align
.InitialCleanup¶
-
align.
InitialCleanup
(dataframe, minwords=2, use_filler_list=None, filler_regex_and_list=False)¶ Perform basic text cleaning to prepare dataframe for analysis. Remove non-letter/-space characters, empty turns, turns below a minimum length, and fillers.
By default, preserves turns 2 words or longer. If desired, this may be changed by updating the minwords argument.
By default, remove common fillers through regex. If desired, remove other words by passing a list of literal strings to use_filler_list argument, and if both regex and list of additional literal strings are to be used, update filler_regex_and_list=True.