Update app.py

app.py

@@ -1,75 +1,66 @@
 import streamlit as st
 import pandas as pd
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+import re
 import io
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
 
-# Load pre-trained model and tokenizer for text classification
-model_name = "TAgroup5/news-classification-model"
+# Load fine-tuned model and tokenizer
+model_name = "TAgroup5/daily-mirror-news-classifier"
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Initialize the text classification pipeline
+# Initialize pipelines
 text_classification_pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
-
-# Initialize the question answering pipeline
 qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
 
-# Streamlit App Layout
+# Streamlit App
 st.title("News Classification and Q&A")
 
-# Component 1: Text Classification Pipeline
+## ====================== Component 1: News Classification ====================== ##
 st.header("Classify News Articles")
-
-st.markdown("""
-    Upload a CSV file containing news articles, and the model will classify each article 
-    into one of the following categories: Business, Opinion, Political Gossip, Sports, or World News.
-""")
+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:
-    df = pd.read_csv(uploaded_file)
-    
+    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("The uploaded CSV file must have a 'content' column containing news excerpts.")
+        st.error("Error: The uploaded CSV must contain a 'content' column.")
     else:
-        st.write("Preview of the data:")
+        st.write("Preview of uploaded data:")
         st.dataframe(df.head())
 
-        # Preprocess the data and classify each article
+        # Preprocessing function
         def preprocess_text(text):
-            # Apply necessary preprocessing steps here (e.g., removing stopwords, special characters, etc.)
+            text = text.lower()  # Ensure consistent casing
+            text = re.sub(r'\s+', ' ', text)  # Remove extra spaces
+            text = re.sub(r'[^a-zA-Z0-9\s]', '', text)  # Remove special characters
             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'])
-        
-        # Show the results
+        df['class'] = df['processed_content'].apply(lambda x: text_classification_pipeline(x)[0]['label'] if x.strip() else "Unknown")
+
+        # Show results
         st.write("Classification Results:")
         st.dataframe(df[['content', 'class']])
 
-        # Provide an option to download the output as CSV
-        output = io.StringIO()
-        df.to_csv(output, index=False)
+        # 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="output.csv", mime="text/csv")
 
-
-# Component 2: Q&A Pipeline
+## ====================== Component 2: Q&A ====================== ##
 st.header("Ask a Question About the News")
-
-st.markdown("""
-    Type in a question, and the model will extract an answer from the provided news content.
-""")
+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 for the Q&A:", height=150)
 
-if question:
-    context = st.text_area("Provide the news article or content for the Q&A:", height=150)
-    
-    if context:
-        # Perform the question-answering task
-        result = qa_pipeline(question=question, context=context)
-        
-        st.write("Answer:", result['answer'])
-
+if question and context.strip():
+    result = qa_pipeline(question=question, context=context)
+    st.write("Answer:", result['answer'])