Spaces:
Sleeping
Sleeping
Commit ·
2c50978
1
Parent(s): 092ef5d
Update functions.py
Browse files- functions.py +1 -1
functions.py
CHANGED
|
@@ -11,6 +11,7 @@ import joblib
|
|
| 11 |
nltk.download('punkt')
|
| 12 |
nltk.download('wordnet')
|
| 13 |
nltk.download('averaged_perceptron_tagger')
|
|
|
|
| 14 |
|
| 15 |
def get_wordnet_pos(treebank_tag):
|
| 16 |
if treebank_tag.startswith('J'):
|
|
@@ -27,7 +28,6 @@ def get_wordnet_pos(treebank_tag):
|
|
| 27 |
lemmatizer = WordNetLemmatizer()
|
| 28 |
|
| 29 |
def preprocess_text(text):
|
| 30 |
-
stopword_list= joblib.load('stopword_list.joblib')
|
| 31 |
text = text.lower() # lowercase text
|
| 32 |
tokens = word_tokenize(text) # tokenize
|
| 33 |
filtered_words = [word for word in tokens if word.lower() not in stopword_list= load.]
|
|
|
|
| 11 |
nltk.download('punkt')
|
| 12 |
nltk.download('wordnet')
|
| 13 |
nltk.download('averaged_perceptron_tagger')
|
| 14 |
+
stopword_list= joblib.load('stopword_list.joblib')
|
| 15 |
|
| 16 |
def get_wordnet_pos(treebank_tag):
|
| 17 |
if treebank_tag.startswith('J'):
|
|
|
|
| 28 |
lemmatizer = WordNetLemmatizer()
|
| 29 |
|
| 30 |
def preprocess_text(text):
|
|
|
|
| 31 |
text = text.lower() # lowercase text
|
| 32 |
tokens = word_tokenize(text) # tokenize
|
| 33 |
filtered_words = [word for word in tokens if word.lower() not in stopword_list= load.]
|