Created
June 20, 2011 10:13
-
-
Save anonymous/1035399 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
# | |
# wget wget http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/6010/zip/imm6010.zip | |
# unzip imm6010.zip | |
import math | |
import re | |
import sys | |
reload(sys) | |
sys.setdefaultencoding('utf-8') | |
# AFINN-111 is as of June 2011 the most recent version of AFINN | |
filenameAFINN = 'AFINN/AFINN-111.txt' | |
afinn = dict(map(lambda (w, s): (w, int(s)), [ | |
ws.strip().split('\t') for ws in open(filenameAFINN) ])) | |
# Word splitter pattern | |
pattern_split = re.compile(r"\W+") | |
def sentiment(text): | |
""" | |
Returns a float for sentiment strength based on the input text. | |
Positive values are positive valence, negative value are negative valence. | |
""" | |
words = pattern_split.split(text.lower()) | |
sentiments = map(lambda word: afinn.get(word, 0), words) | |
if sentiments: | |
# How should you weight the individual word sentiments? | |
# You could do N, sqrt(N) or 1 for example. Here I use sqrt(N) | |
sentiment = float(sum(sentiments))/math.sqrt(len(sentiments)) | |
else: | |
sentiment = 0 | |
return sentiment | |
if __name__ == '__main__': | |
# Single sentence example: | |
text = "Finn is stupid and idiotic" | |
print("%6.2f %s" % (sentiment(text), text)) | |
# No negation and booster words handled in this approach | |
text = "Finn is only a tiny bit stupid and not idiotic" | |
print("%6.2f %s" % (sentiment(text), text)) | |
# Example with downloading from Twitter: | |
import simplejson | |
import urllib | |
query = "pfizer" | |
json = simplejson.load(urllib.urlopen("http://search.twitter.com/search.json?q=" + query)) | |
sentiments = map(sentiment, [ tweet['text'] for tweet in json['results'] ]) | |
print("%6.2f %s" % (sum(sentiments)/math.sqrt(len(sentiments)), query)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment