Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import gradio as gr
 import pandas as pd
 import torch
@@ -11,12 +10,10 @@ import string
 import matplotlib.pyplot as plt
 
 # ====================== NLTK SETUP ======================
-
 nltk.download('wordnet', quiet=True)
 nltk.download('punkt', quiet=True)
 nltk.download('punkt_tab', quiet=True)
 
-
 lemmatizer = WordNetLemmatizer()
 
 def preprocess_text(text):
@@ -24,17 +21,39 @@ def preprocess_text(text):
         return ""
     text = text.lower()
     punct_to_remove = string.punctuation.replace("'","").replace('"',"").replace("$","").replace("%","").replace("?","")
-    text = re.sub(f"[{punct_to_remove}]", " ", text)# Remove punctuation except: ' " $ % ?
+    text = re.sub(f"[{punct_to_remove}]", " ", text)
     tokens = nltk.word_tokenize(text)
-    tokens = [word for word in tokens]
     tokens = [lemmatizer.lemmatize(word) for word in tokens]
     return ' '.join(tokens)
 
-
 classifier_model = "Ginidu2003/Distilbert-Base-News-classifier"
 
+# ====================== COLORED BAR CHART ======================
+def create_colored_bar_chart(category_counts):
+    if category_counts is None or len(category_counts) == 0:
+        fig, ax = plt.subplots()
+        ax.text(0.5, 0.5, "No data available", ha='center', va='center')
+        return fig
+
+    categories = category_counts["Category"]
+    counts = category_counts["Count"]
 
+    colors = ['#FF6B6B', '#4ECDC4', '#45B7D1', '#96CEB4', '#FFEEAD']
 
+    fig, ax = plt.subplots(figsize=(10, 6))
+    bars = ax.bar(categories, counts, color=colors)
+
+    for bar in bars:
+        height = bar.get_height()
+        ax.text(bar.get_x() + bar.get_width()/2, height + 0.5,
+                str(int(height)), ha='center', va='bottom', fontsize=12, fontweight='bold')
+
+    ax.set_title("Category Distribution Across 5 Classes", fontsize=16, fontweight='bold')
+    ax.set_xlabel("Category", fontsize=12)
+    ax.set_ylabel("Count", fontsize=12)
+    plt.xticks(rotation=15)
+    plt.tight_layout()
+    return fig
 
 # ====================== CLASSIFICATION FUNCTION ======================
 @torch.no_grad()
@@ -42,7 +61,7 @@ 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
+            return "Error: CSV must have a column named 'content'", None, None
         
         df['clean_content'] = df['content'].apply(preprocess_text)
         
@@ -61,116 +80,106 @@ def classify_csv(file):
         
         output_file = "output.csv"
         df.to_csv(output_file, index=False)
-
-        # Count categories
+        
         category_counts = df['class'].value_counts().reset_index()
         category_counts.columns = ["Category", "Count"]
-
-        # Create colored bar chart
+        
         fig = create_colored_bar_chart(category_counts)
         
         return f"✅ Success! Classified {len(df)} rows", output_file, fig
     except Exception as e:
         return f"❌ Error: {str(e)}", None, None
 
-# ====================== COLORED BAR CHART ======================
-def create_colored_bar_chart(category_counts):
-    if category_counts is None or len(category_counts) == 0:
-        fig, ax = plt.subplots()
-        ax.text(0.5, 0.5, "No data available", ha='center', va='center')
-        return fig
-
-    categories = category_counts["Category"]
-    counts = category_counts["Count"]
-
-    # Different attractive colors for each category
-    colors = ['#FF6B6B', '#4ECDC4', '#45B7D1', '#96CEB4', '#FFEEAD']
-
-    fig, ax = plt.subplots(figsize=(10, 6))
-    bars = ax.bar(categories, counts, color=colors)
-
-    # Add count numbers on top of bars
-    for bar in bars:
-        height = bar.get_height()
-        ax.text(bar.get_x() + bar.get_width()/2, height + 0.5, 
-                str(int(height)), ha='center', va='bottom', fontsize=12, fontweight='bold')
-
-    ax.set_title("Category Distribution Across 5 Classes", fontsize=14, fontweight='bold')
-    ax.set_xlabel("Category")
-    ax.set_ylabel("Count")
-    plt.xticks(rotation=15)
-    plt.tight_layout()
-    return fig
-        
-        
-
 # ====================== Q&A FUNCTION ======================
 from transformers import AutoTokenizer, AutoModelForQuestionAnswering
-
 qa_tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2")
 qa_model = AutoModelForQuestionAnswering.from_pretrained("deepset/roberta-base-squad2")
+
 def answer_question(news_content, question):
     if not news_content.strip() or not question.strip():
         return "Please enter both news content and a question."
-    
     try:
         inputs = qa_tokenizer(question, news_content, return_tensors="pt", truncation=True, max_length=512)
-        
         with torch.no_grad():
             outputs = qa_model(**inputs)
         
         start_idx = torch.argmax(outputs.start_logits)
         end_idx = torch.argmax(outputs.end_logits) + 1
         
-        # Clean answer - remove question repetition and special tokens
-        answer = qa_tokenizer.decode(inputs.input_ids[0][start_idx:end_idx], 
-                                    skip_special_tokens=True, 
+        answer = qa_tokenizer.decode(inputs.input_ids[0][start_idx:end_idx],
+                                    skip_special_tokens=True,
                                     clean_up_tokenization_spaces=True)
         
         confidence = torch.max(torch.softmax(outputs.start_logits, dim=1)).item()
         
         return f"**Answer:** {answer.strip()}\n\n**Confidence:** {confidence:.2%}"
-    
     except Exception as e:
         return f"Error: {str(e)}"
 
-# ====================== GRADIO INTERFACE ======================
-with gr.Blocks(title=" News Classifier & Question Answering App") as demo:
+# ====================== BEAUTIFUL GRADIO INTERFACE ======================
+with gr.Blocks(
+    title="English News Classifier",
+    theme=gr.themes.Soft(),           # Beautiful modern theme
+    css="""
+    .gradio-container {max-width: 1100px; margin: auto;}
+    h1 {font-size: 2.5rem; text-align: center;}
+    .tab-label {font-size: 1.1rem; font-weight: 600;}
+    """
+) as demo:
+
     gr.Markdown("# 📰 English News Classifier")
-    #gr.Markdown("### Section 02 - Text Analytics Assignment")
+    gr.Markdown("### Intelligent News Analysis Tool | Daily Mirror Sri Lanka")
 
     with gr.Tabs():
+        # ====================== CLASSIFICATION TAB ======================
         with gr.Tab("📊 News Classification"):
-            gr.Markdown("Upload CSV with `content` column")
-            file_input = gr.File(label="Upload CSV", 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")
-            bar_chart = gr.Plot(
-                 label="Category Distribution Across 5 Classes"
-                
-                 
-            )
+            gr.Markdown("### Upload CSV and get automatic category prediction")
             
+            with gr.Row():
+                file_input = gr.File(
+                    label="📤 Upload your CSV file",
+                    file_types=[".csv"],
+                    height=120
+                )
+            
+            classify_btn = gr.Button("🚀 Classify News", variant="primary", size="large")
+            
+            with gr.Row():
+                output_text = gr.Textbox(label="Status", scale=2)
+                output_file = gr.File(label="📥 Download output.csv")
+            
+            bar_chart = gr.Plot(label="📊 Category Distribution Across 5 Classes")
+
             classify_btn.click(
                 fn=classify_csv,
                 inputs=file_input,
-                outputs=[output_text, output_file,bar_chart]
+                outputs=[output_text, output_file, bar_chart]
             )
 
+        # ====================== Q&A TAB ======================
         with gr.Tab("❓ Question Answering"):
-            gr.Markdown("Ask any question about a news article")
-            news_input = gr.Textbox(lines=12, label="Paste News Content", placeholder="Paste the full news article here...")
-            question_input = gr.Textbox(label="Your Question", placeholder="e.g. What is the main topic?")
-            qa_btn = gr.Button("🔍 Get Answer", variant="primary")
-            qa_output = gr.Textbox(label="Answer", lines=5)
+            gr.Markdown("### Ask any question about a news article")
             
+            news_input = gr.Textbox(
+                lines=10,
+                label="📝 Paste News Content",
+                placeholder="Paste the full news article here..."
+            )
+            question_input = gr.Textbox(
+                label="❓ Your Question",
+                placeholder="e.g., What is the main issue? Who is involved?"
+            )
+            
+            qa_btn = gr.Button("🔍 Get Answer", variant="primary", size="large")
+            qa_output = gr.Textbox(label="💡 Answer", lines=6)
+
             qa_btn.click(
                 fn=answer_question,
                 inputs=[news_input, question_input],
                 outputs=qa_output
             )
 
-    #gr.Markdown("Built for Text Analytics Assignment - Section 02")
+    gr.Markdown("---")
+    gr.Markdown("**Built for Text Analytics Assignment (In23-S5-DA3111) - Section 02**")
 
 demo.launch()