Created
February 9, 2016 10:28
-
-
Save ayemos/3c453d2bc90b23be673b to your computer and use it in GitHub Desktop.
Count hinshi-s
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Usage: ruby analyze.rb CSV_FILE | |
require 'csv' | |
require 'awesome_print' | |
VERB_KEYS = [/[^助感]動詞/, /^動詞/] | |
AUX_VERB_KEYS = [/助動詞/] | |
CONJUNCTION_KEYS = [/接続詞/] | |
NOUN_KEYS = [/名詞/] | |
ADJECTIVAL_VERB_KEYS = [/形容動詞/, /形状詞/] | |
ADJECTIVE_KEYS = [/形容詞/] | |
SYMBOL_KEYS = [/記号/] | |
INTERJECTION_KEYS = [/感動詞/] | |
PARTICLE_KEYS = [/助詞/] | |
PREFIX_KEYS = [/接頭辞/] | |
SUFFIX_KEYS = [/接尾辞/] | |
ADVERB = [/副詞/] | |
ANY = [/.*/] | |
ALL = [VERB_KEYS, AUX_VERB_KEYS, CONJUNCTION_KEYS, NOUN_KEYS, ADJECTIVAL_VERB_KEYS, ADJECTIVE_KEYS, | |
SYMBOL_KEYS, INTERJECTION_KEYS, PARTICLE_KEYS, ADVERB, PREFIX_KEYS, SUFFIX_KEYS, ANY] | |
words = 0 | |
count = {} | |
CSV.foreach(ARGV[0]) do |row| | |
_, _, _, _, _, hinshi, *_ = row | |
next if hinshi.nil? | |
words += 1 | |
ALL.each do |keys| | |
if keys.any?{|key| hinshi =~ key} | |
unless count.has_key?(keys[0].to_s) | |
count[keys[0].to_s] = Hash.new(0) | |
end | |
count[keys[0].to_s][hinshi] += 1 | |
end | |
end | |
end | |
c = 0 | |
sum = 0 | |
count.each do |k, v| | |
puts "#{k.gsub(/\(\?-mix:|\)/,'')}: #{v.inject(0) {|sum, hash| sum + hash[1]}}" | |
if c > 0 | |
sum += v.inject(0) {|sum, hash| sum + hash[1]} | |
end | |
c += 1 | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment