modbot.preprocessing.separate_tocheck

modbot.preprocessing.separate_tocheck(config, infile, bounds, wc)[source]

Separate to_check from all other messages

Parameters
  • config (ProcessingConfig) – Class storing preprocessing configuration parameters

  • infile (str) – Input file path

  • bounds (list) – List with starting and ending message index to check

  • wc (WholesomeCheck) – WholesomeCheck class to use for probability predictions

Returns

  • to_check (list) – List of messages to check

  • y_check (list) – List of corresponding to check classifications

  • texts (list) – List of final messages

  • y (list) – List of correposponding final classifications