Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Add canon_case function

This commit is contained in:
Matthew Honnibal 2014-08-30 20:57:43 +02:00
parent 8bbfadfced
commit a779275a59
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/orth.py
View File

@ -41,7 +41,16 @@ def can_tag(name, thresh):
# String features # String features
def canon_case(string, prob, cluster, case_stats, tag_stats): def canon_case(string, prob, cluster, case_stats, tag_stats):
return string upper_pc = case_stats['upper']
title_pc = case_stats['title']
lower_pc = case_stats['lower']
if upper_pc >= lower_pc and upper_pc >= title_pc:
return string.upper()
elif title_pc >= lower_pc:
return string.title()
else:
return string.lower()
def word_shape(string, *args): def word_shape(string, *args):