twitter_sentiment.py

# -*- coding: utf-8 -*-
"""twitter_sentiment.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1hpvsrDsdq2fHKNpQYvbOTJxVSvkKz5_V

Author: Utkarsh Singhal: https://www.linkedin.com/in/utkarsh-singhal-584770181
Article Link on TradeWithPython: https://tradewithpython.com/sentiment-analysis-for-stocks-from-twitter

"""

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import datetime as dt
import re
from wordcloud import WordCloud, STOPWORDS
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import snscrape.modules.twitter as sntwitter

nltk.download('vader_lexicon')

#Get user input
query = input("Query: ")

#As long as the query is valid (not empty or equal to '#')...
if query != '':
    noOfTweet = input("Enter the number of tweets you want to Analyze: ")
    if noOfTweet != '' :
        noOfDays = input("Enter the number of days you want to Scrape Twitter for: ")
        if noOfDays != '':
                #Creating list to append tweet data
                tweets_list = []
                now = dt.date.today()
                now = now.strftime('%Y-%m-%d')
                yesterday = dt.date.today() - dt.timedelta(days = int(noOfDays))
                yesterday = yesterday.strftime('%Y-%m-%d')
                for i,tweet in enumerate(sntwitter.TwitterSearchScraper(query + ' lang:en since:' +  yesterday + ' until:' + now + ' -filter:links -filter:replies').get_items()):
                    if i > int(noOfTweet):
                        break
                    tweets_list.append([tweet.date, tweet.id, tweet.content, tweet.username])

                #Creating a dataframe from the tweets list above 
                df = pd.DataFrame(tweets_list, columns=['Datetime', 'Tweet Id', 'Text', 'Username'])

                print(df)

# Create a function to clean the tweets
def cleanTxt(text):
    text = re.sub('@[A-Za-z0–9]+', '', text) #Removing @mentions
    text = re.sub('#', '', text) # Removing '#' hash tag
    text = re.sub('RT[\s]+', '', text) # Removing RT
    text = re.sub('https?:\/\/\S+', '', text) # Removing hyperlink
    return text
df["Text"] = df["Text"].apply(cleanTxt)

#Sentiment Analysis
def percentage(part,whole):
    return 100 * float(part)/float(whole)

#Assigning Initial Values
positive = 0
negative = 0
neutral = 0
#Creating empty lists
tweet_list1 = []
neutral_list = []
negative_list = []
positive_list = []

#Iterating over the tweets in the dataframe
for tweet in df['Text']:
    tweet_list1.append(tweet)
    analyzer = SentimentIntensityAnalyzer().polarity_scores(tweet)
    neg = analyzer['neg']
    neu = analyzer['neu']
    pos = analyzer['pos']
    comp = analyzer['compound']

    if neg > pos:
        negative_list.append(tweet) #appending the tweet that satisfies this condition
        negative += 1 #increasing the count by 1
    elif pos > neg:
        positive_list.append(tweet) #appending the tweet that satisfies this condition
        positive += 1 #increasing the count by 1
    elif pos == neg:
        neutral_list.append(tweet) #appending the tweet that satisfies this condition
        neutral += 1 #increasing the count by 1 

positive = percentage(positive, len(df)) #percentage is the function defined above
negative = percentage(negative, len(df))
neutral = percentage(neutral, len(df))

#Converting lists to pandas dataframe
tweet_list1 = pd.DataFrame(tweet_list1)
neutral_list = pd.DataFrame(neutral_list)
negative_list = pd.DataFrame(negative_list)
positive_list = pd.DataFrame(positive_list)
#using len(length) function for counting
print("Since " + noOfDays + " days, there have been", len(tweet_list1) ,  "tweets on " + query, end='\n*')
print("Positive Sentiment:", '%.2f' % len(positive_list), end='\n*')
print("Neutral Sentiment:", '%.2f' % len(neutral_list), end='\n*')
print("Negative Sentiment:", '%.2f' % len(negative_list), end='\n*')

#Creating PieCart

labels = ['Positive ['+str(round(positive))+'%]' , 'Neutral ['+str(round(neutral))+'%]','Negative ['+str(round(negative))+'%]']
sizes = [positive, neutral, negative]
colors = ['yellowgreen', 'blue','red']
patches, texts = plt.pie(sizes,colors=colors, startangle=90)
plt.style.use('default')
plt.legend(labels)
plt.title("Sentiment Analysis Result for keyword= "+query+"" )
plt.axis('equal')
plt.show()

# word cloud visualization
def word_cloud(text):
    stopwords = set(STOPWORDS)
    allWords = ' '.join([twts for twts in text])
    wordCloud = WordCloud(background_color='black',width = 1600, height = 800,stopwords = stopwords,min_font_size = 20,max_font_size=150,colormap='prism').generate(allWords)
    fig, ax = plt.subplots(figsize=(20,10), facecolor='k')
    plt.imshow(wordCloud)
    ax.axis("off")
    fig.tight_layout(pad=0)
    plt.show()

print('Wordcloud for ' + query)
word_cloud(df['Text'].values)