Lost trying to figure out sentiments PSET 6 2017

Question

I need some help with pset6 I'm basically lost trying to figure out what I should be doing. I have my analyzer code which doesn't return any errors when I run it but at the same time returns no output either. I also have my tweets code which also returns no errors but at the same time no output as well. I haven't gotten started on the application.py because I don't know where I should be pulling the positive, negative and neutral percentages from. Here is my analyzer code:

import nltk
import sys
import string

from nltk.tokenize import TweetTokenizer

class Analyzer():
  """Implements sentiment analysis."""

def __init__(self, positives, negatives):
    """Initialize Analyzer."""

    self.negatives = []
    self.positives = []

    with open(negatives) as negative:
        for line in negative:
            if line.startswith((";", " ")):
                continue
            else:
                self.negatives.extend(line.split())

    with open(positives) as positive:
        for line in positive:
            if line.startswith((";", " ")):
                continue
            else:
                self.positives.extend(line.split())

def analyze(self, text):
    """Analyze text for sentiment, returning its score."""

    tokenizer = nltk.tokenize.TweetTokenizer()
    tokens = tokenizer.tokenize(text)
    score = 0

    for token in tokens:
        token.lower()

        if token in self.positives:
            score += 1
        elif token in self.negatives:
            score -= 1


    # TODO
    return score

Here is my tweets code:

#!/usr/bin/env python3

# TODO
import os
import sys
import nltk

from analyzer import Analyzer
from termcolor import colored
from helpers import get_user_timeline

def main():

#Ensure proper usage 
if len(sys.argv) != 2:
    sys.exit("Usage: ./tweets twitterhandle")

positives = os.path.join(sys.path[0], "positive-words.txt")
negatives = os.path.join(sys.path[0], "negative-words.txt")  

analyzer = Analyzer(positives, negatives)

final_score = analyzer.analyze(sys.argv[1])

for i in range (0, len(final_score)):
    score = final_score[i]
    print(score[0], end="")
    if score[0] > 0.0:
        print(colored(score, "green"))
    elif score[0] < 0.0:
        print(colored(score, "red"))
    else:
        print(colored(score, "yellow"))

if __name__ == "__main__":
    main()

def checkTweet(self, text):
    tweets = get_user_timeline(text, 50)
    if tweets == None:
        sys.exit("Error")
    print(tweets)

    final_score = []
    for tweet in tweets:
        score = 0    
        tokenizer = nltk.tokenize.TweetTokenizer()
        tokens = tokenizer.tokenize(tweet)
        for word in tokens:
            if word in self.positives:
                score += 1
            elif word in self.negatives:
                score -= 1
            else:
                score = 0
        scores = (score, tweet)
        final_score.append(scores)

    return final_score

Lastly here is the untouched application.py:

from flask import Flask, redirect, render_template, request, url_for

import helpers
from analyzer import Analyzer

app = Flask(__name__)

@app.route("/")
def index():
return render_template("index.html")

@app.route("/search")
def search():

# validate screen_name
screen_name = request.args.get("screen_name", "").lstrip("@")
if not screen_name:
    return redirect(url_for("index"))

# get screen_name's tweets
tweets = helpers.get_user_timeline(screen_name)

# TODO
positive, negative, neutral = 0.0, 0.0, 100.0

# generate chart
chart = helpers.chart(positive, negative, neutral)

# render results
return render_template("search.html", chart=chart, screen_name=screen_name)

Please help if you can. I know it is a lot of code to go through. Thanks

Answer 1

One problem in analyze is with split here self.negatives.extend(line.split()). split returns a list. You would have to put token in a list to find it in self.positives or self.negatives. Or perhaps you meant strip.