Spaces:
Runtime error
Runtime error
File size: 8,851 Bytes
a671d2f 5d9538c a671d2f 88e5a9f 99a9eeb 3a25ba9 0828889 824eea0 0828889 4a941bb c1547f4 bdcf72a 3a25ba9 3150a10 4fb044a 1209674 6f4b2a0 3a25ba9 67a232f 1209674 c251eb1 deb5581 824eea0 1209674 b7e1033 6f4b2a0 baa3c55 154f604 553b7d8 b7e1033 824eea0 b7e1033 c1547f4 a671d2f 7c18751 6b7217a c1547f4 4c18796 c1547f4 6b7217a c1547f4 7c18751 8f9e58e c1547f4 adef534 c1547f4 adef534 c1547f4 adef534 c1547f4 4c18796 c1547f4 99a9eeb 0828889 5872984 0828889 99a9eeb a671d2f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
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 &, <, > with &,<,> respectively
text=text.replace(r'&?',r'and')
text=text.replace(r'<',r'<')
text=text.replace(r'>',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
def highlight_survived(s):
return ['background-color: red']*len(s) if (s.Sexista == 1) else ['background-color: green']*len(s)
def color_survived(val):
color = 'red' if val=='Sexista' else 'white'
return f'background-color: {color}'
st.set_page_config(layout="wide")
st.markdown('<style>body{background-color: Blue;}</style>',unsafe_allow_html=True)
#background-color: Blue;
colT1,colT2 = st.columns([2,8])
with colT2:
#st.title('Analisis de comentarios sexistas en Twitter')
st.markdown(""" <style> .font {
font-size:40px ; font-family: 'Cooper Black'; color: #FF9633;}
</style> """, unsafe_allow_html=True)
st.markdown('<p class="font">Análisis de comentarios sexistas en Twitter</p>', unsafe_allow_html=True)
st.markdown(""" <style> .font1 {
font-size:28px ; font-family: 'Times New Roman'; color: #8d33ff;}
</style> """, unsafe_allow_html=True)
st.markdown('<p class="font1">Objetivo 5 de los ODS. Lograr la igualdad entre los géneros y empoderar a todas las mujeres y las niñas</p>', unsafe_allow_html=True)
#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=200)
st.markdown(""" <style> .font2 {
font-size:16px ; font-family: 'Times New Roman'; color: #3358ff;}
</style> """, unsafe_allow_html=True)
st.markdown('<p class="font2">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.La finalidad del proyecto, es en línea con el Objetivo 5 de los ODS, eliminar todas las formas de violencia contra todas las mujeres y las niñas en los ámbitos público y privado, incluidas la trata y la explotación sexual y otros tipos de explotación. Los comentarios sexistas son una forma de violencia contra la mujer con está aplicación puede ayudar a hacer un estudio sistemático de la misma.</p>',unsafe_allow_html=True)
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 correspondiente")
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,tweet_mode="extended").items(number_of_tweets)
elif (usuario):
tweets = api.user_timeline(screen_name = search_words,count=number_of_tweets,tweet_mode="extended")
tweet_list = [i.full_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 =['Últimos '+ str(number_of_tweets)+' Tweets'+' de '+search_words, 'Sexista'])
df['Sexista']= np.where(df['Sexista']== 0, 'No Sexista', 'Sexista')
st.table(df.reset_index(drop=True).head(50).style.applymap(color_survived, subset=['Sexista']))
#st.dataframe(df.style.apply(highlight_survived, axis=1))
#st.table(df)
#st.write(df)
run() |