cardiffnlp/twitter-roberta-base-offensive

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

# Preprocesamiento de texto (placeholders de nombre de usuario y enlace)
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, emotion, hate, irony, offensive, sentiment
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
task='offensive'
MODEL = f'cardiffnlp/twitter-roberta-base-{task}'

tokenizer = AutoTokenizer.from_pretrained(MODEL)

# descarga de 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 = 'Good night 😊'
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)

# # TF
# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)
# model.save_pretrained(MODEL)

# text = 'Good night 😊'
# encoded_input = tokenizer(text, return_tensors='tf')
# output = model(encoded_input)
# scores = output[0][0].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) not-offensive 0.9073
2) offensive 0.0927