mexico-pml-forecast/flask_api/app/server.py

import os
import pandas as pd
import pickle
from flask import Flask, jsonify, request
from .utils import PreProcessing

app = Flask(__name__)

@app.route('/')
def index():
	""" Index Web Page
	"""
	return "Modelo Mexico PML Day Ahead Forecast"

@app.route('/predict', methods=['POST'])
def apicall():
	"""API Call
	
	Pandas dataframe (sent as a payload) from API Call
	"""
	prepro = PreProcessing()
	print(request)
	try:
		data_json = request.get_json()
		data = pd.read_json(data_json, orient='index')

		data = prepro.process(data)
		data = data[data.index.date == data.index.max().date()].drop('P', axis=1)

		#Getting the datetime into separated out
		forecast_datetime = data.index

	except Exception as e:
		raise e
	
	rgs = 'lbrprice_model_svr.pkl'
	
	if data.empty:
		return(bad_request())
	else:
		#Load the saved model
		print("Loading the model...")
		loaded_model = None
		with open('./models/'+rgs,'rb') as f:
			loaded_model = pickle.load(f)

		print("The model has been loaded...doing predictions now...")
		predictions = loaded_model.predict(data)
		
		"""Add the predictions as Series to a new pandas dataframe
								OR
		   Depending on the use-case, the entire test data appended with the new files
		"""
		prediction_series = list(pd.Series(predictions))

		final_predictions = pd.DataFrame({'pred_price': prediction_series}, index=forecast_datetime)
		
		"""We can be as creative in sending the responses.
		   But we need to send the response codes as well.
		"""
		responses = jsonify(predictions=final_predictions.to_json(orient="index", date_format='iso'))
		responses.status_code = 200

		return (responses)


@app.errorhandler(400)
def bad_request(error=None):
	message = {
			'status': 400,
			'message': 'Bad Request: ' + request.url + '--> Please check your data payload...',
	}
	resp = jsonify(message)
	resp.status_code = 400

	return resp

if __name__ == '__main__':
	app.run(host='0.0.0.0')