Azure Machine Learning Tutorial

In this Azure Machine Learning tutorial, I’ll walk you through everything you need to know to get started, from setting up your environment to deploying your first model. This guide is designed to help you master Microsoft Azure Machine Learning confidently.

Azure Machine Learning Tutorial

What is Machine Learning?

Machine Learning is a part of Artificial intelligence (AI) that allows systems to learn without being explicitly programmed. It is an application of AI.

Now, the next question that comes to your mind is, What is Artificial Intelligence (AI) then?

Artificial intelligence (AI) is the process of simulating a human’s intelligence, thinking, and behavior in a machine using Programs.

Now, let’s move toward the Azure ML Tutorial.

Azure Machine Learning is a set of services and tools that helps developers develop and deploy various machine learning models easily. Primarily, it also saves a lot of cost and time needed for the implementation.

The most interesting fact is that you can now create a machine learning model with a few clicks. Can you believe this? Yes, this is the truth; with the help of an IDE, i.e., Azure Machine Learning Studio, we can easily develop and deploy the machine learning model.

Why Use Azure Machine Learning?

• Scalability: Easily scale your compute resources up or down.
• Integration: Seamlessly integrates with other Azure services like Azure Data Lake, Azure SQL Database, and Power BI.
• MLOps Support: Automate and manage your ML workflows with built-in MLOps capabilities.
• Flexibility: Supports Python SDK, drag-and-drop GUI, and REST APIs for various skill levels.
• Security & Compliance: Meets rigorous USA regulatory standards for data security.

Benefits of Azure Machine Learning

• Azure ML offers numerous benefits, including significant cost and time savings, enabling medium-sized and small businesses to develop machine learning models confidently. So, it enables mid-scale and small companies to adopt machine learning models.
• The other benefit of Azure ML is that you can directly connect with the Azure SQL and other services, making the task for the developer easy.
• Azure Machine Learning supports operations with massive or Big data. The quantity of data is not restricted.
• The pricing model is flexible, utilizing the “pay as you go” model, which helps the organization save a significant amount of costs.
• Azure ML is very user-friendly, offering a simple set of tools that are easy to use.
• Azure Machine Learning Studio helps us with drag-and-drop features where no coding knowledge is required.
• Azure Machine Learning Studio offers built-in algorithms and data transformation tools that provide significant assistance.
• The set of Azure ML tools is built with the latest technologies and features that help to provide more accurate predictions.
• It enables real-time predictions using the fastest algorithm.
• We can publish our data model as a web service, which helps.
• The clutter feature in Office 365 is also being used along with Azure Machine Learning, which helps limit the data’s inaccuracy.

Azure Machine Learning comes with the Azure Machine Learning Studio and Azure Machine Learning Service.

Azure Machine Learning Studio is the IDE (Integrated Development Environment) that helps us with the environment and options to develop Machine learning models with drag-and-drop facilities. The best part is that no coding knowledge is required here.

Azure Machine Learning Service is a fully managed cloud service that enables us to train, deploy, and manage machine learning models. Here, coding is involved. It supports open-source technologies.

You can use many open-source Python packages, such as TensorFlow and Pytorch, along with the Azure Machine Learning Service.

Azure Machine Learning service also comes with support for the Visual Studio Code extension, which helps you manage your resources and deployments in Visual Studio Code.

Getting Started with Azure Machine Learning

Step 1: Set Up Your Azure Account

If you don’t have an Azure account yet, sign up for a free Azure account. Microsoft offers $200 in free credits for new users, which is perfect for experimenting with Azure ML services.

Step 2: Create an Azure Machine Learning Workspace

Your workspace is the foundational resource for all your ML activities. It organizes your experiments, datasets, models, and compute resources.

• Go to the Azure Portal.
• Click Create a resource > AI + Machine Learning > Machine Learning.
• Fill in the workspace name, subscription, resource group (create a new one or use an existing one), and region (choose a USA-based region like East US or West US).
• Click Review + create and then Create. Refer to the screenshot below for your reference.

Different Methods to Use Azure Machine Learning

Azure ML offers multiple ways to build and deploy models. Let’s explore the most popular ones:

1. Azure Machine Learning Studio (Visual Interface)

Perfect for beginners and those who prefer a drag-and-drop experience without coding.

• Features:
  • Visual workflow designer.
  • Pre-built modules for data transformation, feature engineering, and model training.
  • Quick deployment with minimal setup.
• How to use:
  • Access Azure ML Studio at ml.azure.com.
  • Create a new experiment.
  • Drag datasets and modules onto the canvas.
  • Connect modules to define your pipeline.
  • Run and evaluate your experiment.
  • Deploy your model as a web service.

2. Azure Machine Learning Python SDK

Ideal for data scientists and developers comfortable with Python.

• Features:
  • Full control over ML workflows.
  • Supports custom scripts and libraries.
  • Enables automation and integration with CI/CD pipelines.
• Basic workflow:
  1. Install the SDK

pip install azure-ai-ml

2. Connect to your workspace:

from azure.ai.ml import MLClient
from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()
ml_client = MLClient(credential, subscription_id, resource_group, workspace_name)

3. Prepare data, define experiments, and train models.

4. Deploy models using ml_client.

3. Automated Machine Learning (AutoML)

Ideal for users seeking to build models without extensive ML expertise rapidly.

• Features:
  • Automatically selects algorithms and tunes hyperparameters.
  • Supports classification, regression, and time series forecasting.
  • Provides explainability reports.
• How to use:
  • Use Azure ML Studio or Python SDK.
  • Provide a labeled dataset.
  • Configure the AutoML experiment and run.
  • Review the best models and deploy.

Working with Azure Machine Learning Studio

Let’s discuss Azure Machine Learning Studio a bit further. In that case, Microsoft Azure Machine Learning Studio is a tool that provides a drag-and-drop feature and is used to build, test, and deploy predictive analytics solutions on your data.

As already discussed, we can publish Azure Machine Learning as a web service that various external applications, such as Excel, can consume.

Developing an Azure Machine learning model is an iterative process that uses data from different sources, transforms and analyzes that data through various data manipulation mechanisms, and generates a set of Outputs.

Azure Machine Learning Studio provides a visual workspace that helps you easily build, test, and iterate on Predictive data analysis models. You can drag and drop the datasets and modules, and then, after connecting them, form an experiment. You can use that experiment in your Azure Machine learning studio.

A valid experiment has the following characteristics

1. The experiment should contain a minimum of one dataset and one module
2. Datasets may be connected to only different modules.
3. The modules can be connected to different datasets or other modules.
4. You must configure all the necessary parameters for the modules used in the experiment.

Datasets

A dataset is data that you will have to upload to Azure Machine Learning Studio that you will use for the data analytics model. You can upload the dataset as per your requirements. Along with this, you will also get a set of sample datasets from different areas. Those data sets you can utilize as per your requirement.

Some of the sample datasets available are

• MPG Dataset for various automobiles
• Weather Dataset
• Flight Delays Data
• Time Series Dataset
• Book Reviews from Amazon
• Movie Tweets
• Airport Codes Dataset

Modules

Modules are a different set of algorithms you perform on your data. Azure Machine Learning Studio offers a diverse set of modules, ranging from data ingestion functions to training, scoring, and validation processes.

Below are a few examples of the built-in modules.

• Linear Regression
• Score Model
• Two-Class Logistic Regression

No programming knowledge is required to use Azure Machine Learning Studio. You need datasets and modules to construct your predictive data analytics model.

Now, the next question that comes to mind is where you will get the Azure Machine Learning Studio.

Hands-on with Azure Machine Learning

Before accessing the Azure Machine Learning Studio, we need an Azure account or subscription as a prerequisite. Make sure you have an Azure Account or Azure Subscription. If you don’t have an Azure account, you can Create An Azure Free Account now.

Now, assuming you have a valid Azure account, to access the Azure Machine Learning Studio, you can search for it on Google and access the first link. Once the link opens, click on the Sign In button and enter your Azure credentials when it prompts you to do so.

Once you Sign In with your Azure credentials, you can see the Microsoft Azure Machine Learning Studio below.

Next, select the Experiment from the left navigation and click the + New button to create a new experiment.

Now, click on the Blank experiment as highlighted below.

You can see “Experiment created on the date.” Now, you can rename it to the Experiment name you want to mention. Here, I mentioned the experiment named Prediction for Diabetes.

Now, the next step is to select the DataSet. To do that, click on the Saved Datasets from the left side menu and expand the Samples. You can see many sample datasets. From those datasets, select the dataset named Pima Indian Diabetes Binary Classification Dataset.

Now, drag the Pima Indian Diabetes Binary Classification Dataset to the center of the screen, as indicated by the Arrow mark with the hints. Drag items here.

Now, to view the data set we have selected for our experiment, click the 1 with the circle option (highlighted below) and then select the Visualize option. You can also download that data by clicking on the Download link.

You can now see that it is displaying detailed data on that.

The next step is to select the columns you want to include in your Data Model.

Now, on the left side, you can see a search bar. Search for Select Columns in Dataset, and drag that search result towards the center of the screen, down to the Pima Indian Diabetes Binary Classification Dataset box. Now connect both boxes by pulling from the dot in the first box. Once you connect both, it will highlight with an arrow, as shown below.

Now, click on the Launch Column Selector button on the right side.

Now you can see it is shown with lists of 9 Columns. All are relevant to our topic, so you can select all the columns and click the > button. You can see that all the columns are now moved to the Selected Columns section. Now click the tick mark button at the bottom of the screen, as highlighted below.

Now, the next step is to split our data into the training and test datasets. To do that, search for ” Split Data from the left side navigation search bar.

Drag the search result Split Data on the Workspace under the Select Columns in the DataSet box. Then, connect the Select Columns in the DataSet box and the “Split Data” box by dragging the dot symbol highlighted below. Once both are connected, you can see an arrow as highlighted below. From the right side, you can adjust the percentage as needed.

Next, we need to apply the algorithm to train our data model. Although many algorithms are available, we will choose the two-class logistic regression algorithm here. Now, you might be thinking about why this algorithm. OK, the answer here is that this algorithm is used to predict the probability of an outcome.

We are splitting into two Outcomes here, using the two-class logistic regression algorithm.

It would be best if you searched for the two-class logistic regression from the left-side search box. Then, you will find the two-class logistic regression algorithm as the search result. Drag that algorithm to the workspace area, as highlighted below.

Now that we have selected our algorithm, we must train our Data Model. To do that, we need to search for the Train Model and drag it to the workspace, as highlighted below.

Now, connect the two-class Logistic Regression to the Train Model and the Split Data to the Train Model, as highlighted below. Now, click on the Launch column selector to select the columns and select the first column. You can choose any of the columns based on your requirements. I have selected the first column.

Now, we need to score our trained Model. To do that, search for the Score Model and drag the search result to the Workspace. Connect the Train Model, and then link the Training Dataset from the Split Data to it.

The next step is to search for the Evaluate Model from the left navigation search area and then drag the result to the Workspace. Connect the Score Model with it. See the image below for your reference.

The next step is to click the Save button to save the experiment, and then click the Run button to run it.

After clicking the run button, the system verifies each stage and displays a green tick mark for each one. See the screenshot below for your reference. Once it finishes running, it will show Finished running.

Now, click on the dot on the Evaluate Model and then click on the Visualize option to see the report.

The report is below. You can adjust the threshold to minimize the false negative value. Ideally, the number of False Positives and False Negatives should be minimal.

This is just one example of working with Azure Machine Learning Studio. You can do so many things using this.

Check out: What is Azure Machine Learning Designer

Key Azure Machine Learning Features

Best Practices When Using Azure Machine Learning

• Use USA-based regions to minimize latency and comply with data residency laws.
• Leverage MLOps for lifecycle management and reproducibility.
• Automate model retraining with scheduled pipelines.
• Monitor models continuously to detect data drift.
• Secure endpoints with authentication keys and role-based access control.

FAQs

Which Azure service is used for machine learning?

Answer: Azure Machine Learning (Azure ML).

Conclusion

Azure Machine Learning offers powerful tools and flexibility to build, train, and deploy machine learning models efficiently. Whether you prefer a no-code visual interface or complete control with Python SDK, Azure ML has you covered.

Begin by setting up your workspace, select the method that best suits your expertise, and then follow the step-by-step tutorial above to deploy your first model.

You may also like the following articles below

• How to create Azure Machine Learning Workspace
• Azure Machine Learning pricing

Bijay Kumar

I am Bijay, a Microsoft MVP (10 times) having more than 17 years of experience in the software industry. During my IT career, I got a chance to share my expertise in SharePoint and Microsoft Azure, like Azure VM, Azure Active Directory, Azure PowerShell, etc. I hope you will learn from these Azure tutorials. Read more