Delete app.py

app.py

@@ -1,95 +0,0 @@
-import gradio as gr
-import pickle
-import numpy as np
-
-# Load model and scaler
-with open("marketing_model.pkl", "rb") as f:
-    model = pickle.load(f)
-
-with open("scaler.pkl", "rb") as f:
-    scaler = pickle.load(f)
-
-
-def predict_campaign(
-    income,
-    kidhome,
-    teenhome,
-    recency,
-    wines,
-    fruits,
-    meat,
-    fish,
-    sweets,
-    gold,
-    web_purchases,
-    store_purchases
-):
-
-    # Convert inputs to float
-    income = float(income)
-    kidhome = float(kidhome)
-    teenhome = float(teenhome)
-    recency = float(recency)
-    wines = float(wines)
-    fruits = float(fruits)
-    meat = float(meat)
-    fish = float(fish)
-    sweets = float(sweets)
-    gold = float(gold)
-    web_purchases = float(web_purchases)
-    store_purchases = float(store_purchases)
-
-    # Calculate total spending
-    total_spending = wines + fruits + meat + fish + sweets + gold
-
-    # Feature array
-    features = np.array([
-        income,
-        kidhome,
-        teenhome,
-        recency,
-        wines,
-        fruits,
-        meat,
-        fish,
-        sweets,
-        gold,
-        web_purchases,
-        store_purchases,
-        total_spending
-    ]).reshape(1, -1)
-
-    # Scale features
-    features = scaler.transform(features)
-
-    # Prediction
-    prediction = model.predict(features)[0]
-
-    if prediction == 1:
-        return "✅ Customer will likely accept the marketing campaign"
-    else:
-        return "❌ Customer is unlikely to accept the marketing campaign"
-
-
-interface = gr.Interface(
-    fn=predict_campaign,
-    inputs=[
-        gr.Number(label="Income"),
-        gr.Number(label="Kidhome"),
-        gr.Number(label="Teenhome"),
-        gr.Number(label="Recency"),
-        gr.Number(label="Wine Spending"),
-        gr.Number(label="Fruit Spending"),
-        gr.Number(label="Meat Spending"),
-        gr.Number(label="Fish Spending"),
-        gr.Number(label="Sweet Spending"),
-        gr.Number(label="Gold Spending"),
-        gr.Number(label="Web Purchases"),
-        gr.Number(label="Store Purchases"),
-    ],
-    outputs=gr.Textbox(label="Prediction Result"),
-    title="Sales Analytics & Marketing Automation",
-    description="Predict whether a customer will accept a marketing campaign."
-)
-
-interface.launch()