sexismdetector / app.py
robertou2's picture
Update app.py
6b7217a
raw
history blame
6.33 kB
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.title('Analisis de comentarios sexistas en Twitter con Tweepy and HuggingFace Transformers')
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')
def run():
with st.form(key='Introduzca Texto'):
search_words = st.text_input('Introduzca el termino o usuario para analizar y pulse el check ')
number_of_tweets = st.number_input('Introduzca número de twweets a analizar. Máximo 50', 0,50,10)
termino=st.checkbox('Término')
usuario=st.checkbox('Usuario')
submit_button = st.form_submit_button(label='Analizar')
if submit_button:
date_since = "2020-09-14"
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_words1,count=50)
#new_search = search_words + " -filter:retweets"
#tweets = tweepy.Cursor(api.search,q=new_search,lang="es",since=date_since).items(number_of_tweets)
#tweets =tw.Cursor(api.search_tweets,q=search_words).items(number_of_tweets)
#tweets =tw.Cursor(api.search_tweets,q=new_search,lang="es",since=date_since).items(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()