app.py

import tweepy as tw
import streamlit as st
import pandas as pd
import torch
import numpy as np
import re


from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
from transformers import AutoTokenizer, AutoModelForSequenceClassification,AdamW
tokenizer = AutoTokenizer.from_pretrained('hackathon-pln-es/twitter_sexismo-finetuned-exist2021-metwo')
model = AutoModelForSequenceClassification.from_pretrained("hackathon-pln-es/twitter_sexismo-finetuned-exist2021-metwo")

import torch
if torch.cuda.is_available():  
    device = torch.device("cuda")
    print('I will use the GPU:', torch.cuda.get_device_name(0))
    
else:
    print('No GPU available, using the CPU instead.')
    device = torch.device("cpu")

consumer_key = st.secrets["consumer_key"]
consumer_secret = st.secrets["consumer_secret"]
access_token = st.secrets["access_token"]
access_token_secret = st.secrets["access_token_secret"]
auth = tw.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tw.API(auth, wait_on_rate_limit=True)

def preprocess(text):
    text=text.lower()
    # remove hyperlinks
    text = re.sub(r'https?:\/\/.*[\r\n]*', '', text)
    text = re.sub(r'http?:\/\/.*[\r\n]*', '', text)
    #Replace &amp, &lt, &gt with &,<,> respectively
    text=text.replace(r'&amp;?',r'and')
    text=text.replace(r'&lt;',r'<')
    text=text.replace(r'&gt;',r'>')
    #remove hashtag sign
    #text=re.sub(r"#","",text)   
    #remove mentions
    text = re.sub(r"(?:\@)\w+", '', text)
    #text=re.sub(r"@","",text)
    #remove non ascii chars
    text=text.encode("ascii",errors="ignore").decode()
    #remove some puncts (except . ! ?)
    text=re.sub(r'[:"#$%&\*+,-/:;<=>@\\^_`{|}~]+','',text)
    text=re.sub(r'[!]+','!',text)
    text=re.sub(r'[?]+','?',text)
    text=re.sub(r'[.]+','.',text)
    text=re.sub(r"'","",text)
    text=re.sub(r"\(","",text)
    text=re.sub(r"\)","",text)
    text=" ".join(text.split())
    return text


st.set_page_config(layout="wide")
colT1,colT2 = st.columns([2,7])
with colT2:
    st.title('Analisis de comentarios sexistas en Twitter') 
    st.header('Objetivo 5 de los ODS, Lograr la igualdad entre los géneros y empoderar a todas las mujeres y las niñas')
with colT1:
    st.image("https://upload.wikimedia.org/wikipedia/commons/thumb/c/c7/Sustainable_Development_Goal-es-13.jpg/1200px-Sustainable_Development_Goal-es-13.jpg",width=100)
st.markdown('Esta app utiliza tweepy para descargar tweets de twitter en base a la información de entrada y procesa los tweets usando transformers de HuggingFace para detectar comentarios sexistas. El resultado y los tweets correspondientes se almacenan en un dataframe para mostrarlo que es lo que se ve como resultado')
st.markdown('La finalidad del proyecto es en línea con el Objetivo 5 de los ODS, Lograr la igualdad entre los géneros y empoderar a todas las mujeres y las niñas.Una vez analizados los tweets, los que resulten sexistas se pueden contestar para intentar reeducar a las personas que bien por su educación o circustancias presenten un comportamiento contrario al del Objetivo 5 antes mencionado. Igualmente en casos más graves se pueden realizar otras acciones')


def run():
    with st.form(key='Introduzca Texto'):
        col,buff1, buff2 = st.columns([2,2,1])
        #col.text_input('smaller text window:')
        search_words = col.text_input('Introduzca el termino o usuario para analizar y pulse el check ')
        number_of_tweets = col.number_input('Introduzca número de twweets a analizar. Máximo 50', 0,50,10)
        termino=st.checkbox('Término')
        usuario=st.checkbox('Usuario')
        submit_button = col.form_submit_button(label='Analizar')
        error=False
        if submit_button:
            date_since = "2020-09-14"
            if ( termino == False and usuario == False):
                st.text('Error no se ha seleccionado ningun check')
                error=True
            elif ( termino == True and usuario == True):
                st.text('Error se han seleccionado los dos check')
                error=True
            
           
            if (error == False):
                if (termino):
                    new_search = search_words + " -filter:retweets"
                    tweets =tw.Cursor(api.search_tweets,q=new_search,lang="es",since=date_since).items(number_of_tweets)
                elif (usuario):
                    tweets = api.user_timeline(screen_name = search_words,count=number_of_tweets)
                
                tweet_list = [i.text for i in tweets]
                #tweet_list = [strip_undesired_chars(i.text) for i in tweets]
                text= pd.DataFrame(tweet_list)
                text[0] = text[0].apply(preprocess)
                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)
                # Set the batch size.  
                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 = []
                # Predict 
                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 = np.argmax(flat_predictions, axis=1).flatten()#p = [i for i in classifier(tweet_list)]
                df = pd.DataFrame(list(zip(tweet_list, flat_predictions)),columns =['Latest'+str(number_of_tweets)+'Tweets'+' on '+search_words, 'Sexista'])
                df['Sexista']= np.where(df['Sexista']== 0, 'No Sexista', 'Sexista')
                st.table(df)
            #st.write(df)
run()