Python NLTK: SyntaxError: Non-ASCII character '\xc3' in file (Sentiment Analysis -NLP)
I am playing around with NLTK to do an assignment on sentiment analysis. I am using Python 2.7. NLTK 3.0 and NumPy1.9.1 version.
This is the code :
__author__ = 'karan'
import nltk
import re
import sys
def main():
print("Start");
# getting the stop words
stopWords = open("english.txt","r");
stop_word = stopWords.read().split();
AllStopWrd = []
for wd in stop_word:
AllStopWrd.append(wd);
print("stop words-> ",AllStopWrd);
# sample and also cleaning it
tweet1= 'Love, my new toyí ½í¸í ½í¸#iPhone6. Its good https://twitter.com/Sandra_Ortega/status/513807261769424897/photo/1'
print("old tweet-> ",tweet1)
tweet1 = tweet1.lower()
tweet1 = ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)"," ",tweet1).split())
print(tweet1);
tw = tweet1.split()
print(tw)
#tokenize
sentences = nltk.word_tokenize(tweet1)
print("tokenized ->", sentences)
#remove stop words
Otweet =[]
for w in tw:
if w not in AllStopWrd:
Otweet.append(w);
print("sans stop word-> ",Otweet)
# get taggers for neg/pos/inc/dec/inv words
taggers ={}
negWords = open("neg.txt","r");
neg_word = negWords.read().split();
print("ned words-> ",neg_word)
posWords = open("pos.txt","r");
pos_word = posWords.read().split();
print("pos words-> ",pos_word)
incrWords = open("incr.txt","r");
inc_word = incrWords.read().split();
print("incr words-> ",inc_word)
decrWords = open("decr.txt","r");
dec_word = decrWords.read().split();
print("dec wrds-> ",dec_word)
invWords = open("inverse.txt","r");
inv_word = invWords.read().split();
print("inverse words-> ",inv_word)
for nw in neg_word:
taggers.update({nw:'negative'});
for pw in pos_word:
taggers.update({pw:'positive'});
for iw in inc_word:
taggers.update({iw:'inc'});
for dw in dec_word:
taggers.update({dw:'dec'});
for ivw in inv_word:
taggers.update({ivw:'inv'});
print("tagger-> ",taggers)
print(taggers.get('little'))
# get parts of speech
posTagger = [nltk.pos_tag(tw)]
print("posTagger-> ",posTagger)
main();
This is the error that I am getting when running my code:
SyntaxError: Non-ASCII character '\xc3' in file C:/Users/karan/PycharmProjects/mainProject/sentiment.py on line 19, but no encoding declared; see http://www.python.org/peps/pep-0263.html for details
How do I fix this error?
I also tried the code using Python 3.4.2 and with NLTK 3.0 and NumPy 1.9.1 but then I get the error:
Traceback (most recent call last):
File "C:/Users/karan/PycharmProjects/mainProject/sentiment.py", line 80, in <module>
main();
File "C:/Users/karan/PycharmProjects/mainProject/sentiment.py", line 72, in main
posTagger = [nltk.pos_tag(tw)]
File "C:\Python34\lib\site-packages\nltk\tag\__init__.py", line 100, in pos_tag
tagger = load(_POS_TAGGER)
File "C:\Python34\lib\site-packages\nltk\data.py", line 779, in load
resource_val = pickle.load(opened_resource)
UnicodeDecodeError: 'ascii' codec can't decode byte 0xcb in position 0: ordinal not in range(128)
Add the following to the top of your file # coding=utf-8
If you go to the link in the error you can seen the reason why:
Defining the Encoding
Python will default to ASCII as standard encoding if no other encoding hints are given. To define a source code encoding, a magic comment must be placed into the source files either as first or second line in the file, such as: # coding=