cardiffnlp/twitter-roberta-base-irony

from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer
import numpy as np
from scipy.special import softmax
import csv
import urllib.request

# Preprocesar texto (placeholders de nombres de usuario y enlaces)
def preprocess(text):
  new_text = []
  for t in text.split(' '):
    t = '@user' if t.startswith('@') and len(t) > 1 else t
    t = 'http' if t.startswith('http') else t
    new_text.append(t)
  return ' '.join(new_text)

# Tareas:
# emoji, emoción, odio, ironía, ofensivo, sentimiento
# posición/aborto, posición/ateísmo, posición/clima, posición/feminista, posición/hillary
task='irony'
MODEL = f'cardiffnlp/twitter-roberta-base-{task}'

tokenizer = AutoTokenizer.from_pretrained(MODEL)

# Descargar mapeo de etiquetas
labels=[]
mapping_link = f'https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt'
with urllib.request.urlopen(mapping_link) as f:
  html = f.read().decode('utf-8').split('\n')
  csvreader = csv.reader(html, delimiter='\t')
  labels = [row[1] for row in csvreader if len(row) > 1]

# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
model.save_pretrained(MODEL)

text = 'Genial, se rompió el primer día...'
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)

ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
  l = labels[ranking[i]]
  s = scores[ranking[i]]
  print(f'{i+1}) {l} {np.round(float(s), 4)}')

Output:
1) ironía  0.914
2) no_ironia  0.086