t1.py

import sys,tweepy,csv,re
from textblob import TextBlob
import matplotlib.pyplot as plt
import re
import pandas as pd 
import numpy as np 
import seaborn as sns
import string
import nltk
import warnings 
warnings.filterwarnings("ignore", category=DeprecationWarning)
%matplotlib inline

class SentimentAnalysis:

    def __init__(self):
        self.tweets = []
        self.tweetText = []
        self.result=[]
    def DownloadData(self):
        # authenticating
        consumerKey = '####################'
        consumerSecret = '#################################'
        accessToken = '##################'
        accessTokenSecret = '##############################'
        auth = tweepy.OAuthHandler(consumerKey, consumerSecret)
        auth.set_access_token(accessToken, accessTokenSecret)
        api = tweepy.API(auth)

        # input for term to be searched and how many tweets to search
        searchTerm = input("Enter Keyword/Tag to search about: ")
        NoOfTerms = int(input("Enter how many tweets to search: "))

        # searching for tweets
        self.tweets = tweepy.Cursor(api.search, q=searchTerm, lang = "en").items(NoOfTerms)

        # Open/create a file to append data to
        csvFile = open('result.csv', 'w')

        # Use csv writer
        csvWriter = csv.writer(csvFile)


        # creating some variables to store info
        polarity = 0
        positive = 0
        wpositive = 0
        spositive = 0
        negative = 0
        wnegative = 0
        snegative = 0
        neutral = 0
        i=0
        l=0
        df=pd.DataFrame(columns=['Tweet','Report'])
        def remove_pattern(input_txt, pattern):
            r = re.findall(pattern, input_txt)
            for i in r:
                input_txt = re.sub(i, '', input_txt)
                return input_txt 
        
        # iterating through tweets fetched
        for tweet in self.tweets:
            #print(tweet.text+'\n\n')
            s=remove_pattern(tweet.text,"@[\w]*")
            if(s!=None):
                s=s.replace("[^a-zA-Z#] ", " ")
            f=''
            if(s!=None):
                for w in s.split():
                    if(len(w)>3):
                        f=f+w+' '
            s=f
            #print(s+'\n')
            analysis = TextBlob(s)
            if analysis.sentiment.polarity <0:
                x=-1
            elif analysis.sentiment.polarity == 0:
                x=0
            else:
                x=1
            df.loc[l,'Tweet']=s
            df.loc[l,'Report']=x
            l+=1
            self.tweetText.append(s.encode('utf-8'))
            self.result.append(x)
            #print(analysis.sentiment) 
            # print tweet's polarity
            polarity += analysis.sentiment.polarity  # adding up polarities to find the average later

            if (analysis.sentiment.polarity == 0):  # adding reaction of how people are reacting to find average later
                neutral += 1
            elif (analysis.sentiment.polarity > 0 and analysis.sentiment.polarity <= 0.3):
                wpositive += 1
            elif (analysis.sentiment.polarity > 0.3 and analysis.sentiment.polarity <= 0.6):
                positive += 1
            elif (analysis.sentiment.polarity > 0.6 and analysis.sentiment.polarity <= 1):
                spositive += 1
            elif (analysis.sentiment.polarity > -0.3 and analysis.sentiment.polarity <= 0):
                wnegative += 1
            elif (analysis.sentiment.polarity > -0.6 and analysis.sentiment.polarity <= -0.3):
                negative += 1
            elif (analysis.sentiment.polarity > -1 and analysis.sentiment.polarity <= -0.6):
                snegative += 1


        # Write to csv and close csv file
        for i in range(NoOfTerms):
            csvWriter.writerow(self.tweetText[i])
        csvFile.close()
        df.to_csv('report.csv')
        # finding average of how people are reacting
        positive = self.percentage(positive, NoOfTerms)
        wpositive = self.percentage(wpositive, NoOfTerms)
        spositive = self.percentage(spositive, NoOfTerms)
        negative = self.percentage(negative, NoOfTerms)
        wnegative = self.percentage(wnegative, NoOfTerms)
        snegative = self.percentage(snegative, NoOfTerms)
        neutral = self.percentage(neutral, NoOfTerms)

        # finding average reaction
        polarity = polarity / NoOfTerms

        # printing out data
        print("How people are reacting on " + searchTerm + " by analyzing " + str(NoOfTerms) + " tweets.")
        print()
        print("General Report: ")

        if (polarity == 0):
            print("Neutral")
        elif (polarity > 0 and polarity <= 0.3):
            print("Weakly Positive")
        elif (polarity > 0.3 and polarity <= 0.6):
            print("Positive")
        elif (polarity > 0.6 and polarity <= 1):
            print("Strongly Positive")
        elif (polarity > -0.3 and polarity <= 0):
            print("Weakly Negative")
        elif (polarity > -0.6 and polarity <= -0.3):
            print("Negative")
        elif (polarity > -1 and polarity <= -0.6):
            print("Strongly Negative")

        print()
        print("Detailed Report: ")
        print(str(positive) + "% people thought it was positive")
        print(str(wpositive) + "% people thought it was weakly positive")
        print(str(spositive) + "% people thought it was strongly positive")
        print(str(negative) + "% people thought it was negative")
        print(str(wnegative) + "% people thought it was weakly negative")
        print(str(snegative) + "% people thought it was strongly negative")
        print(str(neutral) + "% people thought it was neutral")

        self.plotPieChart(positive, wpositive, spositive, negative, wnegative, snegative, neutral, searchTerm, NoOfTerms)


    def cleanTweet(self, tweet):
        # Remove Links, Special Characters etc from tweet
        return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t]) | (\w +:\ / \ / \S +)", " ", tweet).split())

    # function to calculate percentage
    def percentage(self, part, whole):
        temp = 100 * float(part) / float(whole)
        return format(temp, '.2f')

    def plotPieChart(self, positive, wpositive, spositive, negative, wnegative, snegative, neutral, searchTerm, noOfSearchTerms):
        labels = ['Positive [' + str(positive) + '%]', 'Weakly Positive [' + str(wpositive) + '%]','Strongly Positive [' + str(spositive) + '%]', 'Neutral [' + str(neutral) + '%]',
                  'Negative [' + str(negative) + '%]', 'Weakly Negative [' + str(wnegative) + '%]', 'Strongly Negative [' + str(snegative) + '%]']
        sizes = [positive, wpositive, spositive, neutral, negative, wnegative, snegative]
        colors = ['yellowgreen','lightgreen','darkgreen', 'gold', 'red','lightsalmon','darkred']
        patches, texts = plt.pie(sizes, colors=colors, startangle=90)
        plt.legend(patches, labels, loc="best")
        plt.title('How people are reacting on ' + searchTerm + ' by analyzing ' + str(noOfSearchTerms) + ' Tweets.')
        plt.axis('equal')
        plt.tight_layout()
        plt.show()



if __name__== "__main__":
    sa = SentimentAnalysis()
    sa.DownloadData()