You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
misc/shell_scripts/logs_own_vocabulary

18 lines
748 B

#! /usr/bin/env bash
# see related ideas
# http://fabien.benetou.fr/innovativ.it/www/HistoricalArchives/Seedea/Oimp/Ubiquitousvocabulary
# http://fabien.benetou.fr/Cookbook/Cognition#LearningNewLanguage
# and most_used_commands
LOGS=web/thelab/stigmergylive/logs/ChannelLogger/freenode/#*/*
cat $LOGS | grep "<Utopiah" | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq
# cleaning by removing low frequency words
# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | grep -v " 1" | grep -v " 2" | grep -v " 3" | wc -l
# 10 most commonly used words
# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | sort -n | tail -15