org.candelbio.multitool.nlp — org.candelbio/multitool 0.1.0

bigrams clj/s

(bigrams tokens)

levenshtein clj/s

(levenshtein str1 str2)

overexpressed clj/s

(overexpressed freq base-freq)

remove-numbers clj/s

(remove-numbers tokenized)

remove-ruthlessly clj/s

(remove-ruthlessly tokenized)

remove-shorts clj/s

(remove-shorts tokenized)

remove-stops clj/s

(remove-stops tokenized stops)

stops clj/s

tokens clj/s

(tokens s)