app.py

from datetime import datetime
from flask import Flask,request,jsonify
from flask_cors import CORS
import joblib
import numpy as np
import pandas as pd
import logging

logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')

app = Flask(__name__)
#CORS(app)
CORS(app, resources={r"/*":{"origins":"*"}})

try:
  model_gradbosot = joblib.load('gradboost_RSCV.joblib')
  model_rndmfrst = joblib.load('RndmFrstReg_RSCV.joblib')
  pipeline = joblib.load('pipeline.joblib')
  feature_names = joblib.load('feature_names.joblib')
except Exception as Ex:
  logging.error(f'Exception in loading joblib file: {Ex}')

required_features =['Product_Weight','Product_Sugar_Content','Product_Allocated_Area',
                    'Product_Type','Product_MRP','Store_Size','Store_Location_City_Type',
                    'Store_Type','Store_Establishment_Year'
                    ]
model_features =['Product_Weight','Product_Sugar_Content','Product_Allocated_Area',
                    'Product_Type','Product_MRP','Store_Size','Store_Location_City_Type',
                    'Store_Type','Age_Of_Store'
                    ]

@app.get('/')
def home():
  logging.debug("Accessed endpoint of Home page")
  return "Welcome to Superkart Prediction system"

@app.route('/predict', methods=['POST'])
def predict():
  try:

    data = request.get_json()
    logging.debug(f"Input received:{data}")
    if not data:
      return jsonify({'Error':'No data provided for prediction'},400)

    if not all(feature in data for feature in required_features):
      feature_missing = [feature for feature in required_features if feature not in data]
      logging.error(f"Exception feature missing:{feature_missing}")
      return jsonify({'Exception':f'Feature missing {feature_missing}'},400)

    present_year = datetime.now().year
    feature_for_prediction =pd.DataFrame([{
        'Product_Weight':float(data['Product_Weight']),
        'Product_Sugar_Content':data['Product_Sugar_Content'],
        'Product_Allocated_Area':float(data['Product_Allocated_Area']),
        'Product_Type': data['Product_Type'],
        'Product_MRP':float(data['Product_MRP']),
        'Store_Size':data['Store_Size'],
        'Store_Location_City_Type':data['Store_Location_City_Type'],
        'Store_Type':data['Store_Type'],
        'Store_Establishment_Year':float(data['Store_Establishment_Year'])
        }],columns=required_features)

    feature_for_prediction['Age_Of_Store'] = present_year - feature_for_prediction['Store_Establishment_Year']
    feature_for_prediction = feature_for_prediction[model_features]



    prediction_gradboost = model_gradbosot.predict(feature_for_prediction)[0]
    prediction_randFrst = model_rndmfrst.predict(feature_for_prediction)[0]

    logging.debug(f"Prediction gradmodel: {prediction_gradboost}")
    logging.debug(f"Prediction RandmFrst: {prediction_randFrst}")

    return jsonify ({'gradientBoosting':float(prediction_gradboost),
              'randomForest':float(prediction_randFrst)})


  except Exception as ex:
    logging.error(f'Exception: {ex}')
    return jsonify({'Exception': str(ex) })



@app.route('/Predict_BatchProcess', methods=['POST'])
def Predict_BatchProcess():
  logging.debug(f"Request headers : {request.headers}")
  if 'file' not in request.files:
    return jsonify({'Exception': 'No files provided for batch processing'}),400

  file = request.files['file']
  if not file.filename.endswith('csv'):
    logging.error("Invalid file, Application process only .csv files")
    return jsonify({'Exception': 'Invalid file, Application process only .csv files'})

  ip_data = pd.read_csv(file)
  logging.debug(f'File loaded for batch processing total rows and columns: {ip_data.shape}')

  if not all(feature in ip_data.columns for feature in required_features):
    feature_missing = [feature for feature in required_features
                       if feature not in ip_data.columns]
    logging.error(f"feature missing in csv {feature_missing}")
    return jsonify({'Exception':f"feature missing in csv {feature_missing}"}),400

  ip_data = ip_data[required_features]
  present_year = datetime.now().year

  ip_data['Age_Of_Store'] = present_year - ip_data['Store_Establishment_Year']
  ip_data = ip_data[model_features]


  prediction_gradboost = model_gradbosot.predict(ip_data)
  prediction_randFrst = model_rndmfrst.predict(ip_data)

  logging.debug(f"Prediction gradmodel: {prediction_gradboost}")
  logging.debug(f"Prediction RandmFrst: {prediction_randFrst}")

  df_prediction = ip_data.copy()
  df_prediction['GradeientModel_Prediction'] = prediction_gradboost
  df_prediction['RandomForest_Prediction'] = prediction_randFrst

  return jsonify (df_prediction.to_dict(orient='records'))



if __name__ == '__main__':
  app.run(host='0.0.0.0', port=7860, debug=False)