Update app.py

app.py

@@ -7,6 +7,8 @@ import itertools
 import collections
 from collections import Counter
 import numpy as np
+from transformers import pipeline
+classifier = pipeline('sentiment-analysis')
 #hashtag_phrase ="#datascience"
 #recent_tweet_count_you_want =100
 def search_hashtag1(hashtag_phrase,recent_tweet_count_you_want):
@@ -27,7 +29,8 @@ def search_hashtag1(hashtag_phrase,recent_tweet_count_you_want):
   for tweet in tweepy.Cursor(api.search_tweets, q=hashtag_phrase+' -filter:retweets',lang="en", tweet_mode='extended').items(recent_tweet_count_you_want):
     timestamp1=tweet.created_at
     timestamp.append(timestamp1)
-    tweet_text1=tweet.full_text.replace('\n',' ').encode('utf-8')
+    #tweet_text1=tweet.full_text.replace('\n',' ').encode('utf-8')
+    tweet_text1=tweet.full_text
     tweet_text.append(tweet_text1)
     user_name1=tweet.user.screen_name.encode('utf-8')
     user_name.append(user_name1)
@@ -40,9 +43,15 @@ def search_hashtag1(hashtag_phrase,recent_tweet_count_you_want):
   data5=pd.concat([data4,data3],axis=1)
   data7=pd.DataFrame(user_id,columns={"user_id"})
   data6=pd.concat([data5,data7],axis=1)
-  data6.to_csv("tweet_data1.csv")
+  tweet_list=data6.tweet_text.to_list()
+  p = [i for i in classifier(tweet_list)]
+  q=[p[i]['label'] for i in range(len(p))]
+  data10=pd.DataFrame(q,columns={"sentiment"})
+  data_tweet_final=pd.concat([data6,data10],axis=1)
+  data_tweet_final.to_csv("tweet_data2.csv")
+  #data6.to_csv("tweet_data1.csv")
   #data6=data5.head(10)
-  return data6
+  return data_tweet_final
 iface = gr.Interface(
     search_hashtag1,inputs=["text","number"],
     outputs="dataframe",