o2w/talon
5
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

consider word capitilized only if it is camel case - not all upper case

Browse Source
This commit is contained in:
Sergey Obukhov
2016-07-19 16:22:04 -07:00
parent 7cdd7a8f35
commit a21ccdb21b
5 changed files with 2504 additions and 2670 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5141
talon/signature/data/train.data
View File

File diff suppressed because it is too large Load Diff

3
talon/signature/learning/helpers.py
View File

@@ -185,12 +185,13 @@ def capitalized_words_percent(s):
s = to_unicode(s, precise=True)
words = re.split('\s', s)
words = [w for w in words if w.strip()]
words = [w for w in words if len(w) > 2]
capitalized_words_counter = 0
valid_words_counter = 0
for word in words:
if not INVALID_WORD_START.match(word):
valid_words_counter += 1
if word[0].isupper():
if word[0].isupper() and not word[1].isupper():
capitalized_words_counter += 1
if valid_words_counter > 0 and len(words) > 1:
return 100 * float(capitalized_words_counter) / valid_words_counter