Update app.py

app.py

@@ -1,127 +1,7 @@
-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
-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):
-    if not isinstance(text, str):
-        return ""
-    text = text.lower()
-    punct_to_remove = string.punctuation.replace("'","").replace('"',"").replace("$","").replace("%","").replace("?","")
-    text = re.sub(f"[{punct_to_remove}]", " ", text)
-    tokens = nltk.word_tokenize(text)
-    tokens = [lemmatizer.lemmatize(word) for word in tokens]
-    return ' '.join(tokens)
-
-classifier_model = "Ginidu2003/Distilbert-Base-News-classifier"
-
-# ====================== BEAUTIFUL 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"]
-
-    # Nice modern color palette
-    colors = ['#3498DB', '#E67E22', '#9B59B6', '#2ECC71', '#E74C3C']
-
-    fig, ax = plt.subplots(figsize=(11, 6))
-    bars = ax.bar(categories, counts, color=colors, edgecolor='white', linewidth=0.8)
-
-    # Add value on top of bars
-    for bar in bars:
-        height = bar.get_height()
-        ax.text(bar.get_x() + bar.get_width()/2, height + 0.8,
-                str(int(height)), ha='center', va='bottom', fontsize=13, fontweight='bold')
-
-    ax.set_title("Category Distribution Across 5 Classes", fontsize=16, fontweight='bold', pad=20)
-    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()
-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, None
-        
-        df['clean_content'] = df['content'].apply(preprocess_text)
-        
-        classifier = pipeline("text-classification", model=classifier_model, device=-1)
-        
-        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')
-        
-        output_file = "output.csv"
-        df.to_csv(output_file, index=False)
-        
-        category_counts = df['class'].value_counts().reset_index()
-        category_counts.columns = ["Category", "Count"]
-        
-        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
-
-# ====================== 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
-        
-        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)}"
-
 # ====================== BEAUTIFUL UI ======================
 with gr.Blocks(
     title="English News Classifier",
-    theme=gr.themes.Dark(),
+    theme=gr.themes.Soft(),           # Modern & Clean theme
     css="""
     .gradio-container {
         max-width: 1200px;
@@ -133,10 +13,6 @@ with gr.Blocks(
         font-size: 2.8rem;
         margin-bottom: 10px;
     }
-    .tab-label {
-        font-size: 1.2rem;
-        font-weight: 600;
-    }
     """
 ) as demo: