Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import tweepy as tw
 import pandas as pd
+import matplotlib.pyplot as plt
 from transformers import pipeline
 import os
 
@@ -8,50 +9,54 @@ consumer_key = 'OCgWzDW6PaBvBeVimmGBqdAg1'
 consumer_secret = 'tBKnmyg5Jfsewkpmw74gxHZbbZkGIH6Ee4rsM0lD1vFL7SrEIM'
 access_token = '1449663645412065281-LNjZoEO9lxdtxPcmLtM35BRdIKYHpk'
 access_token_secret = 'FL3SGsUWSzPVFnG7bNMnyh4vYK8W1SlABBNtdF7Xcbh7a'
-
 auth = tw.OAuthHandler(consumer_key, consumer_secret)
 auth.set_access_token(access_token, access_token_secret)
 api = tw.API(auth, wait_on_rate_limit=True)
 classifier = pipeline('sentiment-analysis')
-
-# Define file name and headers
 FILE_NAME = 'query_history.csv'
 HEADERS = ['Search Query', 'Number of Tweets', 'Results', 'Date']
 
-# Create file if it does not exist
 if not os.path.isfile(FILE_NAME):
     df = pd.DataFrame(columns=HEADERS)
     df.to_csv(FILE_NAME, index=False)
 
-# Make program take up full width of screen
 st.set_page_config(page_title='😃 Twitter Sentiment Analysis', layout='wide')
 
-# Define function to display history
 def display_history():
     df = pd.read_csv(FILE_NAME)
     st.dataframe(df.style.highlight_max(axis=0))
 
-# Define main function
 def run():
-    with st.form(key='Enter name'):
-        search_words = st.text_input('Enter a word or phrase you want to know about')
-        number_of_tweets = st.number_input('How many tweets do you want to see? (maximum 50)', 0,50,10)
-        submit_button = st.form_submit_button(label='Submit')
+    search_words = st.text_input('Enter a word or phrase you want to know about')
+    number_of_tweets = st.number_input('How many tweets do you want to see? (maximum 50)', 1, 50, 50)
+    submit_button = st.form_submit_button(label='Submit')
 
     if submit_button:
-        tweets =tw.Cursor(api.search_tweets,q=search_words,lang="en").items(number_of_tweets)
-        tweet_list = [i.text for i in tweets]
-        p = [i for i in classifier(tweet_list)]
-        q=[p[i]['label'] for i in range(len(p))]
-        df = pd.DataFrame(list(zip([search_words], [number_of_tweets], [tweet_list], [pd.Timestamp.now()])),columns = HEADERS)
-        st.write(pd.DataFrame(list(zip(tweet_list, q)),columns =['Latest '+str(number_of_tweets)+' Tweets'+' on '+search_words, 'sentiment']))
+        unique_tweets, tweet_list, sentiment_list = set(), [], []
+        tweets = tw.Cursor(api.search_tweets, q=search_words, lang="en").items(number_of_tweets)
+        for tweet in tweets:
+            if tweet.text not in unique_tweets:
+                unique_tweets.add(tweet.text)
+                tweet_list.append(tweet.text)
+                p = classifier(tweet.text)
+                sentiment_list.append(p[0]['label'])
+
+        df = pd.DataFrame(list(zip(tweet_list, sentiment_list)), columns=['Tweets', 'Sentiment'])
+        st.write(df)
+
+        summary = df.groupby('Sentiment').size().reset_index(name='Counts')
+        fig, ax = plt.subplots()
+        ax.pie(summary['Counts'], labels=summary['Sentiment'], autopct='%1.1f%%', startangle=90)
+        ax.axis('equal')
+        st.pyplot(fig)
+
         with open(FILE_NAME, mode='a', newline='') as file:
             df.to_csv(file, header=False, index=False)
-            
+
     if st.button('Clear History'):
         os.remove(FILE_NAME)
         st.write('History has been cleared.')
-        
+
     if st.button('Display History'):
         display_history()