Update app.py

app.py

@@ -98,53 +98,23 @@ 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
+      
   tweet_list = [i.text for i in tweets]
   text= pd.DataFrame(tweet_list)
   text[0] = text[0].apply(preprocess_tweet)
   text1=text[0].values
-  indices1=tokenizer.batch_encode_plus(text1.tolist(), max_length=128,add_special_tokens=True, return_attention_mask=True,pad_to_max_length=True,truncation=True)
-  input_ids1=indices1["input_ids"]
-  attention_masks1=indices1["attention_mask"]
-  prediction_inputs1= torch.tensor(input_ids1)
-  prediction_masks1 = torch.tensor(attention_masks1)
-  batch_size = 25
-  # Create the DataLoader.
-  prediction_data1 = TensorDataset(prediction_inputs1, prediction_masks1)
-  prediction_sampler1 = SequentialSampler(prediction_data1)
-  prediction_dataloader1 = DataLoader(prediction_data1, sampler=prediction_sampler1, batch_size=batch_size)
-  #print('Predicting labels for {:,} test sentences...'.format(len(prediction_inputs1)))
-  # Put model in evaluation mode
-  model.eval()
-  # Tracking variables 
-  predictions = []
-  for batch in prediction_dataloader1:
-    batch = tuple(t.to(device) for t in batch)
-    # Unpack the inputs from our dataloader
-    b_input_ids1, b_input_mask1 = batch
+  predictions = pipeline_nlp(text1)
+  data = [{'Texto': text1, 'Prediccion': prediction['label'], 'Probabilidad': prediction['score']} for prediction in predictions]
+  # crea un DataFrame a partir de la lista de diccionarios
+  df = pd.DataFrame(data)
 
-    #Telling the model not to compute or store gradients, saving memory and   # speeding up prediction
-    with torch.no_grad():
-      # Forward pass, calculate logit predictions
-      outputs1 = model(b_input_ids1, token_type_ids=None,attention_mask=b_input_mask1)
-    logits1 = outputs1[0]
-    # Move logits and labels to CPU
-    logits1 = logits1.detach().cpu().numpy()
-    # Store predictions and true labels
-    predictions.append(logits1)
-      
-  #flat_predictions = [item for sublist in predictions for item in sublist]
-  flat_predictions = [item for sublist in predictions for item in sublist]
-  
-  flat_predictions = np.argmax(flat_predictions, axis=1).flatten()
-  
-  probability = np.amax(logits1,axis=1).flatten()
   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']== 0, 'No Sexista', 'Sexista')
-  df['Tweets'] = df['Tweets'].str.replace('RT|@', '')   
-  #df['Tweets'] = df['Tweets'].apply(lambda x: re.sub(r'[:;][-o^]?[)\]DpP3]|[(/\\]|[\U0001f600-\U0001f64f]|[\U0001f300-\U0001f5ff]|[\U0001f680-\U0001f6ff]|[\U0001f1e0-\U0001f1ff]','', x))
-
+  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']))
 
   return tabla
@@ -155,14 +125,14 @@ def analizar_frase(frase):
   predictions = pipeline_nlp(frase)
 
   # convierte las predicciones en una lista de diccionarios
-  data = [{'text': frase, 'label': prediction['label'], 'score': prediction['score']} for prediction in predictions]
+  data = [{'Texto': frase, 'Prediccion': prediction['label'], 'Probabilidad': prediction['score']} for prediction in predictions]
   
   # crea un DataFrame a partir de la lista de diccionarios
   df = pd.DataFrame(data)
-  df['label'] = np.where( df['label'] == 'LABEL_1', 'Sexista', 'No Sexista')
+  df['Prediccion'] = np.where( df['Prediccion'] == 'LABEL_1', 'Sexista', 'No Sexista')
   # muestra el DataFrame
  #st.table(df.reset_index(drop=True).head(30).style.applymap(color_survived, subset=['Prediccion']))
-  tabla = st.table(df)
+  tabla = st.table(df.reset_index(drop=True).head(30).style.applymap(color_survived, subset=['Prediccion']))
   
   return tabla