| #!/usr/bin/env bash | |
| # | |
| # Backup home directory | |
| # | |
| # | |
| set -o errexit | |
| set -o nounset | |
| set -o pipefail |
| /* eslint-disable no-undef */ | |
| ;(function (window, document) { | |
| "use strict" | |
| /** | |
| * The Nord Documentation object | |
| * | |
| * @constructor | |
| */ | |
| function NordDocs() { |
This is a quick example showing how to use regexes to find tri-grams in Shakespeare...well, 570,872 of them, anyway, if we do some basic filtering of non-dialogue.
Though tokenization and n-grams should typically be done using a proper natural language processing framework, it's possible to do in a jiffy from the command-line, using standard Unix tools and ack, the better-than-grep utility.
| /** | |
| * | |
| * Search Query Mining Tool | |
| * | |
| * This script calculates the contribution of each word or phrase found in the | |
| * search query report and outputs a report into a Google Doc spreadsheet. | |
| * | |
| * Version: 2.2 | |
| * Updated 2015-09-17: replacing 'KeywordText' with 'Criteria' | |
| * Updated 2016-10-11: replacing 'ConvertedClicks' with 'Conversions' |