1
0
mirror of https://github.com/gsi-upm/sitc synced 2025-09-16 03:42:21 +00:00

Compare commits

1 Commits

Author SHA1 Message Date
Dani Vera
19ea5dff09 Update 4_1_Lexical_Processing.ipynb 2019-11-26 15:14:40 +01:00

View File

@@ -326,7 +326,7 @@
"def preprocess(words, type='doc'):\n",
" if (type == 'tweet'):\n",
" tknzr = TweetTokenizer(strip_handles=True, reduce_len=True)\n",
" tokens = tknzr.tokenize(tweet)\n",
" tokens = tknzr.tokenize(words)\n",
" else:\n",
" tokens = nltk.word_tokenize(words.lower())\n",
" porter = nltk.PorterStemmer()\n",