Update app.py

app.py

@@ -133,13 +133,13 @@ def analizar_tweets(search_words, number_of_tweets ):
   
   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' , 'Sexista','Probabilidad'])
+  df = pd.DataFrame(list(zip(text1, flat_predictions,probability)), columns = ['Tweets' , 'Prediccion','Probabilidad'])
   
-  df['Sexista']= np.where(df['Sexista']== 0, 'No Sexista', 'Sexista')
+  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))
 
-  tabla = st.table(df.reset_index(drop=True).head(30).style.applymap(color_survived, subset=['Sexista']))
+  tabla = st.table(df.reset_index(drop=True).head(30).style.applymap(color_survived, subset=['Prediccion']))
 
   return tabla
 
@@ -199,17 +199,95 @@ def analizar_frase(frase):
     
   return tabla
 
-   
+def tweets_localidad(buscar_localidad):
+  location = geolocator.geocode(buscar_localidad)
+  radius = "200km"
+  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]
+  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'])
+  
+  df['Prediccion']= np.where(df['Prediccion']== 0, 'No Sexista', 'Sexista')
+  #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_no_sexista = df[df['Probabilidad'] > 0]
+  sexista = len(df_sexista)
+  no_sexista = len(df_no_sexista)
+
+  # Crear un gráfico de barras
+  labels = ['Sexista  ', ' No sexista']
+  counts = [sexista, no_sexista]
+  plt.bar(labels, counts)
+  plt.xlabel('Categoría')
+  plt.ylabel('Cantidad de tweets')
+  plt.title('Cantidad de tweets sexistas y no sexistas')
+  plt.show()
+
+  return df
+
+
+
+    
 def run():   
  with st.form("my_form"):
    col,buff1, buff2 = st.columns([2,2,1])
    st.write("Escoja una Opción")
-   search_words = col.text_input("Introduzca el termino o usuario para analizar y pulse el check correspondiente")
+   search_words = col.text_input("Introduzca el termino, usuario o localidad para analizar y pulse el check correspondiente")
    number_of_tweets = col.number_input('Introduzca número de tweets a analizar. Máximo 50', 0,50,10)
    termino=st.checkbox('Término')
    usuario=st.checkbox('Usuario')
+   localidad=st.checkbox('Localidad')
    submit_button = col.form_submit_button(label='Analizar')
-   error=False
+   error =False
+     
+     
    if submit_button:
             # Condición para el caso de que esten dos check seleccionados
             if ( termino == False and usuario == False):
@@ -225,6 +303,7 @@ def run():
                     
                 elif (usuario):
                     analizar_tweets(search_words,number_of_tweets)
-                  
+                elif (localidad):
+                    tweets_localidad(search_words)
 
 run()