mirror of
https://github.com/gsi-upm/senpy
synced 2024-11-14 04:32:29 +00:00
Added sufixes dictionary for wordnet lemmatizer. This close #4
This commit is contained in:
parent
5427b02a1a
commit
241f478a68
@ -70,23 +70,23 @@ class SentiTextPlugin(SentimentPlugin):
|
|||||||
|
|
||||||
def analyse_entry(self, entry, params):
|
def analyse_entry(self, entry, params):
|
||||||
|
|
||||||
language = params.get("language","eng")
|
language = params.get("language")
|
||||||
text = entry.get("text", None)
|
text = entry.get("text", None)
|
||||||
tokens = self._tokenize(text)
|
tokens = self._tokenize(text)
|
||||||
tokens = self._pos(tokens)
|
tokens = self._pos(tokens)
|
||||||
|
sufixes = {'es':'spa','en':'eng','it':'ita','fr':'fra'}
|
||||||
for i in tokens:
|
for i in tokens:
|
||||||
tokens[i]['lemmas'] = {}
|
tokens[i]['lemmas'] = {}
|
||||||
for w in tokens[i]['tokens']:
|
for w in tokens[i]['tokens']:
|
||||||
lemmas = wn.lemmas(w[0], lang=language)
|
lemmas = wn.lemmas(w[0], lang=sufixes[language])
|
||||||
if len(lemmas) == 0:
|
if len(lemmas) == 0:
|
||||||
continue
|
continue
|
||||||
tokens[i]['lemmas'][w[0]] = lemmas
|
tokens[i]['lemmas'][w[0]] = lemmas
|
||||||
|
|
||||||
if language == "eng":
|
if language == "en":
|
||||||
trans = TextBlob(unicode(text))
|
trans = TextBlob(unicode(text))
|
||||||
else:
|
else:
|
||||||
trans = TextBlob(unicode(text)).translate(from_lang=TextBlob(unicode(text)).detect_language(),to='en')
|
trans = TextBlob(unicode(text)).translate(from_lang=language,to='en')
|
||||||
useful_synsets = {}
|
useful_synsets = {}
|
||||||
for s_i, t_s in enumerate(trans.sentences):
|
for s_i, t_s in enumerate(trans.sentences):
|
||||||
useful_synsets[s_i] = {}
|
useful_synsets[s_i] = {}
|
||||||
|
@ -13,7 +13,7 @@
|
|||||||
"language": {
|
"language": {
|
||||||
"aliases": ["language", "l"],
|
"aliases": ["language", "l"],
|
||||||
"required": true,
|
"required": true,
|
||||||
"options": ["eng","spa", "ita", "fra", "auto"],
|
"options": ["en","es", "it", "fr", "auto"],
|
||||||
"default": "auto"
|
"default": "auto"
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
|
Loading…
Reference in New Issue
Block a user