My Tweets function can output score and tweet from Tweeter user. However, the output is a bit different to the staff version's output.
I find that some words with first character capitalized are not detected even they exist in the positive-words.txt or negative-words.txt. But I have make all tokens lowercase using the .lower() method.
There may be some other reasons for this problem. I am still thinking. Could anyone help? Thanks in advance.
My tweets code:
#!/usr/bin/env python3
import os
import sys
import helpers
import analyzer
from termcolor import colored
def main():
# ensure proper usage
if len(sys.argv) != 2:
sys.exit("Usage: ./tweets @screen_name")
# accepts screen name for a user on Twitter without "@"
user = (sys.argv[1]).lstrip("@")
# absolute paths to lists
positives = os.path.join(sys.path[0], "positive-words.txt")
negatives = os.path.join(sys.path[0], "negative-words.txt")
# instantiate analyzer
tweet_analyzer = analyzer.Analyzer(positives, negatives)
# query Twitter’s API for a user’s most recent 50 tweets
tweets = helpers.get_user_timeline(user, 50)
# check if successful
if tweets == None:
# error message if unsuccessful
sys.exit("Error! The screen name may not exist or its tweets are private.")
score = 0
# analyze each tweet
for tweet in tweets:
score = tweet_analyzer.analyze(tweet)
text = "{0:2d} {1}".format(score, tweet)
if score > 0.0:
print(colored(text, "green"))
elif score < 0.0:
print(colored(text, "red"))
else:
print(colored(text, "yellow"))
score = 0
if __name__ == "__main__":
main()
And my analyzer.py code:
import nltk
class Analyzer():
"""Implements sentiment analysis."""
# load positive and negative words
def __init__(self, positives, negatives):
"""Initialize Analyzer."""
# declare lists for positve and negative words
self.positives = []
self.negatives = []
# load words from positive-words.txt
with open(positives) as positive:
for line in positive:
# don't include the comments
if line.startswith(";") != True:
# extend self.positives list
# split on all leading/trailing whitespace
self.positives.extend(line.split())
# load words from negative-words.txt
with open(negatives) as negative:
for line in negative:
# don't include the comments
if line.startswith(";") != True:
# extend self.negatives list
# split on all leading/trailing whitespace
self.negatives.extend(line.split())
def analyze(self, text):
"""Analyze text for sentiment, returning its score."""
# split a tweet into a list of words (shorter strings)
tokenizer = nltk.tokenize.TweetTokenizer()
tokens = tokenizer.tokenize(text)
# initial score is neutral
score = 0
# iterate over tokens
for token in tokens:
# make all tokens lowercase
token.lower()
# assign each word in text a value (-1, 0, 1)
if token in self.positives:
score += 1
elif token in self.negatives:
score -= 1
# calculate text's total score
return score
Updated:
Athough I have submitted to cs50.me and score 100/100, I still want to know if I have done anything wrong. I add two examples of my and staff's output below. Any help is appreciated. Thanks!
My output:
~/workspace/pset6/sentiments/ $ python smile Love
:|
~/workspace/pset6/sentiments/ $ python smile Hate
:|
Staff's output:
~/workspace/pset6/sentiments/ $ ~cs50/pset6/smile Love
:)
~/workspace/pset6/sentiments/ $ ~cs50/pset6/smile Hate
:(
My output:
~/workspace/pset6/sentiments/ $ python tweets @cs50
0 RT @actoutgames: Boston Travel Day 1! @cs50 @Harvard Professor Interview with @davidjmalan & Walking the Freedom Trail! https://t.co/7ybOIu…
0 RT @HS_QuizShow: Crack the code to this question from @davidjmalan of @CS50 & @HarvardSummer – watch @WGBH this weekend for the answer! htt…
Staff's output:
~/workspace/pset6/sentiments/ $ ~cs50/pset6/tweets @cs50
1 RT @actoutgames: Boston Travel Day 1! @cs50 @Harvard Professor Interview with @davidjmalan & Walking the Freedom Trail! https://t.co/7ybOIu…
-1 RT @HS_QuizShow: Crack the code to this question from @davidjmalan of @CS50 & @HarvardSummer – watch @WGBH this weekend for the answer! htt…
