How to get all 3 labels' sentiment from finbert instead of the most likely label's?

Question

I'm using bert to do sentiment analysis. I previous used cardiffnlp's twitter-roberta-base-sentiment, https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment.

It gives the the usage on its page.

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

# Preprocess text (username and link placeholders)
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)

# Tasks:
# emoji, emotion, hate, irony, offensive, sentiment
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary

task='sentiment'
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"

tokenizer = AutoTokenizer.from_pretrained(MODEL)

# download label mapping
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)

It shows sentiments of all three labels, positive, neutral and negative.

However, I'm now trying to use Finbert from ProsusAI to do sentiment analysis https://huggingface.co/ProsusAI/finbert. It doesn't give me its usage on its page. So I'm following this tutorial https://towardsdatascience.com/effortless-nlp-using-pre-trained-hugging-face-pipelines-with-just-3-lines-of-code-a4788d95754f.

My code is

from transformers import pipeline
classifier = pipeline('sentiment-analysis', model='ProsusAI/finbert')
classifier('Stocks rallied and the British pound gained.')

However, the result is [{'label': 'positive', 'score': 0.8983612656593323}]. It only shows the sentiment of the most likely label's (positive). But I need all three labels' sentiment (positive, neutral and negative). How should I use it?

Answer 1

You can get the scores for all labels as follows:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import scipy

tokenizer = AutoTokenizer.from_pretrained("ProsusAI/finbert")
model = AutoModelForSequenceClassification.from_pretrained("ProsusAI/finbert")

inputs = tokenizer("Stocks rallied and the British pound gained.", return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits
scores = {k: v for k, v in zip(model.config.id2label.values(), scipy.special.softmax(logits.numpy().squeeze()))}
scores
# {'negative': 0.034473564, 'neutral': 0.067165166, 'positive': 0.8983614}