Twitter sentimental analysis using python

Author: adityajai25

MachineLearning Projects/Twitter-sentiments-analysis/README.md

@@ -0,0 +1,29 @@
+
+## Get Started
+
+Tweepy: 
+Tweepy is the python client for the official Twitter API. Install it using following pip command:
+
+```bash
+            pip install tweepy
+```
+
+TextBlob: textblob is the python library for processing textual data. Install it using following pip command:
+
+```bash
+            pip install textblob
+```
+
+Install some NLTK corpora using following command:
+
+```bash
+            python -m textblob.download_corpora
+```
+## Authentication: 
+In order to fetch tweets through Twitter API, one needs to register an App through their twitter account. Follow these steps for the same:
+
+1. Open developer.twitter.com/apps and click the button: ‘Create New App’
+2. Fill the application details. You can leave the callback url field empty.
+3. Once the app is created, you will be redirected to the app page.
+4. Open the ‘Keys and Access Tokens’ tab.
+5. Copy ‘Consumer Key’, ‘Consumer Secret’, ‘Access token’ and ‘Access Token Secret’.

MachineLearning Projects/Twitter-sentiments-analysis/twitter-sentiment-analysis.py

@@ -0,0 +1,114 @@
+import re
+import tweepy
+from tweepy import OAuthHandler
+from textblob import TextBlob
+
+class TwitterClient(object):
+	def __init__(self):
+		# keys and tokens from the Twitter Dev Console
+		consumer_key = 'XXXXXXXXXXXXXXXXXXXXXXXX'
+		consumer_secret = 'XXXXXXXXXXXXXXXXXXXXXXXXXXXX'
+		access_token = 'XXXXXXXXXXXXXXXXXXXXXXXXXXXX'
+		access_token_secret = 'XXXXXXXXXXXXXXXXXXXXXXXXX'
+
+		# attempt authentication
+		try:
+			# create OAuthHandler object
+			self.auth = OAuthHandler(consumer_key, consumer_secret)
+			# set access token and secret
+			self.auth.set_access_token(access_token, access_token_secret)
+			# create tweepy API object to fetch tweets
+			self.api = tweepy.API(self.auth)
+		except:
+			print("Error: Authentication Failed")
+
+	def clean_tweet(self, tweet):
+		'''
+		Utility function to clean tweet text by removing links, special characters
+		using simple regex statements.
+		'''
+		return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])
+									|(\w+:\/\/\S+)", " ", tweet).split())
+
+	def get_tweet_sentiment(self, tweet):
+		'''
+		Utility function to classify sentiment of passed tweet
+		using textblob's sentiment method
+		'''
+		# create TextBlob object of passed tweet text
+		analysis = TextBlob(self.clean_tweet(tweet))
+		# set sentiment
+		if analysis.sentiment.polarity > 0:
+			return 'positive'
+		elif analysis.sentiment.polarity == 0:
+			return 'neutral'
+		else:
+			return 'negative'
+
+	def get_tweets(self, query, count = 10):
+		'''
+		Main function to fetch tweets and parse them.
+		'''
+		# empty list to store parsed tweets
+		tweets = []
+
+		try:
+			# call twitter api to fetch tweets
+			fetched_tweets = self.api.search(q = query, count = count)
+
+			# parsing tweets one by one
+			for tweet in fetched_tweets:
+				# empty dictionary to store required params of a tweet
+				parsed_tweet = {}
+
+				# saving text of tweet
+				parsed_tweet['text'] = tweet.text
+				# saving sentiment of tweet
+				parsed_tweet['sentiment'] = self.get_tweet_sentiment(tweet.text)
+
+				# appending parsed tweet to tweets list
+				if tweet.retweet_count > 0:
+					# if tweet has retweets, ensure that it is appended only once
+					if parsed_tweet not in tweets:
+						tweets.append(parsed_tweet)
+				else:
+					tweets.append(parsed_tweet)
+
+			# return parsed tweets
+			return tweets
+
+		except tweepy.TweepError as e:
+			# print error (if any)
+			print("Error : " + str(e))
+
+def main():
+	# creating object of TwitterClient Class
+	api = TwitterClient()
+	# calling function to get tweets
+	tweets = api.get_tweets(query = 'Donald Trump', count = 200)
+
+	# picking positive tweets from tweets
+	ptweets = [tweet for tweet in tweets if tweet['sentiment'] == 'positive']
+	# percentage of positive tweets
+	print("Positive tweets percentage: {} %".format(100*len(ptweets)/len(tweets)))
+	# picking negative tweets from tweets
+	ntweets = [tweet for tweet in tweets if tweet['sentiment'] == 'negative']
+	# percentage of negative tweets
+	print("Negative tweets percentage: {} %".format(100*len(ntweets)/len(tweets)))
+	# percentage of neutral tweets
+	print("Neutral tweets percentage: {} % \
+		".format(100*(len(tweets) -(len( ntweets )+len( ptweets)))/len(tweets)))
+
+	# printing first 5 positive tweets
+	print("\n\nPositive tweets:")
+	for tweet in ptweets[:10]:
+		print(tweet['text'])
+
+	# printing first 5 negative tweets
+	print("\n\nNegative tweets:")
+	for tweet in ntweets[:10]:
+		print(tweet['text'])
+
+if __name__ == "__main__":
+	# calling main function
+	main()