Spaces:
Runtime error
Runtime error
Upload folder using huggingface_hub
Browse files
app.py
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import joblib
|
| 2 |
+
import pandas as pd
|
| 3 |
+
from flask import Flask, request, jsonify
|
| 4 |
+
|
| 5 |
+
# Initialize Flask app with a name
|
| 6 |
+
Sales_predictor_api = Flask("SuperKart Sales Predictor")
|
| 7 |
+
|
| 8 |
+
# Load the trained churn prediction model
|
| 9 |
+
model = joblib.load("SuperKart_Sales_Predictor.joblib")
|
| 10 |
+
|
| 11 |
+
# Define a route for the home page
|
| 12 |
+
@Sales_predictor_api.get('/')
|
| 13 |
+
def home():
|
| 14 |
+
return "Welcome to the SuperKart Sales Predictor API!"
|
| 15 |
+
|
| 16 |
+
# Define an endpoint to predict churn for a single customer
|
| 17 |
+
@Sales_predictor_api.post('/v1/sales')
|
| 18 |
+
def predict_sales():
|
| 19 |
+
# Get JSON data from the request
|
| 20 |
+
sales_data = request.get_json()
|
| 21 |
+
|
| 22 |
+
# Extract relevant sales features from the input data
|
| 23 |
+
sample = {
|
| 24 |
+
'Product_Weight': sales_data['Product_Weight'],
|
| 25 |
+
'Product_Allocated_Area': sales_data['Product_Allocated_Area'],
|
| 26 |
+
'Product_MRP': sales_data['Product_MRP'],
|
| 27 |
+
'Product_Type' : sales_data['Product_Type'],
|
| 28 |
+
'Product_MRP' : sales_data['Product_Type'] ,
|
| 29 |
+
'Store_Size' : sales_data['Store_Size'] ,
|
| 30 |
+
'Store_Location_City_Type' : sales_data['Store_Location_City_Type'] ,
|
| 31 |
+
'Store_Type' : sales_data['Store_Type'],
|
| 32 |
+
'Store_Age' : sales_data['Store_Age'] ,
|
| 33 |
+
'Avg_Sales_Per_Product' : sales_data['Avg_Sales_Per_Product'] ,
|
| 34 |
+
'Avg_Sales_Per_Store' : sales_data['Avg_Sales_Per_Store'] ,
|
| 35 |
+
'Product_Sales_Rank' : sales_data['Product_Sales_Rank'] ,
|
| 36 |
+
'Store_Product_Share' : sales_data['Store_Product_Share'] ,
|
| 37 |
+
'Product_MRP_Band' : sales_data['Product_MRP_Band']
|
| 38 |
+
}
|
| 39 |
+
|
| 40 |
+
# Convert the extracted data into a DataFrame
|
| 41 |
+
input_data = pd.DataFrame([sample])
|
| 42 |
+
|
| 43 |
+
# Make a churn prediction using the trained model
|
| 44 |
+
prediction = model.predict(input_data).tolist()[0]
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
# Return the prediction as a JSON response
|
| 48 |
+
return jsonify({'Prediction': prediction})
|
| 49 |
+
|
| 50 |
+
# Run the Flask app in debug mode
|
| 51 |
+
if __name__ == '__main__':
|
| 52 |
+
app.run(debug=True)
|