Last active
December 19, 2015 21:39
-
-
Save isdyy/6022027 to your computer and use it in GitHub Desktop.
ngram実験
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
| # -*- coding: utf-8 -*- | |
| def ngram_word_split(u): | |
| return u.split() | |
| def ngram_split(u, n): | |
| length = len(u) | |
| pos = 0 | |
| res = [] | |
| while pos < length: | |
| ngram = u[pos:pos+n] | |
| if len(ngram.strip()) > 1: | |
| res.append(ngram) | |
| pos += 1 | |
| return res | |
| def ngram_print(u): | |
| for w in ngram_word_split(u): | |
| l = len(w) | |
| n = 2 | |
| while n <= l: | |
| for s in ngram_split(w, n): | |
| print s | |
| n += 1 | |
| ngram_print(u'やまざき まさよし') | |
| print '--' | |
| ngram_print(u'たかはし ゆきひろ') | |
| print '--' | |
| ngram_print(u'') | |
| print '--' | |
| ngram_print(u' ') |
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
| # 重複除去が必要 | |
| まざ | |
| ざき | |
| やまざ | |
| まざき | |
| ざき | |
| やまざき | |
| まざき | |
| ざき | |
| まさ | |
| さよ | |
| よし | |
| まさよ | |
| さよし | |
| よし | |
| まさよし | |
| さよし | |
| よし | |
| -- | |
| たか | |
| かは | |
| はし | |
| たかは | |
| かはし | |
| はし | |
| たかはし | |
| かはし | |
| はし | |
| ゆき | |
| きひ | |
| ひろ | |
| ゆきひ | |
| きひろ | |
| ひろ | |
| ゆきひろ | |
| きひろ | |
| ひろ | |
| -- | |
| -- |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment