cardiffnlp/twitter-roberta-base-hate

from transformers import AutoModelForSequenceClassification
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
# postura/aborto, postura/ateísmo, postura/clima, postura/feminista, postura/hillary
task = 'hate'
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 = 'Buenas noches 😊'
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)}')

# Resultado:
# 1) not-hate 0.9168
# 2) hate 0.0832