Tutorial: Getting started with Azure Machine Learning Studio

Qasim Shah
A free video tutorial from Qasim Shah
Enterprise Architect, Digitization Expert & Teacher
4.2 instructor rating • 25 courses • 179,332 students

Learn more from the full course

Microsoft Azure Machine Learning (ML) Fundamentals

Create your first Data Science experiment in Microsoft Azure using Machine learning (ML). Real world data analysis.

01:37:30 of on-demand video • Updated November 2018

  • Build basic data science experiments using Microsoft Azure Machine Learning
  • Understand and apply Microsoft Azure Machine learning concepts to real world problems
  • Learn Azure ML Studio
  • Become proficient at Machine Learning workings including predictive analysis
English [Auto] Hi everybody. So in this lesson we're going to look at the azure portal specifically and look at the studio. We're going to familiarize ourselves with how to log in with the different options that are available and that will help us out in the future lessons when we actually start developing experiments and start predictive analysis. The first thing to do is go to the azure amounts to report portal so that portal can be found at Studio that you're older that have triggered the ongoing to Simon. So once you guys are signed then you guys see a few experiments that I'm working on but for the first understanding and this will be empty. So this is basically called the azure workbench or in other words is basically the dashboard that you guys see when we first log in to the machine learning studio on the left hand side are all the different options are available depending on the type of subscription that you have. This is for the free subscription that Microsoft offers for the first year when you're working with Azure portal. So these are all options that allow you to use for free. But if you have a paid subscription there are many more options that are available depending on again the level and type of subscription that you have to the azure service. So for this machine learning of course and for this machine learning demo and the free version works just as well where you have projects you can create new projects an experiment where it lists all the different experiments or predictive analysis items that you are doing one good thing about studio is if you click on the samples Microsoft has a ton of pre-built experiments already for you that you can use to start working on your own or you can use as examples to develop your own. So there's certain experiments that you want to do in marketing let's say for direct marketing. You can use one already built by Microsoft and just expand on that or modify it based on your specific needs. So that's one very good thing about the end our studio are the ton of experiments that are already pre-built for you. So as a first homework assignment pleases go through and click on some of the experiments that sound interesting just to look at how they look and feel for you. Because when we develop our own experiments this will definitely help out. So just to give you guys an example let's say that I want to quickly take a peek at what an experiment looks like. So I will pick a direct marketing experiment and it will take me into the already pre-build experiment that Microsoft has done for us and here is where we can zoom in to see all of the different variables that are being used. And again we will go through these in more detail than we actually develop our own experiment in the next lesson. So just to go back again there's experiments actionless the experiment you're currently working on and the samples are those pre-built samples that Microsoft already has for you the Web services section allows you to see all the different web services that you have published. So this is after you've completed your experiments and you publish them as a web service they will show up here will allow you to view the links and there you are eyes for all of the experiments that you have done that you want to use or or that you want to have your business stakeholders use. We also have an option for notebooks and again these are more used for programming or if not a modifier on modules. You will see these here the data sets you to see all the data sets that you have uploaded. Or again like with experiments Microsoft has a number of pre uploaded data sets that you can use as testing to do when you're developing experiments. So let's say you want to develop an experiment to do predictive analysis on a certain item but you want to test out to see if your logic is correct. You can use one of these pre-build data sets just to practice on creating experiments and familiarize yourself with what different logics will work in what circumstances. Train models you will see after you have completed the experiments and you have trained the different models for conducting predictive analysis often will show up here. So again depending on how many experiments that you are conducting you will see that many train models here. Helen finally the settings tab allow you to change the different settings of your workspace where that's the name of the description you can see how much the available disk space you have used again for free disk space. They get Marsar gives you 10 gigabytes of space but for a paid workspace again it can be considerably larger depending on what tier of subscription you have with Microsoft one of the good things that you are able to do is you can invite other users to your workspace. So for example if you want other users within your organization to see your experiments or collaborate with you on the experiments that you are doing this is where you can invite them to your workspace on the bottom here you can see invite more users. And here is where way you can put in their email addresses and they will get an invite to join your workspace. It is a very good tool because again most experiments that you will be doing are more extremes that organizations do involve more than one person and usually involves a team. So this is where the entire team can collaborate and work on a single experiment or multiple projects. So again you going to have project based teams you know experiment based teams. It just depends on the type of set up that you have that you would like to do. And then another good thing is it gives you an option to join machine learning forms or read machine learning forums. Some of the forms give you very good insight in terms of answering some questions that you might have and for what kind of regression or what kind of analysis you should run on what type of data. So as a homework assignment please go through the list of forms that are out there because you might find some that could be very useful for you and your organization or are you under a specific project or experiment that you doing so is a very good practice to see what others are doing in your industry. So again you can see there's quite a few different forms that are available with a variety of different questions. And again if you have one specific question you can also post your own question and hopefully get answers from other experts in the field. And lastly if you want to create a new experiment or let's say you want to upload our data I see the option for a new on the bottom left hand corner. If you click on that this is where it allows you to upload your own data set. If See here you can go ahead and choose and upload whatever data is that you have for your organization. Additionally you can choose different modules. And again these are already pre-built modules by Microsoft since we're working in Studio 4 am for more service. Again you build your own modules from different programming languages the experiment and again these are already pre-build experiments by Microsoft to make our job a lot easier. So depending on what type of analysis that you want to do with your data you can pick and choose whether it's a k means clustering whether it's our model whether it's a linear regression with a binary classification or Again depending on your problem depending on what question you are trying to answer. There are tons of pre-built samples already for you. Or again we can or you can always start with a blank experiment and build your own. If that is your preference. So again it just depends on the lower the level of expertise that are within your organization or within your team. So if you have sufficient expertise you are more than welcome to build your own experiment or if you lack some expertise within your team I would suggest. I would highly suggest you use one of the pre-built samples that Microsoft has done for you. It just makes the job a lot easier especially if you don't have a statistical expert on your team. And in the project window is where you can see and create new projects and projects. How has multiple experienced experiments with them so again this depends if multiple departments are using are going to be using machine learning. You can have a project for each department for for the marketing department for the logistics department and within those prizes you can have multiple experiments within a marketing project. You can have multiple experiments for direct marketing for email marketing for social media to see what kind of outcomes we can predict and what campaigns are working and what campaigns are not working. The last option that gives us for creating new is not book and not books are for people who are more experienced in machine learning. So if you have a python or an expert or a programming expert or if are a Jupiter or soccer expert this is where you can create your own logic you can create your own models or use one of the pre-built models that Microsoft already has and just add on to it. So again there are already pre-built examples for you. There's not a pronounceable give scientists a complete walkthrough anything to put a note book within a machine studio. So again there's multiple walkthrough. There are multiple examples. So those are quick or we are bored as are most studio. I hope you guys got a little familiar with what it looks and feels like and the nice lessons are taking you through a few experiments in terms of designing our own and doing some predictive analysis to see how it works. So I hope you guys enjoy this lesson and I look forward to seeing you in the next.