert.org
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.