File size: 2,814 Bytes
e19c3a2 b6c046c e19c3a2 79687df e19c3a2 9f7bad0 e19c3a2 de56a53 e19c3a2 de56a53 e19c3a2 b6c046c e19c3a2 b6c046c e19c3a2 d2c0a74 e19c3a2 c7770a0 9f7bad0 de56a53 9f7bad0 c7770a0 e19c3a2 |
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 71 72 73 74 |
import streamlit as st
from transformers import pipeline
import re
# Function to remove strange characters from the input text
def clean_text(text):
# Only keep alphanumeric characters and some punctuation
return re.sub(r"[^a-zA-Z0-9\s.,!?']", "", text)
# Load the text summarization pipeline
try:
summarizer = pipeline("summarization", model="syndi-models/titlewave-t5-base")
summarizer_loaded = True
except ValueError as e:
st.error(f"Error loading summarization model: {e}")
summarizer_loaded = False
# Load the Question classification pipeline
model_name = "Emily666666/bert-base-cased-news-category-test"
try:
classifier = pipeline("text-classification", model=model_name, return_all_scores=True)
classifier_loaded = True
except ValueError as e:
st.error(f"Error loading classification model: {e}")
classifier_loaded = False
# Dictionary to map numerical labels to real labels
label_mapping = {
0: "Society & Culture",
1: "Science & Mathematics",
2: "Health",
3: "Education & Reference",
4: "Computers & Internet",
5: "Sports",
6: "Business & Finance",
7: "Entertainment & Music",
8: "Family & Relationships",
9: "Politics & Government"
}
# Streamlit app title
st.title("Question Rephrase and Classification")
# Input text for summarization and classification
text_input = st.text_area("Enter long question to rephrase and classify:", "")
if st.button("Process"):
if summarizer_loaded and classifier_loaded and text_input:
try:
# Clean the text input
cleaned_text = clean_text(text_input)
# Perform text summarization
summary = summarizer(cleaned_text, max_length=130, min_length=30, do_sample=False)
summarized_text = summary[0]['summary_text']
except Exception as e:
st.error(f"Error during summarization: {e}")
summarized_text = ""
if summarized_text:
try:
# Perform question classification on the summarized text
results = classifier(summarized_text)[0]
# Find the category with the highest score
max_score = max(results, key=lambda x: x['score'])
predicted_label_index = int(max_score['label'].split('_')[-1]) # Assuming labels are like "LABEL_0", "LABEL_1", etc.
predicted_label = label_mapping[predicted_label_index]
st.write("Rephrased Text:", summarized_text)
st.write("Category:", predicted_label)
st.write("Score:", max_score['score'])
except Exception as e:
st.error(f"Error during classification: {e}")
else:
st.warning("Please enter text to process and ensure both models are loaded.") |