Update app.py

app.py

@@ -104,10 +104,14 @@ def analizar_tweets(search_words, number_of_tweets ):
   text_list = text[0].tolist()
   result = []
   for text in text_list:
-      prediction = pipeline_nlp(text)
-      for predic in prediction:
-          etiqueta = {'Tweets': text,'Prediccion': predic['label'], 'Probabilidad': predic['score']}
-          result.append(etiqueta)
+      if (text.startswith('RT')):
+          continue
+      else:
+          prediction = pipeline_nlp(text)
+          for predic in prediction:
+              etiqueta = {'Tweets': text,'Prediccion': predic['label'], 'Probabilidad': predic['score']}
+              result.append(etiqueta)
+              
   df = pd.DataFrame(result)
   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']))
@@ -134,62 +138,31 @@ def analizar_frase(frase):
 def tweets_localidad(buscar_localidad):
   geolocator = Nominatim(user_agent="nombre_del_usuario")
   location = geolocator.geocode(buscar_localidad)
-  radius = "200km"
+  radius = "10km"
   tweets = api.search(lang="es",geocode=f"{location.latitude},{location.longitude},{radius}", count = 50)
-  #for tweet in tweets:
-  #  print(tweet.text)
-  tweet_list = [i.text for i in tweets]
+  tweet_list = [i.full_text for i in tweets]
   text= pd.DataFrame(tweet_list)
   text[0] = text[0].apply(preprocess_tweet)
-  text1=text[0].values
-  print(text1)
-  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
-
-    #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 50 Tweets'+' de '+ buscar_localidad]
-  df = pd.DataFrame(list(zip(text1, flat_predictions,probability)), columns = ['Tweets' , 'Prediccion','Probabilidad'])
+  text_list = text[0].tolist()
+  result = []
+  for text in text_list:
+      if (text.startswith('RT')):
+          continue
+      else:
+          prediction = pipeline_nlp(text)
+          for predic in prediction:
+              etiqueta = {'Tweets': text,'Prediccion': predic['label'], 'Probabilidad': predic['score']}
+              result.append(etiqueta)
   
-  df['Prediccion']= np.where(df['Prediccion']== 0, 'No Sexista', 'Sexista')
+  df = pd.DataFrame(result)
+  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']))
   #df['Tweets'] = df['Tweets'].str.replace('RT|@', '')
   #df_filtrado = df[df["Sexista"] == 'Sexista']
-  #df['Tweets'] = df['Tweets'].apply(lambda x: re.sub(r'[:;][-o^]?[)\]DpP3]|[(/\\]|[\U0001f600-\U0001f64f]|[\U0001f300-\U0001f5ff]|[\U0001f680-\U0001f6ff]|[\U0001f1e0-\U0001f1ff]','', x))
-  
+
   tabla = st.table(df.reset_index(drop=True).head(50).style.applymap(color_survived, subset=['Prediccion']))
     
-  df_sexista = df[df['Sexista']=="Sexista"]
+  df_sexista = df[df['Prediccion']=="Sexista"]
   df_no_sexista = df[df['Probabilidad'] > 0]
   sexista = len(df_sexista)
   no_sexista = len(df_no_sexista)
@@ -202,8 +175,10 @@ def tweets_localidad(buscar_localidad):
   plt.ylabel('Cantidad de tweets')
   plt.title('Cantidad de tweets sexistas y no sexistas')
   plt.show()
-
-  return df
+  st.pyplot()
+  st.set_option('deprecation.showPyplotGlobalUse', False)
+    
+  return tabla