Create app.py

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+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 ======================
+nltk.download('stopwords', quiet=True)
+nltk.download('wordnet', quiet=True)
+nltk.download('punkt', quiet=True)
+
+stop_words = set(stopwords.words('english'))
+lemmatizer = WordNetLemmatizer()
+
+def preprocess_text(text):
+    if not isinstance(text, str):
+        return ""
+    text = text.lower()
+    text = re.sub(f'[{string.punctuation}]', ' ', text)
+    text = re.sub(r'[^a-z\s]', ' ', text)
+    tokens = nltk.word_tokenize(text)
+    tokens = [word for word in tokens if word not in stop_words]
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    return ' '.join(tokens)
+
+# ====================== LOAD YOUR FINE-TUNED MODEL ======================
+model_name = "Ginidu2003/Distilbert-Base-News-classifier"   # ← Change if your model name is different
+
+@torch.no_grad()
+def classify_csv(file):
+    try:
+        df = pd.read_csv(file)
+        
+        if 'content' not in df.columns:
+            return "Error: CSV must have a column named 'content'", None
+        
+        # Preprocess
+        df['clean_content'] = df['content'].apply(preprocess_text)
+        
+        # Load classifier
+        classifier = pipeline("text-classification", model=model_name, device=-1)
+        
+        # Predict
+        predictions = []
+        for text in df['clean_content']:
+            if not text.strip():
+                predictions.append("Unknown")
+            else:
+                result = classifier(text)[0]
+                predictions.append(result['label'])
+        
+        df['class'] = predictions
+        df = df.drop(columns=['clean_content'], errors='ignore')
+        
+        # Save output
+        output_file = "output.csv"
+        df.to_csv(output_file, index=False)
+        
+        return f"✅ Success! Classified {len(df)} rows", output_file
+        
+    except Exception as e:
+        return f"❌ Error: {str(e)}", None
+
+# ====================== GRADIO INTERFACE ======================
+with gr.Blocks(title="Daily Mirror News Classifier") as demo:
+    gr.Markdown("# 📰 Daily Mirror News Classifier")
+    gr.Markdown("### Classify news into Business, Opinion, Political Gossip, Sports, or World News")
+    
+    with gr.Row():
+        file_input = gr.File(label="Upload CSV file", file_types=[".csv"])
+    
+    classify_btn = gr.Button("🚀 Classify News", variant="primary")
+    
+    output_text = gr.Textbox(label="Status")
+    output_file = gr.File(label="Download output.csv")
+    
+    classify_btn.click(
+        fn=classify_csv,
+        inputs=file_input,
+        outputs=[output_text, output_file]
+    )
+
+    gr.Markdown("Built for Text Analytics Assignment - Section 02")
+
+demo.launch()