Spaces:
Runtime error
Runtime error
File size: 3,181 Bytes
51caef2 ccc3eca 51caef2 ccc3eca c1ddc17 ccc3eca c1ddc17 ccc3eca 84b6cc7 ccc3eca 84b6cc7 ccc3eca 84b6cc7 ccc3eca e18cd1b ccc3eca e18cd1b ccc3eca e18cd1b ccc3eca d846800 ccc3eca e18cd1b |
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 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import streamlit as st
from transformers import pipeline, AutoModelForSequenceClassification, AutoModelForSeq2SeqLM, AutoTokenizer
class CombinedModel:
def __init__(self, classifier_model, classifier_tokenizer, summarizer_model, summarizer_tokenizer):
self.classifier_model = classifier_model
self.classifier_tokenizer = classifier_tokenizer
self.summarizer_model = summarizer_model
self.summarizer_tokenizer = summarizer_tokenizer
def classify_and_summarize(self, text):
classifier = pipeline("text-classification", model=self.classifier_model, tokenizer=self.classifier_tokenizer, return_all_scores=True)
summarizer = pipeline("summarization", model=self.summarizer_model, tokenizer=self.summarizer_tokenizer)
# Classify the text
classification_results = classifier(text)[0]
# Determine the label with the highest score
max_score = float('-inf')
max_label = ''
for result in classification_results:
if result['score'] > max_score:
max_score = result['score']
max_label = result['label']
# Summarize the text
summary_results = summarizer(text, max_length=50, min_length=25, do_sample=False)
return max_label, max_score, summary_results[0]['summary_text']
@classmethod
def from_pretrained(cls, classifier_path, summarizer_path):
classifier_model = AutoModelForSequenceClassification.from_pretrained(classifier_path)
classifier_tokenizer = AutoTokenizer.from_pretrained(classifier_path)
summarizer_model = AutoModelForSeq2SeqLM.from_pretrained(summarizer_path)
summarizer_tokenizer = AutoTokenizer.from_pretrained(summarizer_path)
return cls(classifier_model, classifier_tokenizer, summarizer_model, summarizer_tokenizer)
# Load the combined model
classifier_path = "lqqqqqqqqq/FinetunedModelGr9"
summarizer_path = "lqqqqqqqqq/SummarizeModelGr9"
combined_model = CombinedModel.from_pretrained(classifier_path, summarizer_path)
# Streamlit application title
st.title("Twitter Text Classification and Summarization")
st.write("Classification for 3 labels: negative, neutral, positive")
st.markdown("Please enter at least 50 words & more than 4 sentences for better summarization")
# Text input for user to enter the text to classify
texts_input = st.text_area("Enter the texts to classify and summarize (one text per line)", "")
# Perform text classification and summarization when the user clicks the "Classify" button
if st.button("Classify & Summarize"):
texts = texts_input.split('\n')
for text in texts:
text = text.strip()
if text: # Check if text is not empty
# Classify and summarize the input text
label, score, summary = combined_model.classify_and_summarize(text)
# Display the results
st.write("Text:", text)
st.write("Label:", label)
st.write("Score:", score)
st.write("Summary:", summary)
st.write("---")
else:
st.write("Please enter some text(more than 4 sentences) to classify and summarize.")
|