cardiffnlp / twitter-xlm-roberta-base-sentiment

Ejemplo de Pipeline

from transformers import pipeline
model_path = "cardiffnlp/twitter-xlm-roberta-base-sentiment"
sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
sentiment_task("T'estimo!")

# Resultado: [{'label': 'Positive', 'score': 0.6600581407546997}]

Ejemplo completo de clasificación

from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
import numpy as np
from scipy.special import softmax

# Procesamiento del 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)

MODEL = f"cardiffnlp/twitter-xlm-roberta-base-sentiment"

tokenizer = AutoTokenizer.from_pretrained(MODEL)
config = AutoConfig.from_pretrained(MODEL)

# 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)

# Imprimir etiquetas y puntuaciones
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
    l = config.id2label[ranking[i]]
    s = scores[ranking[i]]
    print(f"{i+1}) {l} {np.round(float(s), 4)}")

# Resultado:
# 1) Positive 0.7673
# 2) Neutral 0.2015
# 3) Negative 0.0313