Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+
+# --- Dummy data (replace later if needed) ---
+np.random.seed(42)
+data = pd.DataFrame({
+    "track": [f"Track {i}" for i in range(1, 21)],
+    "sentiment": np.random.uniform(-1, 1, 20),
+    "streams": np.random.randint(1000, 100000, 20),
+    "price": np.random.uniform(5, 15, 20)
+})
+
+# --- Functions ---
+def sentiment_analysis():
+    avg_sentiment = data["sentiment"].mean()
+    return f"Average sentiment score: {round(avg_sentiment, 3)}"
+
+def forecast_streams():
+    forecast = int(data["streams"].mean() * 1.1)
+    return f"Predicted average streams next period: {forecast}"
+
+def pricing_recommendation():
+    avg_price = data["price"].mean()
+    if avg_price > 10:
+        return "Recommendation: Consider lowering price to improve conversion."
+    else:
+        return "Recommendation: Pricing is competitive."
+
+# --- UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎧 Music Streaming Analytics App")
+    gr.Markdown("Optimize playlist curation and subscription pricing using sentiment + forecasting")
+
+    with gr.Tab("Sentiment Insights"):
+        btn1 = gr.Button("Analyze Sentiment")
+        out1 = gr.Textbox()
+        btn1.click(fn=sentiment_analysis, outputs=out1)
+
+    with gr.Tab("Stream Forecast"):
+        btn2 = gr.Button("Forecast Streams")
+        out2 = gr.Textbox()
+        btn2.click(fn=forecast_streams, outputs=out2)
+
+    with gr.Tab("Pricing Strategy"):
+        btn3 = gr.Button("Get Pricing Recommendation")
+        out3 = gr.Textbox()
+        btn3.click(fn=pricing_recommendation, outputs=out3)
+
+demo.launch()