AFranzi afranzi

pyenv install 3.7.0
pyenv global 3.7.0 # Use Python 3.7
mkvirtualenv mlflow # Create a Virtual Env with Python 3.7
workon mlflow

Install required libraries.

pip install mlflow==0.7.0 \

Start by downloading the latest stable Apache Spark (current 2.4.3).

cd ~/Downloads/
tar -xzf spark-2.4.3-bin-hadoop2.7.tgz
mv ~/Downloads/spark-2.4.3-bin-hadoop2.7 ~/
ln -s ~/spark-2.4.3-bin-hadoop2.7 ~/spark̀

Install PySpark and Jupyter in our virtualEnv

	/*
	* Copyright (c) 2018 Schibsted Media Group. All rights reserved
	*/
	package com.saas.presto.access.authentication

	import java.security.Principal
	import java.util.concurrent.TimeUnit.MILLISECONDS

	import com.facebook.presto.spi.security.{AccessDeniedException, BasicPrincipal, PasswordAuthenticator}
	import com.google.common.cache.{CacheBuilder, CacheLoader, LoadingCache}

	import argparse
	import errno
	import os
	import sys

	from jinja2 import Environment, FileSystemLoader, StrictUndefined

	UTF8 = 'utf8'
	TEMPLATE = 'template'

	# Running a Tracking Server
	mlflow server \
	--file-store /tmp/mlflow/fileStore \
	--default-artifact-root s3://<bucket>/mlflow/artifacts/ \
	--host localhost
	--port 5000

	MLFLOW_TRACKING_URI=http://localhost:5000 python wine_quality.py \
	--alpha 0.9
	--l1_ration 0.5
	--wine_file ./data/winequality-red.csv

	with mlflow.start_run():

	... model ...

	mlflow.log_param("source", wine_path)
	mlflow.log_param("alpha", alpha)
	mlflow.log_param("l1_ratio", l1_ratio)

	mlflow.log_metric("rmse", rmse)
	mlflow.log_metric("r2", r2)

	# Serve a sklearn model through 127.0.0.0:5005
	MLFLOW_TRACKING_URI=http://0.0.0.0:5000 mlflow sklearn serve \
	--port 5005 \
	--run_id 0f8691808e914d1087cf097a08730f17 \
	--model-path model

	# Query Tracking Server Endpoint
	curl -X POST \
	http://127.0.0.1:5005/invocations \
	-H 'Content-Type: application/json' \
	-d '[
	{
	"fixed acidity": 3.42,
	"volatile acidity": 1.66,
	"citric acid": 0.48,
	"residual sugar": 4.2,