Create streamlit_app.py

streamlit_app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import pandas as pd
+import torch
+from transformers import pipeline
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+import re
+import string
+
+# ====================== PREPROCESSING (Same as Task 2) ======================
+
+# ====================== LOAD FINE-TUNED MODEL ======================
+@st.cache_resource
+def load_model():
+    model_name = "Ginidu2003/Distilbert-Base-News-classifier"   # ← Your exact model name
+    return pipeline(
+        "text-classification",
+        model=model_name,
+        device=0 if torch.cuda.is_available() else -1
+    )
+
+classifier = load_model()
+
+# ====================== STREAMLIT APP ======================
+st.title("📰 Daily Mirror News Classifier")
+st.subheader("Classify news into Business, Opinion, Political Gossip, Sports, or World News")
+
+st.markdown("**Upload a CSV file** with a column named `content`")
+
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+if uploaded_file is not None:
+    df = pd.read_csv(uploaded_file)
+    
+    st.write("### Preview of uploaded data")
+    st.dataframe(df.head())
+
+    if 'content' not in df.columns:
+        st.error("Your CSV must have a column named 'content'")
+    else:
+        with st.spinner("Preprocessing and classifying..."):
+            # Apply same preprocessing as Task 2
+            #df['clean_content'] = df['content'].apply(preprocess_text)
+            
+            # Classify
+            predictions = []
+            for text in df['clean_content']:
+                if text.strip() == "":
+                    predictions.append("Unknown")
+                else:
+                    result = classifier(text)[0]
+                    predictions.append(result['label'])
+            
+            df['class'] = predictions
+            
+            # Drop helper column
+            #df = df.drop(columns=['clean_content'], errors='ignore')
+            
+            st.success("✅ Classification completed!")
+            st.write("### Preview of classified data")
+            st.dataframe(df.head())
+
+            # Download button
+            csv = df.to_csv(index=False).encode('utf-8')
+            st.download_button(
+                label="📥 Download output.csv",
+                data=csv,
+                file_name="output.csv",
+                mime="text/csv"
+            )
+
+st.caption("Built for Text Analytics Assignment - Section 02")