Spaces:
Sleeping
Sleeping
import joblib | |
import numpy as np | |
import pandas as pd | |
from flask import Flask, request, jsonify | |
super_kart_api=Flask("Superkart_price_prediction") | |
model=joblib.load('model.joblib') | |
def home(): | |
return "Welcome to SuperKart sales Prediction" | |
def sale_pred_single(): | |
sale_data=request.get_json() | |
sample={ | |
'Product_Weight':sale_data['Product_Weight'], | |
'Product_Sugar_Content':sale_data['Product_Sugar_Content'], | |
'Product_Allocated_Area':sale_data['Product_Allocated_Area'], | |
'Product_Type':sale_data['Product_Type'], | |
'Product_MRP':sale_data['Product_MRP'], | |
'Store_Id':sale_data['Store_Id'], | |
'Store_Size':sale_data['Store_Size'], | |
'Store_Location_City_Type':sale_data['Store_Location_City_Type'], | |
'Store_Type':sale_data['Store_Type'], | |
'Store_age':sale_data['Store_age'] | |
} | |
input_data=pd.DataFrame([sample]) | |
predicted_sale=model.predict(input_data)[0] | |
response={'Store_Outlet':sample['Store_Id'],"Sale":round(float(predicted_sale), 2)} | |
return jsonify(response) | |
def sale_pred_batch(): | |
file = request.files['file'] | |
print("File Received:", file.filename) | |
# Read input data | |
input_data = pd.read_csv(file) | |
print("Input Data Shape:", input_data.shape) | |
print(input_data.head()) | |
# Make predictions | |
predicted_sale = model.predict(input_data).tolist() | |
print("Predicted Sales Length:", len(predicted_sale)) | |
predicted_sales = [round(float(i)) for i in predicted_sale] | |
sale_outlets = input_data['Store_Id'].tolist() | |
print("Sale Outlets Length:", len(sale_outlets)) | |
# Create response | |
response = dict(zip(sale_outlets, predicted_sales)) | |
print("Response:", response) | |
repshape = {'input_shape': input_data.shape, 'predicted_count': len(predicted_sale)} | |
print("Response Shape:", repshape) | |
# Return combined response | |
return jsonify({ | |
'predictions': response, | |
'metadata': repshape | |
}) | |
if __name__=='__main__': | |
super_kart_api.run() | |