KevinMidboe/linguist
1
0
Fork 0
mirror of https://github.com/KevinMidboe/linguist.git synced 2025-10-29 17:50:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor docs/naming

Browse Source
This commit is contained in:
Ted Nyman
2013-11-15 18:42:53 -08:00
parent 791d9eed41
commit 4f656c200b
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
lib/linguist/classifier.rb
View File

@@ -15,8 +15,8 @@ module Linguist
# #
# Returns nothing. # Returns nothing.
# #
# Set LINGUIST_DEBUG=1 or =2 to see probabilities per-token, # Set LINGUIST_DEBUG=1 or =2 to see probabilities per-token or
# per-language. See also dump_all_tokens, below. # per-language. See also #dump_all_tokens, below.
def self.train!(db, language, data) def self.train!(db, language, data)
tokens = Tokenizer.tokenize(data) tokens = Tokenizer.tokenize(data)
@@ -151,10 +151,10 @@ module Linguist
printf "%#{maxlen}s", "" printf "%#{maxlen}s", ""
puts " #" + languages.map { |lang| sprintf("%10s", lang) }.join puts " #" + languages.map { |lang| sprintf("%10s", lang) }.join
tokmap = Hash.new(0) token_map = Hash.new(0)
tokens.each { |tok| tokmap[tok] += 1 } tokens.each { |tok| token_map[tok] += 1 }
tokmap.sort.each { |tok, count| token_map.sort.each { |tok, count|
arr = languages.map { |lang| [lang, token_probability(tok, lang)] } arr = languages.map { |lang| [lang, token_probability(tok, lang)] }
min = arr.map { |a,b| b }.min min = arr.map { |a,b| b }.min
minlog = Math.log(min) minlog = Math.log(min)