File size: 1,822 Bytes
29c5704 47f38d5 062e6a2 47f38d5 a11ee17 645c754 a11ee17 29c5704 7af1a44 a11ee17 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import gradio
import nltk
import pandas as pd
from transformers import pipeline
nltk.download('punkt')
summarizer = pipeline('summarization', model='t5-base')
# classifier_model_name = 'bhadresh-savani/distilbert-base-uncased-emotion'
# classifier_emotions = ['anger', 'disgust', 'fear', 'joy', 'sadness', 'surprise']
classifier_model_name = 'ProsusAI/finbert'
classifier_emotions = ['positive', 'neutral', 'negative']
classifier = pipeline('text-classification', model=classifier_model_name)
def find_emotional_sentences(text, emotions, threshold):
sentences_by_emotion = {}
for e in emotions:
sentences_by_emotion[e]=[]
sentences = nltk.sent_tokenize(text)
print(f'Document has {len(text)} characters and {len(sentences)} sentences.')
for s in sentences:
prediction = classifier(s)
if (prediction[0]['label']!='neutral' and prediction[0]['score']>threshold):
#print (f'Sentence #{sentences.index(s)}: {prediction} {s}')
sentences_by_emotion[prediction[0]['label']].append(s)
for e in emotions:
print(f'{e}: {len(sentences_by_emotion[e])} sentences')
return sentences_by_emotion
def summarize_sentences(sentences_by_emotion, min_length, max_length):
for k in sentences_by_emotion.keys():
if (len(sentences_by_emotion[k])!=0):
text = ' '.join(sentences_by_emotion[k])
summary = summarizer(text, min_length=min_length, max_length=max_length)
print(f"{k.upper()}: {summary[0]['summary_text']}\n")
def my_inference_function(text):
sentences_by_emotion = find_emotional_sentences(text, classifier_emotions, 0.7)
return sentences_by_emotion
gr_interface = gradio.Interface(
fn = my_inference_function,
inputs = "text",
outputs = "text"
)
gr_interface.launch()
|