Update app.py

app.py

@@ -1,4 +1,60 @@
-gradio
-vaderSentiment
-pandas
-numpy
+import gradio as gr
+import pandas as pd
+import numpy as np
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+
+analyzer = SentimentIntensityAnalyzer()
+
+restaurants = ['PastaPlace', 'BurgerHub', 'SushiBar', 'TacoLoco', 'CafeBleu']
+
+np.random.seed(42)
+df_sales = pd.DataFrame({
+    'restaurant': np.repeat(restaurants, 20),
+    'week': list(range(1, 21)) * 5,
+    'revenue': np.random.randint(3000, 15000, 100),
+    'avg_price': np.random.uniform(12, 45, 100).round(2)
+})
+
+def analyze_restaurant(restaurant, review):
+    # Sentiment analysis
+    score = analyzer.polarity_scores(review)['compound']
+    if score > 0.05:
+        sentiment = "😊 Positive"
+    elif score < -0.05:
+        sentiment = "😡 Negative"
+    else:
+        sentiment = "😐 Neutral"
+    
+    # Sales stats
+    stats = df_sales[df_sales['restaurant'] == restaurant]['revenue']
+    avg_rev = stats.mean().round(2)
+    
+    # Pricing recommendation
+    if score > 0.05 and avg_rev > 8000:
+        recommendation = "📈 Increase prices by 10% - Strong performance!"
+    elif score < -0.05:
+        recommendation = "📉 Improve service before adjusting prices"
+    else:
+        recommendation = "➡️ Keep current pricing strategy"
+    
+    result = f"""
+    🍽️ Restaurant: {restaurant}
+    📊 Sentiment: {sentiment} (score: {score:.2f})
+    💰 Average Weekly Revenue: €{avg_rev}
+    💡 Recommendation: {recommendation}
+    """
+    return result
+
+iface = gr.Interface(
+    fn=analyze_restaurant,
+    inputs=[
+        gr.Dropdown(choices=restaurants, label="Select Restaurant"),
+        gr.Textbox(label="Enter a customer review", 
+                   placeholder="e.g. Amazing food, loved it!")
+    ],
+    outputs=gr.Textbox(label="Analysis & Recommendation"),
+    title="🍽️ Restaurant Performance Analyzer",
+    description="Analyze customer sentiment and get pricing recommendations"
+)
+
+iface.launch()