I am using the following Hugging Face transformer code.
from transformers import pipeline
classifier = pipeline("sentiment-analysis",model='bhadresh-savani/distilbert-base-uncased-emotion', return_all_scores=True)
prediction = classifier("I love using transformers. The best part is wide range of support and its easy to use", )
print(prediction)
The result is:
[[{'label': 'sadness', 'score': 0.010154823772609234}, {'label': 'joy', 'score': 0.5637667179107666}, {'label': 'love', 'score': 0.4066571295261383}, {'label': 'anger', 'score': 0.01734882965683937}, {'label': 'fear', 'score': 0.0011737244203686714}, {'label': 'surprise', 'score': 0.0008987095206975937}]]
I would like to know how can I get the highest score together with the label, but I am not sure how to iterate this object or if there is an easy way with expressions.
You are using a TextClassificationPipeline. When you __call__ the pipeline you get a list of dict if top_k=0 or a list of list of dict if top_k=None as per the documentation.
You can either set top_k to 0 (the default value) and then access the values you want - in this case you will only get the score and text of the highest scoring label:
from transformers import pipeline
classifier = pipeline("sentiment-analysis",model='bhadresh-savani/distilbert-base-uncased-emotion', top_k=0)
prediction = classifier("I love using transformers. The best part is wide range of support and its easy to use")
print(prediction[0]["label"], prediction[0]["score"])
Or, if you want the scores for all labels, and then access only the highest scoring label (top_k=0):
from transformers import pipeline
classifier = pipeline("sentiment-analysis",model='bhadresh-savani/distilbert-base-uncased-emotion', top_k=None)
prediction = classifier("I love using transformers. The best part is wide range of support and its easy to use")
print(max(prediction[0], key=lambda k: k["score"]))