Update app.py

app.py

@@ -98,21 +98,18 @@ with colT2:
 
 def analizar_tweets(search_words, number_of_tweets ):
   tweets = api.user_timeline(screen_name = search_words, count= number_of_tweets)
-  #for tweet in tweets:
-   #   tweet_list = tweet.text
+  for tweet in tweets:
+      tweet_list = tweet.text
       
-  tweet_list = [i.text for i in tweets]
+  #tweet_list = [i.text for i in tweets]
   text= pd.DataFrame(tweet_list)
-  text[0] = text[0].apply(preprocess_tweet)
-  text1=text[0].values
+  #text[0] = text[0].apply(preprocess_tweet)
+  text= text.apply(preprocess_tweet)
+  #text1=text[0].values
   predictions = pipeline_nlp(text1)
-  data = [{'Texto': text1, 'Prediccion': prediction['label'], 'Probabilidad': prediction['score']} for prediction in predictions]
+  data = [{'Texto': text, 'Prediccion': prediction['label'], 'Probabilidad': prediction['score']} for prediction in predictions]
   # crea un DataFrame a partir de la lista de diccionarios
   df = pd.DataFrame(data)
-
-  Tweets =['Últimos '+ str(number_of_tweets)+' Tweets'+' de '+search_words]
-  df = pd.DataFrame(list(zip(text1, flat_predictions,probability)), columns = ['Tweets' , 'Prediccion','Probabilidad'])
-  
   df['Prediccion'] = np.where( df['Prediccion'] == 'LABEL_1', 'Sexista', 'No Sexista')
   
   tabla = st.table(df.reset_index(drop=True).head(30).style.applymap(color_survived, subset=['Prediccion']))