File size: 5,556 Bytes
3f187d4 bd726b0 3f187d4 bf10d29 3f187d4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
# Import necessary libraries
import numpy as np
import joblib # For loading the serialized model
import pandas as pd # For data manipulation
from flask import Flask, request, jsonify # For creating the Flask API
# Initialize the Flask application
product_store_sales_predictor_api = Flask("SuperKart Product Store Sales Predictor")
# Load the trained machine learning model
model = joblib.load("superkart_sales_prediction_model_v1_0.joblib")
# Define a route for the home page (GET request)
@product_store_sales_predictor_api.get('/')
def home():
"""
This function handles GET requests to the root URL ('/') of the API.
It returns a simple welcome message.
"""
return "Welcome to SuperKart Product Store Sales Predictor API!"
# Define an endpoint for single property prediction (POST request)
@product_store_sales_predictor_api.post('/v1/productsales')
def predict_product_sales():
"""
This function handles POST requests to the '/v1/productsales' endpoint.
It expects a JSON payload containing Product and store details and returns
the predicted sales price as a JSON response.
"""
# Get the JSON data from the request body
product_data = request.get_json()
# Extract relevant features from the JSON data
sample = {
'Product_Weight': product_data['Product_Weight'],
'Product_Allocated_Area': product_data['Product_Allocated_Area'],
'Product_MRP': product_data['Product_MRP'],
'Store_Age': product_data['Store_Age'],
'Product_Identifier': product_data['Product_Identifier'],
'Product_Sugar_Content_No Sugar': product_data['Product_Sugar_Content_No Sugar'],
'Product_Sugar_Content_Regular': product_data['Product_Sugar_Content_Regular'],
'Product_Sugar_Content_reg': product_data['Product_Sugar_Content_reg'],
'Product_Type_Breads': product_data['Product_Type_Breads'],
'Product_Type_Breakfast': product_data['Product_Type_Breakfast'],
'Product_Type_Canned': product_data['Product_Type_Canned'],
'Product_Type_Dairy': product_data['Product_Type_Dairy'],
'Product_Type_Frozen Foods': product_data['Product_Type_Frozen Foods'],
'Product_Type_Fruits and Vegetables': product_data['Product_Type_Fruits and Vegetables'],
'Product_Type_Hard Drinks': product_data['Product_Type_Hard Drinks'],
'Product_Type_Health and Hygiene': product_data['Product_Type_Health and Hygiene'],
'Product_Type_Household': product_data['Product_Type_Household'],
'Product_Type_Meat': product_data['Product_Type_Meat'],
'Product_Type_Others': product_data['Product_Type_Others'],
'Product_Type_Seafood': product_data['Product_Type_Seafood'],
'Product_Type_Snack Foods': product_data['Product_Type_Snack Foods'],
'Product_Type_Soft Drinks': product_data['Product_Type_Soft Drinks'],
'Product_Type_Starchy Foods': product_data['Product_Type_Starchy Foods'],
'Store_Id_OUT002': product_data['Store_Id_OUT002'],
'Store_Id_OUT003': product_data['Store_Id_OUT003'],
'Store_Id_OUT004': product_data['Store_Id_OUT004'],
'Store_Size_Medium': product_data['Store_Size_Medium'],
'Store_Size_Small': product_data['Store_Size_Small'],
'Store_Location_City_Type_Tier 2': product_data['Store_Location_City_Type_Tier 2'],
'Store_Location_City_Type_Tier 3': product_data['Store_Location_City_Type_Tier 3'],
'Store_Type_Food Mart': product_data['Store_Type_Food Mart'],
'Store_Type_Supermarket Type1': product_data['Store_Type_Supermarket Type1'],
'Store_Type_Supermarket Type2': product_data['Store_Type_Supermarket Type2']
}
# Convert the extracted data into a Pandas DataFrame
input_data = pd.DataFrame([sample])
# Make prediction (get log_price)
predicted_sales = model.predict(input_data)[0]
# Convert predicted_price to Python float
predicted_sales = round(float(predicted_sales), 2)
# The conversion above is needed as we convert the model prediction (log price) to actual price using np.exp, which returns predictions as NumPy float32 values.
# When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error
# Return the actual price
return jsonify({'Predicted Product Store Sales Total': predicted_sales})
# Define an endpoint for batch prediction (POST request)
@product_store_sales_predictor_api.post('/v1/productsalesbatch')
def predict_product_sales_batch():
"""
This function handles POST requests to the '/v1/productsalesbatch' endpoint.
It expects a CSV file containing product and store details for multiple entries
and returns the predicted sales as a dictionary in the JSON response.
"""
# Get the uploaded CSV file from the request
file = request.files['file']
# Read the CSV file into a Pandas DataFrame
input_data = pd.read_csv(file)
# Make predictions for all products in the DataFrame
predicted_sales = model.predict(input_data).tolist()
# Create a dictionary of predictions with Product_Id as keys
product_ids = input_data['Product_Id'].tolist() # Assuming 'Product_Id' is the product ID column
output_dict = dict(zip(product_ids, predicted_sales))
# Return the predictions dictionary as a JSON response
return output_dict
# Run the Flask application in debug mode if this script is executed directly
if __name__ == '__main__':
product_store_sales_predictor_api.run(debug=True)
|