Spaces:
Sleeping
Sleeping
File size: 4,842 Bytes
246133f 5cdc45c 237a63b 5cdc45c ec68c76 73c0f99 e245042 2ec8bb5 3412bc8 73c0f99 3412bc8 2ec8bb5 3412bc8 e245042 3412bc8 e245042 |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import streamlit as st
import pandas as pd
import re
import io
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
from transformers import AutoModelForQuestionAnswering
# Load fine-tuned models and tokenizers for both functions
model_name_classification = "TAgroup5/news-classification-model"
model = AutoModelForSequenceClassification.from_pretrained(model_name_classification)
tokenizer = AutoTokenizer.from_pretrained(model_name_classification)
model_name_qa = "distilbert-base-cased-distilled-squad"
model_qa = AutoModelForQuestionAnswering.from_pretrained(model_name_qa)
tokenizer_qa = AutoTokenizer.from_pretrained(model_name_qa)
# Initialize pipelines
from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
model_name = "distilbert-base-cased-distilled-squad" # Example model
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
text_classification_pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
qa_pipeline = pipeline("question-answering", model=model)
# Streamlit App
st.set_page_config(page_title="News Classification & Q&A", page_icon="📰", layout="wide")
st.markdown(
"""
<style>
body {background-color: #f4f4f4;}
.title {text-align: center; font-size: 36px; font-weight: bold; color: #ff4b4b;}
.subheader {font-size: 24px; color: #333; margin-bottom: 20px; text-align: right;}
.stTextInput>div>div>input {border-radius: 10px;}
.stTextArea>div>div>textarea {border-radius: 10px;}
.stButton>button {border-radius: 10px; background-color: #ff4b4b; color: white; font-weight: bold;}
</style>
""",
unsafe_allow_html=True,
)
st.markdown('<h1 class="title">📰 News Classification & Q&A App</h1>', unsafe_allow_html=True)
col1, col2 = st.columns([2, 1])
with col2:
# ====================== Component 1: News Classification ====================== #
st.markdown('<h2 class="subheader">📌 Classify News Articles</h2>', unsafe_allow_html=True)
st.markdown("Upload a CSV file with a 'content' column to classify news into categories.")
uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
if uploaded_file is not None:
try:
df = pd.read_csv(uploaded_file, encoding="utf-8") # Handle encoding issues
except UnicodeDecodeError:
df = pd.read_csv(uploaded_file, encoding="ISO-8859-1")
if 'content' not in df.columns:
st.error("❌ Error: The uploaded CSV must contain a 'content' column.")
else:
st.success("✅ File successfully uploaded!")
st.write("Preview of uploaded data:")
st.dataframe(df.head())
# Preprocessing function to clean the text
def preprocess_text(text):
text = text.lower() # Convert to lowercase
text = re.sub(r'\s+', ' ', text) # Remove extra spaces
text = re.sub(r'[^a-z\s]', '', text) # Remove special characters & numbers
return text
# Apply preprocessing and classification
df['processed_content'] = df['content'].apply(preprocess_text)
df['class'] = df['processed_content'].apply(lambda x: text_classification_pipeline(x)[0]['label'] if x.strip() else "Unknown")
# Show results
st.markdown("### 🔹 Classification Results:")
st.dataframe(df[['content', 'class']])
# Provide CSV download
output = io.BytesIO()
df.to_csv(output, index=False, encoding="utf-8-sig")
st.download_button(label="⬇️ Download classified news", data=output.getvalue(), file_name="classified_news.csv", mime="text/csv")
# ====================== Component 2: Q&A ====================== #
st.markdown('<h2 class="subheader">❓ Ask a Question About the News</h2>', unsafe_allow_html=True)
st.markdown("Enter a question and provide a news article to get an answer.")
question = st.text_input("🔍 Ask a question:")
context = st.text_area("📝 Provide the news article or content:", height=150)
if question and context.strip():
model_name_qa = "distilbert-base-uncased-distilled-squad"
qa_pipeline = pipeline("question-answering", model=model_name_qa, tokenizer=model_name_qa)
result = qa_pipeline(question=question, context=context)
# Display Answer
if 'answer' in result and result['answer']:
st.markdown(f"### ✅ Answer: {result['answer']}")
else:
st.markdown("### ❌ No answer found in the provided content.")
|