Provisioning and deleting compute clusters & compute instances using the Azure ML Python SDK — When running machine learning experiments using the Azure ML Python SDK, one of the things you will need to have handy is a compute resource. This article walks you through some common Python code you might write to retrieve, provision, update, and even delete compute instances and compute clusters in…

Making sense of compute instances vs compute clusters and more in Azure Machine Learning — Azure Machine Learning is a powerful suite of tools to manage datasets, train, version, and evaluate machine learning models, and deploy those models to endpoints where others can use them. But many of these tasks take raw computing power, so it is important to understand the many options we have…

Using standard metrics to interpret classification models in machine learning — Let’s say you’re running a classification experiment in machine learning and you have a trained model, but you want to understand how good that model actually is. While there are a lot of different metrics and tools available to evaluate the performance of a classification experiment, the first one I…

Migrate your Pandas DataFrames to Azure Machine Learning and back again — Before machine learning can be accomplished, data is frequently cleaned in Python using Pandas DataFrames to filter, clean, sort, and aggregate data into a more usable format. But if you, like me, prefer to use the Azure ML Python SDK to help augment your data science tasks, you’ll need to…

Use the Azure ML Python SDK to connect to Azure Machine Learning Studio — In this article we’ll explore several ways of connecting to an Azure Machine Learning Studio Workspace from Python code using the Azure Machine Learning SDK for Python as well as some of the things you can do with that workspace after connecting. Note: this article assumes you have already installed…

Using regression metrics to evaluate machine learning models — Regression at a Glance In this article we’ll explore the common metrics you’ll see evaluating the performance of a trained machine learning model for a regression task. Regression experiments are one of the 3 core machine learning tasks and used for predicting a numerical label given a set of features and training data. An…

My study plan for becoming an Azure Data Scientist Associate — Last week I took and passed the DP-100 exam and am officially a Microsoft Certified: Azure Data Scientist Associate. This was my first attempt at the exam and I passed with a 934 out of 1000 with a minimum of 700 points needed to pass the exam. In this article…

Using Regression Models and Automated Machine Learning to Predict High-Risk Games — This project is the results of a machine learning experiment that considers historical hockey games from 2001–2020 to build a regression model capable of predicting the number of penalty minutes that might be expected for a given NHL hockey game factoring in only the home team, the away team, and…

A high-level overview of Azure’s enterprise-level data engineering solution — Recently I had the opportunity to spend some time studying Azure Synapse Analytics and I wanted to share a high-level summary of what I learned so you can determine if it is a good match for your data processing needs. This content is also available in video form on YouTube Introducing Synapse Analytics …