timmyshen · July 9, 2014 03:32 · Jul 9, 2014
diff --git a/tweet_sentiment.py b/tweet_sentiment.py
@@ -0,0 +1,54 @@
+import sys
+import json
+
+def hw():
+    print 'Hello, world!'
+
+def lines(fp):
+    print str(len(fp.readlines()))
+
+def main():
+    sent_file = open(sys.argv[1])
+    tweet_file = open(sys.argv[2])
+    hw()
+    lines(sent_file)
+    lines(tweet_file)
+
+
+def make_afinn_dict(afinn_file):
+    with open(afinn_file) as f:
+        # lines -- list of strings
+        lines = f.readlines()
+    linecells = [convert_line(line) for line in lines]
+    return dict(linecells)
+
+
+def convert_line(line):
+    word, score_str = line.rstrip().split('\t')
+    score = int(score_str)
+    return [word, score]
+
+
+def make_tweet_json(input_file):
+    with open(input_file) as f:
+        lines = f.readlines()
+    return [make_tweet(line) for line in lines]
+
+
+def make_tweet(line):
+    return json.loads(line)
+
+def calc_score(afinn_dict, text):
+    words = text.split()
+    words_scores = [afinn_dict[word] if afinn_dict.has_key(word) else 0 for word in words]
+    return sum(words_scores)
+
+if __name__ == '__main__':
+    afinn_file = sys.argv[1]
+    input_file = sys.argv[2]
+    afinn_dict = make_afinn_dict(afinn_file)
+    tweets = make_tweet_json(input_file)
+    scores = [calc_score(afinn_dict, tweet['text']) if tweet.has_key('text') else 0 for tweet in tweets]
+    for score in scores:
+        print score
+