Tag Azure data factory

1.    What is Azure Data Factory?

Azure Data factory is a cloud based ETL/ELT tool.

Azure Data Factory is a cloud-based integration service offered by Microsoft that lets you create data-driven workflows for orchestrating and automating data movement and data transformation overcloud. Data Factory services also offer to create and running data pipelines that move and transform data and then run the pipeline on a specified schedule.

2.    What is Linked Service?

A linked service is a connection to a specific service or data store that can either be a source of data, or a destination (also called target or sink).

A linked service will store the connection string, but also any method on how to authenticate with the service. Once a linked service is created, you can reuse it everywhere. For example, if you have a data warehouse in Azure SQL database, you will only need to define this connection once.

Linked services can be found in the Manage section of ADF Studio (lowest icon in the left menu bar.

There we can find the two linked services we created in the previous part:

3. What is the difference between Linked Service and Dataset?

Dataset:

Datasets can be considered as the source and target of a pipeline. A pipeline can have multiple Datasets, sometimes extracting a file, transforming it, and then writing it to a different folder within the same storage account. Thus a Dataset is just a term to describe tables, file storages, or ERP systems.

Linked Services:

Linked Services can be through of as the connection string, or the authorization that the pipeline uses to connect to a Dataset. A linked service can be the key value of a blob storage account, the username and password of a database, or a Service account that is used to log into a BW system. While it is possible to have more than one Linked Service attached to the same Dataset, usually you will see a one to one relationship.

4. What is Integration Runtime? What are the different type?

Integration runtime is the infrastructure that is used for computations. Azure Data Factory uses it to offer many integration capabilities. They can be data flows and data movement, activity dispatch, and SSIS package execution.

The most important integration runtime is the one we’ve been using all this time: the Azure-IR. Every installation of ADF has a default IR: the AutoResolveIntegrationRuntime. You can find it when you go to the Manage section of ADF and then click on Integration Runtimes.

There are 3 types of the integration runtime available in the Azure data factory. We can choose based upon our requirement the specific integration runtime best fitted in specific scenario. The three types are :

• Azure IR
• Self-hosted
• Azure-SSIS

Azure IR:

The Azure-IR is a fully managed, serverless compute service. You don’t have to do anything to manage, except pay for the duration it has been running compute. You can always use the default Azure-IR, but you can also create a new one.

In the new window, choose the option with “Azure, Self-Hosted”

In the next step, choose Azure again.

In the following screen, enter a name for the new IR. Also choose your closest region.

You can also configure the IR to use a Virtual Network, but this is an advanced setting

Keep in mind that billing for pipeline durations is several magnitudes higher when you’re using a virtual network. In the third pane, we can configure the compute power for data flows.

There are two main reasons to create your own Azure-IR:

• You want to specify a specific region for your compute. For example, if regulations specify your data can never leave a certain reason, you need to create your own Azure-IR located in that region.
• You want to specify a data flow runtime with different settings than the default one. Especially the Time To Live setting is something that is worth changing (shorter if you want to save on costs, longer if you don’t want to restart you cluster too often during development/debugging).

The Self-hosted IR

Suppose you have data on-premises that you need to access from ADF. How can ADF reach this data store when it is in the Azure cloud? The self-hosted IR provides us with a solution. You install the self-hosted IR on one of your local machines. This IR will then act as a gateway through which ADF can reach the on-premises data.

Another use case for the self-hosted IR is when you want to run compute on your own machines instead of in the Azure cloud. This might be an option if you want to save costs (the billing for pipeline durations is lower on the self-hosted IR than one the Azure-IR) or if you want to control everything yourself. ADF will then act as an orchestrator, while all of the compute is running on your own local servers.

After clicking on New then select Self-Hosted.

Specify the name of the Integration Runtime and click on create.

After the creation of IR open it and copy key 1 or key 2.

Paste that key into Installed Microsoft Integration Runtime On your PC.

After pasting the key click on Register.

The Azure-SSIS IR

ADF provides us with the opportunity to run Integration Services packages inside the ADF environment. This can be useful if you want to quickly migrate SSIS project to the Azure cloud, without a complete rewrite of your projects. The Azure-SSIS IR provides us with a scale-out cluster of virtual machines that can run SSIS packages. You create an SSIS catalog in either Azure SQL database or in Azure SQL Server Managed Instance.

5. What Are the different types of trigger in ADF?

Totally there are 3 types of triggers available in Azure Data Factory,

• Schedule triggers
• Tumbling window triggers
• Event triggers

Schedule Trigger:

Schedule triggers are common triggers that can execute a pipeline on the time schedule we set. Schedule triggers offer more flexibility by giving many options to schedule like Minute, Hour, Day(s), Week(s), or Month(s). We can define the start and end date for when the trigger should be active, and it will run only from the moment it is created. The schedule can also be set to run on future calendar dates and times like every 15th and last Saturday of the month or every month’s first and fourth Monday etc.

The New Trigger pane will open. The default trigger type is Schedule, but you can also choose Tumbling Window and Event:

Choose the start date, optionally an end date, and whether or not to activate the trigger immediately after you publish it:

Choose the recurrence, either minutes, hours, days, weeks, or months:

Depending on the recurrence you choose, you can also configure the advanced settings.

If you choose days, you can configure the times:

If you choose weeks, you can configure both the days and times:

Months has two options. You can either configure month days and times, such as the 15th day and the last day.

or week days and times, like the first Monday or the last Sunday.

Tumbling Window Trigger:

Tumbling window triggers run at a specific time or on a periodic interval from a mentioned start time. It is very useful compared to scheduled triggers when you are dealing with historical data to copy or move. For instance, if you want the data to be copied from the SQL database, it will take the pipeline to run in the past and get that piece of data copied. It works by breaking the tumbling window trigger for every hour (if you have defined it for 1 hour) and pass on the start/end time for each time window into the SQL query, post which the data between the start/end time are returned to be saved into a destination of your choice.

Tumbling window triggers have the same settings as schedule triggers for start date, end date, and activation. However, the recurrence setting is different, you can only choose minutes or hours:

You can also specify several advanced settings:

Event Triggers:

Using event-based triggers we can schedule to run the pipelines in response to an event from azure blob storage. The most common use case is configuring to events like file arrival or deletion in blob storage. Azure data factory works on its integration with Azure event grid which works on similar lines but slightly different methodology. Event-based triggers work with not only blob but with ADLS too. Event triggers work on many to many relationships, a single trigger can start multiple pipelines and multiple triggers can start a single pipeline.

Event triggers do not have settings for start date and end date, but you can choose whether or not to activate the trigger immediately after you publish it. The main settings for event triggers are container and blob path. Blob path can begin with a folder path and/or end with a file name or extension:

Trigger Now

Trigger now isn’t really a trigger type, it’s more like a trigger action. You can manually trigger a pipeline, just like debugging pipelines. After you have triggered a pipeline, you can to open up the Monitor page to check

the status and see the output.

Adding triggers to pipelines

Once you have created your triggers, open the pipeline that you want to trigger. From here, you can trigger now or click add trigger, then New/Edit:

This opens the add triggers pane, where you can select the trigger:

In the triggers tab, you can now see that the trigger has a pipeline attached to it, and you can click to activate it:

6. What are the ARM template in ADF? What are they used for?

ARM templates are a form of infrastructure as code, a concept where you define the infrastructure you need to be deployed. You no longer need to click around the portal creating virtual machines or writing scripts to deploy a storage account. Instead, the template defines the resources, and the Azure ARM management layer is responsible for creating the infrastructure.

These templates use a declarative syntax to let you define your deployment in the form of JSON (JavaScript Object Notation) files.

The primary benefits of using ARM are:

• Consistency: ARM provides a consistent way to create, deploy, and manage Azure resources.
• Modularity: ARM enables you to define your infrastructure as a set of reusable templates, making it easier to manage and maintain.
• Automation: ARM enables you to automate the deployment and management of your infrastructure, saving time and reducing errors. If you have deploy the pipeline on UAT and you want to do the same in production you can use this template.
• Tagging: ARM enables you to tag your resources, making it easier to organize, track, and manage them.

7. How do you deploy Data factory code to higher environment?

1. Create a feature branch
2. Create PR to merge code to Dev branch.
3. Publish the code from dev to generate Arm Templates.
4. This can trigger an automated CI-CD Dev-Ops pipeline to pass code to higher environments.

For More Details follow –

https://www.mssqltips.com/sqlservertip/6510/using-azure-devops-ci-cd-to-deploy-azure-data-factory-environments/

Azure Data Factory – Moving from Development to Production

8. What are the difficulties that you have faced while copying data from on premise to cloud? How do you resolve it?

There are following challenges:

Throughput/Speed:  

We face speed limit during data copy.

When you copy binary files and other files as-is, the copy data process is fast and simple, like copying files on your computer. You take one file, and copy it into a different location:

However, the copy data activity is powerful. You are not limited to copying files as-is, the copy data activity can do some pretty cool things during copying:

Serialization and deserialization can be explained as converting file formats during copying. For example, we can use a CSV file as a source and copy it into an Azure SQL Database destination. To do that, we need to read the source data in CSV format and transfer it as bits and bytes over the network (serialization), then convert that stream of bits and bytes to a SQL format so we can load it into our database (deserialization).

Now following setting change in copy activity can improve performance:

Enable Staging:

Compression and decompression can be explained as zipping and unzipping files during copying. You don’t need to first copy the file and then zip or unzip it. You just specify that the source is zipped and the destination is unzipped, or vice versa. Definitely it will improve copy performance.

Degree of Copy Parallelism:

The degree of copy parallelism value specifies the maximum number of connections that can read from your source or write to your sink in parallel. It will increase the copy activity of the throughput.

Data Integration Units (DIUs):

The more DIUs you specify, the more power you throw at the copy data activity. And the more power you throw at the copy data activity, the more you pay for it.

9. What are the different activities you have used in data factory?

Here are a few of the most used activities:

• Copy Data Activity to copy the data between datasets.
• ForEach Activity for looping.
• Get Metadata Activity that can provide metadata about any data source.
• Set Variable Activity to define and initiate variables within pipelines.
• Lookup Activity to do a lookup to get some values from a table/file.
• Wait Activity to wait for a specified amount of time before/in between the pipeline run.
• Validation Activity will validate the presence of files within the dataset.
• Web Activity to call a custom REST endpoint from an ADF pipeline.

10. Can you execute For-each inside another for-each activity?

No, inside for-each we cannot use another for each activity.

11. What are the different Metadata options that you get in Get Metadata activity?

You can specify the following metadata types in the Get Metadata activity field list to retrieve the corresponding information:

Metadata type	Description
itemName	Name of the file or folder.
itemType	Type of the file or folder. Returned value is File or Folder.
size	Size of the file, in bytes. Applicable only to files.
created	Created datetime of the file or folder.
lastModified	Last modified datetime of the file or folder.
childItems	List of subfolders and files in the given folder. Applicable only to folders. Returned value is a list of the name and type of each child item.
contentMD5	MD5 of the file. Applicable only to files.
structure	Data structure of the file or relational database table. Returned value is a list of column names and column types.
columnCount	Number of columns in the file or relational table.
exists	Whether a file, folder, or table exists. If exists is specified in the Get Metadata field list, the activity won’t fail even if the file, folder, or table doesn’t exist. Instead, exists: false is returned in the output.

To demonstrate Get Metadata activity at work, I will create a data flow with the following logic:

• Read the list of the files available in the source folder, using Get Metadata activity and pass this data to ForEach activity
• Within the ForEach activity, read the properties of each file, using another Get Metadata activity and pass it to conditional activity, to determine if the file has been modified within the last 7 days
• Copy each recently changed file into the destination database.

Here are the steps to create this data flow:

Next, click the ‘+New‘ button to add metadata field and select Child Items from the dropdown list-this field will produce names of the files in the csvfiles container:

Next, let’s add ForEach activity to our pipeline (I’ve named it as ForEach_AC), link it to the Success end of the Get_Folder_Metadata_ACactivity  and add the following expression to its Items text box: @activity(‘Get_Folder_Metadata_AC’).output.childItems. This expression will extract childItems values from the output of the Get_Folder_Metadata_AC activity:

Next, let us switch to Activities tab and click the Add activity button to start adding child tasks to the ForEach activity:

Let us switch to the Dataset tab to specify dataset details. Because this activity is going to receive its file name from the parent activity, its source needs to be a parameterized dataset. I have created a parameterized blob storage dataset (I have named it as blobSTG_DS3) with the FileName parameter.

Next, let’s return to Get_File_Metadata_AC activity, select dataset BlobSTG_DS3 dataset we just created and enter an expression @item().name into its FileName parameter text box. This expression is going to pass the next file name value from ForEach activity’s item collection to the BlobSTG_DS3 dataset:

Next, let’s add the fields Last modified and Item Name fields, using the New button- these fields will be required for the subsequent activities:

Next, let’s add If Condition activity (I’ve named it as CheckDate_AC) and link it to the Success end of the Get_File_Metadata_AC activity:

Let’s switch to the Settings tab and enter the following expression: @greaterOrEquals(activity(‘Get_File_Metadata_AC’).output.lastModified,adddays(utcnow(),-7)). This expression will check whether or not the Last modified field obtained from the previous activity falls within last 7 days period:

Next, switch to Activities tab and click Add If True Activity button, to start building tasks which will be executed when the condition evaluates to true:

Within child activities window, add a Copy activity (I’ve named it as Copy_Data_AC), select BlobSTG_DS3 dataset as its source and assign an expression @activity(‘Get_File_Metadata_AC’).output.itemName to its FileName parameter. This expression will ensure that next file name, extracted by Get_File_Metadata_AC activity is passed as the input file name for copy activity. Here’s the screenshot:

Next, switch to the Sink tab, select FactInternetSales_DS dataset we created earlier and enter following purge query for destination table – Delete from FactInternetSales. This will ensure that this activity doesn’t fail with duplicate key errors, in case the rows we’re transferring already exist in the destination table:

Finally, let’s click the navigation link at the top of the screen and return to the parent pipeline’s design screen:

Now that we have completed building data flow, we can test it. I will execute this pipeline twice to test the following scenarios:

• The first execution will be done with older files in the source container
• The second execution will be done with a newly modified file added to the source folder.

Let us open the blob storage page and ensure that all the files existing in its csvfiles container are dated more than 7 days from the execution date:

Let us start the pipeline in the debug mode and examine execution logs in the Output window:

As you can see from the logs, all the activities, except the copy activity has executed successfully. The copy activity did not run, because the files in the source container are older than 7 days.

Next, I will upload a new file, using Upload button from Azure portal’s blob storage page:

Let us execute the pipeline in a debug mode again and examine execution logs. As you can see from the logs, this execution included the copy activity as well, which is what we expected:

As usual, we will need to publish the changes, to ensure that they are permanent.

12. If you want to use the output by executing a query which activity shall you use?

• Lookup activity helps in retrieving lookup datasets from any Azure data factory-supported resources.
• From the database, we can get dataset using Table, Query, and Stored Procedure.

In the case of files stored in Azure storage:

In the case of data stored in the database:

13. How you can verify the presence of a file in storage?

Validation activity can be used to check the existence of a file.

Step-1:

Step – 2:

Step – 3:

You please make sure that you are passing the correct filename to @dataset().FileName parameter. Passing incorrect filename may be causing your validation activity to wait till timeout happens.

14. Have you used Execute Notebook Activity? How you pass parameters to your notebooks in execute notebook activity?

Using Base Parameter property we can pass parameters to notebook, incase parameters are not satisfied in activity, default values from the notebook will be executed.

15. How do you handle incremental Data in Data factory?

There are couple of ways to handle incremental data:

Delta data loading from database by using a watermark:

1. Define a watermark in your source database. A watermark is a column that has the last updated time stamp or an incrementing key.
2. The delta loading solution loads the changed data between an old watermark and a new watermark.

The workflow for this approach is depicted in the following diagram:

Example –

https://learn.microsoft.com/en-us/azure/data-factory/solution-template-delta-copy-with-control-table

Delta data loading from SQL DB by using the Change Tracking technology:

Change Tracking: A lightweight solution in SQL Server and Azure SQL Database, providing an efficient change tracking mechanism for applications.

It enables an application to easily identify data that was inserted, updated, or deleted.

The workflow for this approach is depicted in the following diagram:

Example  –

https://learn.microsoft.com/en-us/azure/data-factory/tutorial-incremental-copy-change-tracking-feature-powershell

Loading new and changed files only by using LastModifiedDate:

One can copy new and changed files only by using LastModifiedDate to the destination store.

1. ADF will scan all the files from the source store,
2. Apply the file filter by their LastModifiedDate,
3. Only copy the new and updated file since last time to the destination store.

Please be aware that if you let ADF scan huge amounts of files but you only copy a few files to the destination, this will still take a long time because of the file scanning process.

Example –

https://learn.microsoft.com/en-us/azure/data-factory/tutorial-incremental-copy-lastmodified-copy-data-tool

Using qlik replicate Tool:

Qlik Replicate empowers organizations to accelerate data replication, ingestion and streaming across a wide variety of heterogeneous databases, data warehouses, and big data platforms.

To know more just explore this tool.

16. How you send email notifications on your pipeline failure?

There are couple of ways to email notification:

1. Using Logic Apps with Web/Web hook activity
2. Alert and Metrics

Triggering the Logic App from ADF:

Suppose you have already created a pipeline with some activities in ADF.

Now we want to send an email if an error occurs within an activity. Add a web activity to the canvas and connect another activity to this new activity using the arrow. When the connection has been made, right-click on the connection to change it to a Failure precedence constraint.

This will change the color of the connector to red.

Now we need to go the Azure Logic App and copy the HTTP POST URL:

Paste this URL into the URL field in the settings pane of the Web activity. The method needs to be set to POST.

We also need to add a header, where we will set the Content-Type to application/json. In the body, we enter the following JSON (following the structure mentioned before):

We’re using system parameters to retrieve the name of the data factory and the name of the pipeline. All the other fields in the settings pane can be left as-is.

At the end of the pipeline, we can add a similar Web activity to send an email notifying users that the pipeline has finished successfully. This time we use the following body:

Now we can run the pipeline and wait to see if any emails come in:

Configuring Multiple Notifications

Suppose we have more than one single activity for which we want to send a notification if something goes wrong. The following won’t work in ADF:

Alert and Metrics:

Azure Data Factory pipeline run history can be accessed in the Studio of the respective Factory. The runs, inputs, outputs, and failure details will be available for each run.

Failed runs in a Data Factory Pipeline can be monitored by navigating to Monitor -> Alerts & metrics. You will need to identify the monitoring criteria to define the alert logic and evaluation period.

You can set up notification channels to get alerts and stay informed on violations. Azure Action groups enable you to group several notification channels and instantly notify failure alerts to multiple channels.

The image shown below displays a sample alert triggered using the alert rule configured in the Data Factory:

17. Describe the use of ADF in your project?

There are couple of things you can mention to your interviewer>

1. How you copy data from source
2. How you do data transformation (either using ADF or you call the Databrics notebook)
   1. If you mentioned ADF, just let them know are the different activity you have used for the same.
3. How you store the final data.
4. What you have done for performance improvement (Refer to Question -08)

Note – Remember several data transformation and cleaning ADF is not suitable that much, instead of that in organization people prefer those transformation work on Databrics Notebook.

So in short, Describe how many data source you have like csv, sql and other, how amny pipeline you have used in that project, what are the different transforma activity you have used in the same.

18. How do you test your pipeline when you have created code in feature branch?

Use Debug Mode – Whenever you are using any feature branch you have to use debug option.

Monitor Section –> Pipeline Runs –> Debug

19. Have you used Get metadata Activity? Can you give one use case for ‘child items’ property in get metadata activity?

Get the list of the files or folders from a specific location in Azure blob storage:

• Go to the data factory and create one pipeline. 
• Create a linked service which will point to the Azure blob storage location.
• Create a dataset for Azure blob storage using the linked service created in above steps.
• Select Getmetadata activity and go to the dataset tab. Under the dataset tab you will see the field dataset there select the dataset which we have created in above step to connect to the Azure blob storage.
• Scroll down and there you will see the attribute field list. In front of it you will see a plus sign click on it. Drop down box will appear, in this drop down box you will see multiple properties. Here for now just select the child items as we wanted to select all the list of file names and folder names available inside the folder location. Hence just select the child items.  This will return the list of all the folders and files available inside our pointed location along with their type.

• Our pipeline is now ready to run. Just go to the debug tab and click on the debug. This will execute the pipeline. It will take a few seconds based on the size of your folder and after that at the bottom pane you will see that your activity has been completed successfully.

Click on the output of the getmetadata activity. There you will see the output JSON with the property child items and in this child items you will see an array of file and folder names along with their type. For files you will see the type is file and for the folder you will see the type as  folder.

Iterate over list of files available inside folder in Azure storage location:

• For iterating over the file names you have to use the foreach activity. So let’s connect the output of getmetadata activity to the input of foreach activity. There you can iterate over the getmetadata output  which contains array of files names.
• Under the foreach activity setting tab you will see items field. In the items field provide the output of the getmetadata activity. This will be the array of filenames over which you want to iterate. 

Let’s see how you can get the last modified date of a file using getmetadata activity with an example.

• Under the dataset tab you will see another property with name field list. In front of this property you will see a plus sign click on thispPlus sign and add the property.
• Select the last modified date property from the dropdown.

• As in this case we want to get the last modified date of a file or folder that’s why we have selected the property last modified date which will pull out the last updated timestamp for a file or a folder.
• Our pipeline is almost ready to run. Just go to the debug tab and click on the debug. It will execute the pipeline for our demo purpose, we have just added one activity. This will show get-metadata activity output under the output tab.

Go to the output tab and open the output for getmetadata activity. You will see the JSON and here you can see that the last modified date property is giving you the last modified timestamp for your files or folder which you have selected in the dataset.

20. What are mapping and Wrangling data flow in Data Factory?

Mapping Data Flow –

• Mapping data flows are visually designed data transformations in Azure Data Factory.
• When there is a situation like you need to perform transformations using two or more datasets then you use a Mapping data flow.
• You can perform several transformations such as Filter, JOIN, Aggregate, Union, Lookup, Sort, etc using mapping data flows.
• Mapping data flows can be executed within ADF pipelines using data flow activities.
• Azure Data Factory handles the code transformation and execution of Mapping Data Flow behind the scenes.
• Mapping Data Flows activity can be created individually or within an Azure Data Factory pipeline.

Steps to create a Mapping Data Flow:

1. Open the Azure Data Factory using the Azure portal, then click on Author & Monitor

Click on the Author button then click on Data flows option. By clicking on three dots select New data flow option.

2. Select Mapping Data Flow. Click

Steps to build transformation logic in the data flow canvas:

Once you create your Data Flow, you’ll be automatically sent to the data flow canvas.

Note: The assumption is that you are already aware of the basic building blocks of a data factory- like creating linked services, Pipelines, etc.

1. In the data flow canvas, add a source by clicking on the Add Source

2. Name your source. Click on New to create a new source dataset.

3. Choose Azure Blob Storage. Click

4. Choose DelimitedText. Click Continue.

5. Name your dataset. Let’s say empDataDataset. In the linked service dropdown choose Linked service if you have created before or you can click +New button to create new linked service.

6. Once you’re back at the dataset creation window choose your File path. As the CSV file has headers, check First row as header. Select From connection/store to import the header schema directly from the file in storage. Click OK when done.

7. To add a transformation, click on the + icon on the data source which is next to your source node on the data flow canvas as specified in the screenshot below.

Transformation settings

The first tab in each transformation’s configuration pane contains the settings specific to that transformation. For more information, see that transformation’s documentation page.

Optimize

The Optimize tab contains settings to configure partitioning schemes.

21. Consider you have load data from 100 tables into another target, how would you design pipeline for the same?

So inorder to achive that, from system information schema get a list of tables and use foreach loop to copy the data from each table to target.

Now here is the important steps you need to keep in mind inorder to achive this process.

Understanding your data source.

i. Check the source data tables that have been asked to be copied.

ii. Determine the number of rows and columns (yes, columns matter) in each table to assess their size.

iii. Understand how the source tables change, their delta load logic.

iv. Know regular loading times for these source tables.

In this example, let source database = Oracle DB 1.

i. In this source, a daily truncate insert operation is performed on 47 tables. 42 of these tables have a size that is under 40 MB, making them relatively tiny. In contrast, 5 tables totaling more than 100 MB in size are considerably bigger.

ii. Each day, 8 large tables are loaded incrementally from the source.

iii. They all get updated somewhere between 1:50 to 2:20 AM.

Deciding how many pipelines to create.

When developing new pipelines, it is crucial to prioritize their long-term sustainability, especially when considering the possibility of having a large number of pipelines in production, potentially reaching thousands.

To maintain this, we will design pipelines such that each pipeline serves a single purpose. This does not imply that you should build a new pipeline for each table (avoid this) since there may be hundreds of them and you would not be able to maintain it. So what is a single purpose for a pipeline?

In this example, I will create 3 pipelines.

i. A pipeline that loads the 42 small daily full load tables.
ii. A pipeline that loads the 5 large daily full load tables.
iii. A pipeline that loads the 8 large incremental load tables.

Based on the size of the tables and the logic employed to edit them, this isolation is carried out.

How to create a good lookup source file.

The lookup activity that reads a lookup file from your storage explorer to obtain the list of tables it needs to load is the first task for each pipeline. Make your lookup files as detailed as necessary because they are what dynamically drives the remainder of your actions.

At least for me, the following fields must be filled out in the file.

i. source table name : the source table name that you are copying
ii. sink file name — the sink filename to be stored in your landing zone.
iii. delta load condition : The sql where condition to copy only modified data from source. For truncate and load tables, it could be where 1=1 or just blank. For delta tables, it could be anything, example where updated_at >= current_date() -1
iv. source job name : the source job name in charge of bringing up the source table.
v. target table name : Name of the target table in databricks

Three lookup files, one for each pipeline will be made in this pipeline. Here is an example of the lookup file created for 5 large full laod tables

Creating good data sets.

Like pipelines, you need to create datasets that are sustainable too.

In this example, we will create 3 datasets. Assume the linked services are already created.

i. One to read lookup files in storage account.
ii. One to define landing zone sink for copy activity.
iii. One to define source database for copy activity.

Do not create a unique dataset for each lookup file. It is better to have all of your lookup files in one folder inside a container and create a dataset where you can pass the filename dynamically from a pipeline. I am keeping all of my lookup files in a directory /meta/

Example, creating dataset:

Example, using dataset in pipeline:

How to set dependency the right way.

It becomes a challenge to set dependency in a pipeline that loads multiple tables at once because we cannot use event based triggers. So, how can you ensure that the data you are copying has been updated using time based triggers? Let me explain using this example:

As you can see from the preceding text, the source tables are changed between 1:50 and 2:20 AM. For 2:00 AM, I’ll construct a time-based trigger.

The data source owners will build a batch status table in which they will log a status each day after each table is updated. In our scenario, a vendor completes this.

I’ll construct a dynamic pipeline that determines whether a table status has been updated for today in this configuration table and waits until it hasn’t been changed.

By entering the tablename and batch name from my lookup activity for today, I will use this pipeline inside my foreach loop activity to determine if the source table has already been refreshed and wait if it has not.

Batch Check pipeline:

Usage :

[Optimization] Copying data the right way.

Although copying data is one of the easiest tasks in ADF, a lot can go wrong in this situation. Make sure that you are efficiently querying the source table and that you are just copying the necessary data.

After the batch check pipeline in this example, I’ll add a delete activity and a copy activity inside the foreach activity. If the sink file already exists, the delete activity will remove it, and the copy activity will copy the source file when I pass a dynamic delta load condition from my lookup file.

Two things to keep in mind:

Here, I’m turning off the for loop’s sequential options. This will guarantee that the copying processes take place concurrently. Avoid checking this. Consider that it takes 30 minutes for each of your five tables to be replicated to the landing zone. The total running time, if done sequentially, is 5 * 30 minutes.

Do not maintain old sink files, rather overwrite them. You don’t want to be logging into your storage account after a year and see 365*55 old sink files that have no use.

[Optimization] Working with Databricks notebook activity.

I used to believe that I would add a databricks notebook step within the for loop when a copy activity was complete to read the files from the landing zone and load my databricks table. My pipeline would be completed rapidly because these tasks would likewise be carried out concurrently.

NOTE – However this was not the case. Doing this could end badly for you and make your pipeline run longer. so You have to do this in optimise manner.

For small tables I will create a notebook that reads the lookup files and creates a dataframe, then iterates through the rows in the dataframe and loads each table from landing zone to databricks table. (this does not take as long as copy activity).

Let’s say you ran 40 notebooks in parallel, and each time only 4 notebooks would be able to make a successful request. Your retry interval is set to 3 minutes, So this would add N retries * 3 minutes to your pipeline runtime.

Can you do the same for large tables? Probably not. Because iterating through a dataframe and loading them one by one can take very long, so a single notebook will run longer. In this case, you might be better off running notebook calls in parallel inside the foreach activity. What you can do is batch large tables in different pipelines and then run a single notebook to load the tables in this batch at once.

Reference – https://medium.com/@ishanpradhan/constructing-and-improving-adf-pipelines-to-effectively-copy-multiple-tables-823a06caae14

22. How you can handle Full And Incremental Data Loading Concept From Source To Destination Using Azure Data Factory?

Objective: Our objective is to load data incrementally or fully from a source table to a destination table using Azure Data Factory Pipeline. First, we will go through the concept and design, and later the implementation steps using Azure Data Factory.

During the first run, the load activity is the full load of tables. Then, insert few records and perform the load activity once again which should be the incremental load. The configuration table data will updated automatically after the first run(full load), so that in second run it will automatically go for incremental load.

Development Process using Azure Data Factory:
1. First, create two Azure SQL DB resources: a. Source DB and b: Target DB
2. Create the Azure Data Factory resource.
3. Create the configuration Table.
4. Create two tables in the source DB e.g. customer table and transaction table.
5. Load data into the configuration table for customer table and transaction table. Load also an extra row for promotion table. After loading data it should be look like.

6. Load few data into the customer table and transaction table.
7. Go to the Azure Data Factory > Manage > Linked services > New and create two new linked services one for source and another for target.

8. Then, create two parameterized data set (Azure Data Factory > Author > Datasets > New dataset), one for source and another for target so that we can pass the table names on runtime from configuration table and this will help to handle multiple table using a single pipeline.

9. Go to the Azure Data Factory > Author > Pipeline > New Pipeline
10. First, create a lookup activity with query:
select * from [schema].[configuration table name] where Active_Indicator=1;
11. Create a For Each activity to iterate each table and perform activity(full or incremental load) for each table.

12. Then, create a If Condition activity, if ‘Incremental_Full_Load’ is 1, go for the ‘Incremental Load Activity’(associated with True value of if condition) else ‘Full Load Activity’(associated with False value of if condition).

13. Within the Incremental Load Activity,
a. first create a lookup to get the ‘Max_Last_Updated_Date’ from the configuration table for each desire table.
b. Then, using Copy Data activity, move data from source to target.
c. After that, using lookup activity, get the max value of the ‘added_date’ from the target table and update that value in the configuration table for the particular row for the particular ‘Table_Name’ value.

14. Within Full Load Activity, we will do step ‘b’ and step ‘c’. Only a small addition that we also update the ‘Max_Last_Updated_Date’ value to 1 in step ‘c’. So that, the fully loaded tables will automatically perform incremental load from second time.

Reference – https://apu-nandi88.medium.com/full-and-incremental-data-loading-concept-from-source-to-destination-using-azure-data-factory-dd39627d6f21

23. How do you handle duplicate rows in Data flows?

One of the most frequently asked questions in a data engineering interview. In this article let’s see how we can remove duplicate records.

Consider an employee table with duplicate records of an employee.

Select a Data flow activity to remove duplicate records.

Select a Dataset from the storage where data is placed in an Azure.

Preview all the records from the dataset.

Select the specific records and check the dataset columns.

Check the selected specific records.

Select the Windows function to segregate the duplicate records.

Preview the mapped data from the dataset.

Now filter the records where rownum ==1 as duplicate records are sorted with the latest entry first.

Preview the records where rownum=1.

Now add the nonduplicate records to the sink.

Preview the non-duplicate/unique records.

Now check the destination folder in the storage account.

Reference – https://nidhig631.medium.com/removal-of-duplicate-records-in-adf-azure-data-factory-e7da613d1c1c

24. If your input has column ‘Title’ and you get bad records in that column, how do you handle it?

Conditional split transformation defines the maximum length of “title” to be five. Any row that is less than or equal to five will go into the GoodRows stream. Any row that is larger than five will go into the BadRows stream.

Now we need to log the rows that failed. Add a sink transformation to the BadRows stream for logging. Here, we’ll “auto-map” all of the fields so that we have logging of the complete transaction record. This is a text-delimited CSV file output to a single file in Blob Storage. We’ll call the log file “badrows.csv”.

The completed data flow is shown below. We are now able to split off error rows to avoid the SQL truncation errors and put those entries into a log file. Meanwhile, successful rows can continue to write to our target database.

If you choose the error row handling option in the sink transformation and set “Output error rows”, ADF will automatically generate a CSV file output of your row data along with the driver-reported error messages. You do not need to add that logic manually to your data flow with that alternative option. There will be a small performance penalty incurred with this option so that ADF can implement a 2-phase methodology to trap errors and log them.

25. What is the difference between pipeline and Dataflow?

A pipeline is an orchestrator and does not tranform data. It manages a series of one or more activities, such as copy data or executive stored procedure. Data flow is one of these activity types and very different from a pipeline.

26. How you can open and read contents of a file in ADF?

We can use web activity and provide url of file that we want to read from the storage accoount. Output of the web activity contaains the response. Then we can use set variable activity to get the contents of the file in an output response.

27. If you want to Delete files in Blob storage how can you do that?

We can use delete activity in the pipeline and provide configurations for the files thet we want to delete. Alsso we can apply triggers if regular or event deletion is needed.

In this post, we’ll use the Azure Data Factory user interface (UX) to create a pipeline that copies and transforms data from an Azure Data Lake Storage (ADLS) Gen2 source to an ADLS Gen2 sink using mapping data flow. The configuration pattern in this tutorial can be expanded upon when transforming data using mapping data flow.

In this post, will do the following steps:

• Create a data factory.
• Create a pipeline with a Data Flow activity.
• Build a mapping data flow with four transformations.
• Test run the pipeline.
• Monitor a Data Flow activity

Prerequisites

• Azure subscription. If you don’t have an Azure subscription, create a free Azure account before you begin.
• Azure storage account. You use ADLS storage as a source and sink data stores.

Create a data factory

In this step, you create a data factory and open the Data Factory UX to create a pipeline in the data factory.

1. Open Microsoft Edge or Google Chrome. Currently, Data Factory UI is supported only in the Microsoft Edge and Google Chrome web browsers.
2. On the left menu, select Create a resource > Integration > Data Factory:

3. On the New data factory page, under Name, enter ADFTutorialDataFactory.

The name of the Azure data factory must be globally unique. If you receive an error message about the name value, enter a different name for the data factory. (for example, yournameADFTutorialDataFactory). 

4. Select the Azure subscription in which you want to create the data factory.

5. For Resource Group, take one of the following steps:

a. Select Use existing, and select an existing resource group from the drop-down list.

b. Select Create new, and enter the name of a resource group.

6. Under Version, select V2.

7. Under Location, select a location for the data factory. Only locations that are supported are displayed in the drop-down list. Data stores (for example, Azure Storage and SQL Database) and computes (for example, Azure HDInsight) used by the data factory can be in other regions.

8. Select Create.

9. After the creation is finished, you see the notice in Notifications center. Select Go to resource to navigate to the Data factory page.

10. Select Author & Monitor to launch the Data Factory UI in a separate tab.

Create a pipeline with a Data Flow activity

In this step, you’ll create a pipeline that contains a Data Flow activity.

1. On the home page of Azure Data Factory, select Orchestrate.

2. In the General tab for the pipeline, enter TransformMovies for Name of the pipeline.

3. In the Activities pane, expand the Move and Transform accordion. Drag and drop the Data Flow activity from the pane to the pipeline canvas.

4. In the Adding Data Flow pop-up, select Create new Data Flow and then name your data flow TransformMovies. Click Finish when done.

5. In the top bar of the pipeline canvas, slide the Data Flow debug slider on. Debug mode allows for interactive testing of transformation logic against a live Spark cluster. Data Flow clusters take 5-7 minutes to warm up and users are recommended to turn on debug first if they plan to do Data Flow development

Build transformation logic in the data flow canvas

Once you create your Data Flow, you’ll be automatically sent to the data flow canvas. In case you are not redirected to data flow canvas, in the panel below the canvas, go to Settings and select Open, located beside data flow field. This will open the dataflow canvas.

In this step, you’ll build a data flow that takes the moviesDB.csv in ADLS storage and aggregates the average rating of comedies from 1910 to 2000. You’ll then write this file back to the ADLS storage.

1. In the data flow canvas, add a source by clicking on the Add Source box.

2. Name your source MoviesDB. Click on New to create a new source dataset.

3. Choose Azure Data Lake Storage Gen2. Click Continue.

4. Choose DelimitedText. Click Continue.

5. Name your dataset MoviesDB. In the linked service dropdown, choose New.

6. In the linked service creation screen, name your ADLS gen2 linked service ADLSGen2 and specify your authentication method. Then enter your connection credentials. In this tutorial, we’re using Account key to connect to our storage account. You can click Test connection to verify your credentials were entered correctly.

7. Once you’re back at the dataset creation screen, enter where your file is located under the File path field. In this tutorial, the file moviesDB.csv is located in container sample-data. As the file has headers, check First row as header. Select From connection/store to import the header schema directly from the file in storage. Click OK when done.

8. If your debug cluster has started, go to the Data Preview tab of the source transformation and click Refresh to get a snapshot of the data. You can use data preview to verify your transformation is configured correctly.

9. Next to your source node on the data flow canvas, click on the plus icon to add a new transformation. The first transformation you’re adding is a Filter.

10. Name your filter transformation FilterYears. Click on the expression box next to Filter on to open the expression builder. Here you’ll specify your filtering condition.

11. The data flow expression builder lets you interactively build expressions to use in various transformations. Expressions can include built-in functions, columns from the input schema, and user-defined parameters.

In this tutorial, you want to filter movies of genre comedy that came out between the years 1910 and 2000. As year is currently a string, you need to convert it to an integer using the toInteger() function. Use the greater than or equals to (>=) and less than or equals to (<=) operators to compare against literal year values 1910 and 2000. Union these expressions together with the and (&&) operator. The expression comes out as:

toInteger(year) >= 1910 && toInteger(year) <= 2000

To find which movies are comedies, you can use the rlike() function to find pattern ‘Comedy’ in the column genres. Union the rlike expression with the year comparison to get:

toInteger(year) >= 1910 && toInteger(year) <= 2000 && rlike(genres, 'Comedy')

If you’ve a debug cluster active, you can verify your logic by clicking Refresh to see expression output compared to the inputs used. There’s more than one right answer on how you can accomplish this logic using the data flow expression language.

Click Save and Finish once you’re done with your expression.

12. Fetch a Data Preview to verify the filter is working correctly.

13. The next transformation you’ll add is an Aggregate transformation under Schema modifier.

14. Name your aggregate transformation AggregateComedyRatings. In the Group by tab, select year from the dropdown to group the aggregations by the year the movie came out.

15. Go to the Aggregates tab. In the left text box, name the aggregate column AverageComedyRating. Click on the right expression box to enter the aggregate expression via the expression builder.

16. To get the average of column Rating, use the avg() aggregate function. As Rating is a string and avg() takes in a numerical input, we must convert the value to a number via the toInteger() function. This is expression looks like:

avg(toInteger(Rating))

Click Save and Finish when done.

17. Go to the Data Preview tab to view the transformation output. Notice only two columns are there, year and AverageComedyRating.

18. Next, you want to add a Sink transformation under Destination.

19. Name your sink Sink. Click New to create your sink dataset.

20. Choose Azure Data Lake Storage Gen2. Click Continue.

21. Choose DelimitedText. Click Continue.

22. Name your sink dataset MoviesSink. For linked service, choose the ADLS gen2 linked service you created in step 6. Enter an output folder to write your data to. In this tutorial, we’re writing to folder ‘output’ in container ‘sample-data’. The folder doesn’t need to exist beforehand and can be dynamically created. Set First row as header as true and select None for Import schema. Click Finish.

Now you’ve finished building your data flow. You’re ready to run it in your pipeline.

Running and monitoring the Data Flow

You can debug a pipeline before you publish it. In this step, you’re going to trigger a debug run of the data flow pipeline. While data preview doesn’t write data, a debug run will write data to your sink destination.

1. Go to the pipeline canvas. Click Debug to trigger a debug run.

2. Pipeline debug of Data Flow activities uses the active debug cluster but still take at least a minute to initialize. You can track the progress via the Output tab. Once the run is successful, click on the eyeglasses icon to open the monitoring pane.

3. In the monitoring pane, you can see the number of rows and time spent in each transformation step.

4. Click on a transformation to get detailed information about the columns and partitioning of the data.

Reference – https://learn.microsoft.com/

Scenario:

I have a folder full of CSV files. Each file name is a date for which this file contains data (i.e. 2021-10-01T00:00:00Z). I want to organize these files into folders, with a time hierarchy. Meaning, the top level folders will be years (2022, 2023…), the second level will be months in this year (1,2,3…12), and the next level will be folders for a day in a month (1,2…30/31/28). Each day folder will contain one or many files with data referencing that day.

This Structure is important because it will enable you to use partitions when reading that data with tools like SQL serverless pool or spark pool in Synapse. You can read only the data required for the current query and save time and resources.

In this post, I’ll use Azure data factory to copy the files to the new structure. I’m assuming the files are already on an Azure storage account, in one container, and we want to build the new folder structure on another container.

Let’s launch data factory and create a new pipeline.

First, we’ll add 2 parameters, to hold the containers names (source and destination)

We’ll use a metadata activity to get a list of files in our source folder, so drag this activity into the canvas.

In the new metadata activity, on the settings tab, under “field list” click on new and add “child items”.

Create a dataset to your source folder of type blob storage or data lake storage. Set your container to the parameter we added. Leave the directory and file name blank. The file type can be binary since we are only copying the files, and not accessing their content in this pipeline.

Now add a foreach activity, and connect it with a success (green) link from the metadata activity.

On the items field, type in:

@activity('Get file names').output.childItems

This will make the foreach activity loop on each result (which is one for each file in the source folder)

Click on the + sign inside the foreach activity to add an activity that will run for each file, and then click “copy data”.

Click on the copy data activity you just added, to get It’s settings.

On the source tab, create a new dataset, with the same properties as the one we created for the metadata activity, except now we’ll add a parameter to the file name.

Use this dataset in the source tab. A new parameter appear under the dataset for the file name. Click on “dynamic content” and write @item().name . This expression will take the file name in each loop.

You can check “delete files after completion” if you want the source files to be removed after successful copy.

Now on the sink tab, we need to create a new dataset to our destination folder. I am using Azure data lake storage. This time we are creating a parameter on the container and folder parts, leaving the file name blank.

Back on the sink tab, you now can insert a value for the dataset parameters. For the folder value, Click on “dynamic content” and paste in this:

@concat(
  formatDateTime(item().name ,'yyyy'),
   '/',
   formatDateTime(item().name ,'MM'),
   '/',
  formatDateTime(item().name ,'dd')
)

Explaining the expression:

Item().name is the file on the current loop. Something like 2021-10-01T00:00:00Z.

formatDateTime extract part of the timestamp string,

and concat brings the all folder path together.

In our example, that will be 2021/10/1 (the / symbol show moving to a different folder level)

Our pipeline is ready, let click on debug to test it.

We’ll need to supply the parameters, which are the names of our source and destination containers.

Our pipeline works and copied the files to the right folders (while creating those folders)

Reference – https://www.madeiradata.com/

1.    What is Data Engineering?

Data Engineering is a field within the broader domain of data management that focuses on designing, building, and maintaining systems and infrastructure to support the collection, storage, processing, and analysis of large volumes of data. It plays a crucial role in the data lifecycle, ensuring that data is properly ingested, transformed, and made available for various data-driven applications and analytical processes.

The primary goal of data engineering is to create a robust and scalable data infrastructure that enables organizations to efficiently manage their data and extract meaningful insights from it. Data engineers are responsible for implementing data pipelines, integrating different data sources, and ensuring data quality and consistency. Here are some key aspects of data engineering:

1. Data Ingestion: Data engineers collect and ingest data from various sources, including databases, APIs, log files, sensors, and external systems. They design the data ingestion process to handle real-time or batch data streams, depending on the specific requirements of the organization.

2. Data Transformation: Raw data often needs to be processed and transformed into a usable format before it can be analyzed. Data engineers perform data transformations, such as data cleaning, enrichment, aggregation, and normalization, to make it suitable for analysis.

3. Data Storage: Data engineers choose appropriate storage solutions based on the volume, velocity, and variety of data. Common data storage technologies include relational databases, data warehouses, data lakes, and NoSQL databases.

4. Data Modeling: Data engineers create data models that define the structure and relationships of data within the organization. They may use data modeling techniques like entity-relationship diagrams or schema-on-read approaches to represent the data.

5. Data Governance and Security: Data engineers implement security measures and data governance policies to ensure data privacy, compliance with regulations, and data integrity.

6. ETL/ELT: ETL (Extract, Transform, Load) and ELT (Extract, Load, Transform) processes are crucial components of data engineering. ETL involves extracting data from various sources, transforming it, and then loading it into the target data storage. ELT involves loading raw data first and then performing transformations within the data storage system itself.

7. Big Data Technologies: In dealing with large-scale and high-velocity data, data engineers often work with big data technologies like Apache Hadoop, Apache Spark, and cloud-based data services.

Data engineering is fundamental for data-driven decision-making, business intelligence, machine learning, and various data analytics applications. It bridges the gap between raw data and meaningful insights, making it a crucial discipline in today’s data-driven world.

2.    What is Azure Synapse analytics?

As of my last update in September 2021, Azure Synapse Analytics is an integrated analytics service provided by Microsoft as part of the Azure cloud platform. It combines big data and data warehousing capabilities into a single solution, enabling organizations to ingest, prepare, manage, and serve data for business intelligence, machine learning, and real-time analytics purposes. Azure Synapse Analytics was formerly known as Azure SQL Data Warehouse but was rebranded and expanded to offer more comprehensive analytics capabilities.

1. Unified Data Platform: It brings together data integration, data warehousing, big data analytics, and data exploration capabilities into a single unified platform, allowing users to work with diverse data sources seamlessly.

Key features of Azure Synapse Analytics include:

2. Data Integration: Azure Synapse Analytics provides built-in connectors and integration with various data sources, both on-premises and in the cloud, making it easier to ingest and process data from different systems.

3. Data Warehousing: It offers a distributed, scalable, and fully managed data warehousing solution to store and manage large volumes of structured and semi-structured data.

4. Big Data Analytics: The service allows users to perform big data analytics using Apache Spark, enabling data engineers and data scientists to analyze and process large datasets efficiently.

5. Real-time Analytics: Azure Synapse Analytics can be integrated with Azure Stream Analytics, enabling real-time data ingestion and analytics for streaming data scenarios.

6. Machine Learning Integration: It integrates with Azure Machine Learning, facilitating the deployment and operationalization of machine learning models on large datasets.

7. Serverless On-Demand Queries: Users can run serverless SQL queries on data residing in various locations, making it easier to analyze data without requiring a dedicated data warehouse.

8. Power BI Integration: Azure Synapse Analytics seamlessly integrates with Power BI, Microsoft’s business analytics service, enabling users to create interactive reports and dashboards.

9. Security and Governance: The service provides robust security features, including role-based access control, encryption, and data masking, ensuring data privacy and compliance with industry standards.

Overall, Azure Synapse Analytics is designed to provide an end-to-end analytics solution for modern data-driven businesses, allowing them to gain insights from large and diverse datasets efficiently and effectively. However, please note that Microsoft may have introduced new features or updates to Azure Synapse Analytics beyond my last update, so it’s always a good idea to refer to the official Azure documentation for the most current information.

3. Explain the data masking feature of Azure?

Data masking in Azure is a security feature that helps protect sensitive information by obfuscating or hiding sensitive data from unauthorized users or applications. It is an essential part of data security and compliance strategies, ensuring that only authorized individuals can access the actual sensitive data while others are provided with masked or scrambled representations.

Azure provides various tools and services to implement data masking, and one of the primary services used for this purpose is Azure SQL Database. Here’s an overview of how data masking works in Azure:

1. Sensitive Data Identification: The first step in data masking is to identify the sensitive data that needs protection. This includes personally identifiable information (PII), financial data, healthcare data, or any other information that could pose a risk if accessed by unauthorized users.

2. Data Masking Rules: Once sensitive data is identified, data masking rules are defined to specify how the data should be masked. These rules can vary based on the type of data and the level of security required. For example, data might be partially masked, fully masked, or substituted with random characters.

3. Data Masking Operations: When data masking is enabled, the data in the specified columns is automatically masked based on the defined rules. This process happens at the database level, ensuring that applications and users interacting with the database only see the masked data.

4. Access Control: Access control mechanisms, such as role-based access control (RBAC) and permissions, are used to ensure that only authorized users have access to the original (unmasked) data. Access to the masked data is typically provided to users who do not require access to the actual sensitive information.

5. Dynamic Data Masking: In some cases, dynamic data masking is used, which allows administrators to define masking rules dynamically at query runtime based on the user’s privileges. This means that different users may see different masked versions of the data based on their access rights.

Data masking is particularly beneficial in scenarios where developers, testers, or support personnel need access to production data for testing or troubleshooting purposes but should not be exposed to actual sensitive information. By using data masking, organizations can strike a balance between data privacy and the practical need to use realistic datasets for various purposes.

It’s important to note that while data masking provides an additional layer of security, it is not a substitute for robust access controls, encryption, or other security measures. A comprehensive data security strategy should include multiple layers of protection to safeguard sensitive information throughout its lifecycle.

4. Difference between Azure Synapse Analytics and Azure Data Lake Storage?

Feature	Azure Synapse Analytics	Azure Data Lake Storage
Primary Purpose	Unified analytics service that combines big data and data warehousing capabilities.	Scalable and secure data lake storage for storing and managing large volumes of structured and unstructured data.
Data Processing	Provides data warehousing, big data analytics (using Apache Spark), and real-time data processing.	Primarily focused on storing and managing data; data processing is typically performed using separate services or tools.
Data Integration	Offers built-in connectors for integrating data from various sources for analysis.	Primarily focused on data storage, but data can be ingested and processed using other Azure services like Data Factory or Databricks.
Query Language	Supports T-SQL (Transact-SQL) for querying structured data and Apache Spark SQL for big data analytics.	No built-in query language; data is typically accessed and processed through other Azure services or tools.
Data Organization	Organizes data into dedicated SQL data pools and Apache Spark pools for different types of analytics.	Organizes data into hierarchical directories and folders, suitable for storing raw and processed data.
Data Security	Provides robust security measures for data protection, access control, and auditing.	Offers granular access control through Azure Active Directory, and data can be encrypted at rest and in transit.
Schema Management	Requires structured data with a predefined schema for SQL-based analytics.	Supports both structured and unstructured data, allowing schema-on-read for flexible data processing.
Use Cases	Suitable for data warehousing, big data analytics, and real-time analytics scenarios.	Ideal for big data storage, data exploration, data archiving, and serving as a data source for various data processing workloads.
Integration with Other Services	Integrates with other Azure services like Power BI, Azure Machine Learning, and Azure Stream Analytics.	Can be integrated with various Azure services like Data Factory, Databricks, and Azure HDInsight for data processing.

5. Describe various windowing functions of Azure Stream Analytics?

Azure Stream Analytics provides several windowing functions that help you perform calculations on data streams within specific time or event intervals. These functions enable you to perform time-based aggregations, sliding window computations, and more. Here are some of the key windowing functions available in Azure Stream Analytics:

Tumbling Windows:

• Tumbling windows divide the data stream into fixed-size, non-overlapping time intervals.
• Each event belongs to one and only one tumbling window based on its timestamp.
• Useful for performing time-based aggregations over distinct time intervals.

Hopping window

• Hopping windows are similar to tumbling windows but allow overlapping time intervals.
• You can specify the hop size and window size, determining how much overlap exists between adjacent windows.
• Useful for calculating aggregates over sliding time intervals.

Sliding window

• Sliding windows divide the data stream into fixed-size, overlapping time intervals.
• Unlike hopping windows, sliding windows always have an overlap between adjacent windows.
• You can specify the window size and the slide size.
• Useful for analyzing recent data while considering historical context.

With the following input data (illustrated above):

Session Windows:

• Session windows group events that are close together in time based on a specified gap duration.
• The gap duration is the maximum time interval between events that belong to the same session window.
• Useful for detecting and analyzing bursts or periods of activity in data streams.

With the following input data (illustrated above):

Snapshot window

Snapshot windows group events that have the same timestamp. Unlike other windowing types, which require a specific window function (such as SessionWindow()), you can apply a snapshot window by adding System.Timestamp() to the GROUP BY clause.

6. What are the different storage types in Azure?

The following are the various advantages of the Java collection framework:

Storage Types	Operations
Files	Azure Files is an organized way of storing data on the cloud. The main advantage of using Azure Files over Azure Blobs is that Azure Files allows for organizing the data in a folder structure. Also, Azure Files is SMB (Server Message Block) protocol compliant, i.e., and can be used as a file share.
Blobs	Blob stands for a large binary object. This storage solution supports all kinds of files, including text files, videos, images, documents, binary data, etc.
Queues	Azure Queue is a cloud-based messaging store for establishing and brokering communication between various applications and components.
Disks	The Azure disk is used as a storage solution for Azure VMs (Virtual Machines)
Tables	Tables are NoSQL storage structures for storing structured data that does not meet the standard RDBMS (relational database schema).

7. What are the different security options available in the Azure SQL database?

Azure SQL Database provides a range of security options to ensure the confidentiality, integrity, and availability of your data. These options are designed to protect your database from unauthorized access, data breaches, and other security threats. Here are some of the key security features available in Azure SQL Database:

1. Firewall Rules:

• Azure SQL Database allows you to configure firewall rules to control which IP addresses or IP address ranges can access your database.
• By default, all access from outside Azure’s datacenters is blocked until you define the necessary firewall rules.

2. Authentication:

• Azure SQL Database supports two types of authentications: SQL Authentication and Azure Active Directory Authentication.
• SQL Authentication uses usernames and passwords to authenticate users, while Azure Active Directory Authentication enables users to sign in with their Azure AD credentials.

3. Transparent Data Encryption (TDE):

• TDE automatically encrypts data at rest, providing an additional layer of security for your database.
• The data and log files are encrypted using a database encryption key, which is further protected by a service-managed certificate.

4. Always Encrypted:

• Always Encrypted is a feature that allows you to encrypt sensitive data in the database while keeping the encryption keys within your application.
• This ensures that even database administrators cannot access the plaintext data.

5. Auditing and Threat Detection:

• Azure SQL Database offers built-in auditing that allows you to track database events and store audit logs in Azure Storage.
• Threat Detection provides continuous monitoring and anomaly detection to identify potential security threats and suspicious activities.

6. Row-Level Security (RLS):

• RLS enables you to control access to rows in a database table based on the characteristics of the user executing a query.
• This feature is useful for implementing fine-grained access controls on a per-row basis.

7. Virtual Network Service Endpoints:

• With Virtual Network Service Endpoints, you can extend your virtual network’s private IP address space and route traffic securely to Azure SQL Database over the Azure backbone network.
• This helps to ensure that your database can only be accessed from specific virtual networks, improving network security.

8. Data Masking:

• Data Masking enables you to obfuscate sensitive data in query results, making it possible to share the data with non-privileged users without revealing the actual values.

9. Threat Protection:

• Azure SQL Database’s Threat Protection feature helps identify and mitigate potential database vulnerabilities and security issues.

10. Advanced Data Security (ADS):

• Advanced Data Security is a unified package that includes features like Vulnerability Assessment, Data Discovery & Classification, and SQL Injection Protection to enhance the overall security of your database.

By leveraging these security options, you can ensure that your Azure SQL Database remains protected against various security threats and maintain the confidentiality and integrity of your data. It is essential to configure and monitor these security features based on your specific requirements and compliance standards.

8. How data security is implemented in Azure Data Lake Storage(ADLS) Gen2?

Azure Data Lake Storage Gen2 (ADLS Gen2) provides robust data security features to protect data at rest and in transit. It builds on the security features of Azure Blob Storage and adds hierarchical namespace support, enabling it to function as both an object store and a file system. Here’s how data security is implemented in Azure Data Lake Storage Gen2:

1. Role-Based Access Control (RBAC):

• ADLS Gen2 leverages Azure RBAC to control access to resources at the Azure subscription and resource group levels.
• You can assign roles such as Storage Account Contributor, Storage Account Owner, or Custom roles with specific permissions to users, groups, or applications.

2. POSIX Access Control Lists (ACLs):

• ADLS Gen2 supports POSIX-like ACLs, allowing you to grant fine-grained access control to individual files and directories within the data lake.
• This enables you to define access permissions for specific users or groups, controlling read, write, and execute operations.

3. Shared Access Signatures (SAS):

• SAS tokens provide limited and time-bound access to specific resources in ADLS Gen2.
• You can generate SAS tokens with custom permissions and time constraints, which are useful for granting temporary access to external entities without exposing storage account keys.

4. Data Encryption:

• Data at rest is automatically encrypted using Microsoft-managed keys (SSE, Server-Side Encryption).
• Optionally, you can bring your encryption keys using customer-managed keys (CMEK) for an added layer of control.

5. Azure Private Link:

• ADLS Gen2 can be integrated with Azure Private Link, which allows you to access the service over a private, dedicated network connection (Azure Virtual Network).
• This helps to prevent data exposure to the public internet and enhances network security.

6. Firewall and Virtual Network Service Endpoints:

• ADLS Gen2 allows you to configure firewall rules to control which IP addresses or IP address ranges can access the data lake.
• Virtual Network Service Endpoints enable secure access to the data lake from within an Azure Virtual Network.

7. Data Classification and Sensitivity Labels:

• ADLS Gen2 supports Azure Data Classification and Sensitivity Labels, allowing you to classify and label data based on its sensitivity level.
• These labels can be used to enforce policies, auditing, and access control based on data classification.

8. Auditing and Monitoring:

• ADLS Gen2 offers auditing capabilities that allow you to track access to the data lake and log events for compliance and security monitoring.
• You can integrate ADLS Gen2 with Azure Monitor to get insights into the health and performance of the service.

By combining these security features, Azure Data Lake Storage Gen2 ensures that your data is protected from unauthorized access, tampering, and data breaches. It is crucial to configure these security options based on your specific data security requirements and compliance standards to safeguard your data effectively.

9. What are the various data flow partition schemes available in Azure?

Partition Scheme	Explanation	Usage
Round Robin	It is the most straightforward partition scheme which spreads data evenly across partitions.	No good key candidates were available in the data.
Hash	Hash of columns creates uniform partitions such that rows with similar values fall in the same partition.	It is used to check for partition skew.
Dynamic Range	Spark dynamics range based on the provided columns or expression.	Select the column that will be used for partitioning.
Fixed Range	A fixed range of values based on the user-created expression for disturbing data across partitions.	A good understanding of data is required to avoid partition skew.
Key	Partition for each unique value in the selected column.	Good understanding of data cardinality is required.

10. Why is the Azure data factory needed?

Azure Data Factory is a cloud-based data integration service provided by Microsoft Azure. It is designed to address the challenges of data movement and data orchestration in modern data-centric environments. The primary reasons why Azure Data Factory is needed are as follows:

1. Data Integration and Orchestration: In today’s data landscape, organizations often deal with data spread across various sources and formats, both on-premises and in the cloud. Azure Data Factory enables seamless integration and orchestration of data from diverse sources, making it easier to collect, transform, and move data between systems.

2. ETL (Extract, Transform, Load) Workflows: ETL processes are fundamental in data warehousing and analytics. Azure Data Factory allows you to create complex data workflows, where you can extract data from different sources, apply transformations, and load it into the target destination efficiently.

3. Serverless and Scalable: Azure Data Factory is a serverless service, meaning you don’t need to manage the underlying infrastructure. It automatically scales up or down based on demand, ensuring that you can process data of any volume without worrying about infrastructure limitations.

4. Integration with Azure Services: As part of the Azure ecosystem, Data Factory seamlessly integrates with other Azure services like Azure Blob Storage, Azure SQL Database, Azure Data Lake, Azure Databricks, etc. This integration enhances data processing capabilities and enables users to take advantage of Azure’s broader suite of analytics and storage solutions.

5. Data Transformation and Data Flow: Azure Data Factory provides data wrangling capabilities through data flows, allowing users to build data transformation logic visually. This simplifies the process of data cleansing, enrichment, and preparation for analytics or reporting.

6. Monitoring and Management: Azure Data Factory comes with built-in monitoring and management tools that allow you to track the performance of your data pipelines, troubleshoot issues, and set up alerts for critical events.

7. Hybrid Data Movement: For organizations with a hybrid cloud strategy or data stored on-premises, Azure Data Factory offers connectivity to on-premises data sources using a secure data gateway. This enables smooth integration of cloud and on-premises data.

8. Time Efficiency: Data Factory enables you to automate data pipelines and schedule data movements and transformations, reducing manual intervention and saving time in the data integration process.

Overall, Azure Data Factory plays a crucial role in simplifying data integration, enabling organizations to gain insights from their data, and facilitating the development of robust data-driven solutions in the Azure cloud environment.

11. What is Azure Data Factory?

Azure Data Factory is a cloud-based integration service offered by Microsoft that lets you create data-driven workflows for orchestrating and automating data movement and data transformation overcloud. Data Factory services also offer to create and running data pipelines that move and transform data and then run the pipeline on a specified schedule.

12. What is Integration Runtime?

Integration runtime is nothing but a compute structure used by Azure Data Factory to give integration capabilities across different network environments.

Types of Integration Runtimes:

• Azure Integration Runtime – It can copy data between cloud data stores and dispatch the activity to a variety of computing services such as SQL Server, Azure HDInsight
• Self Hosted Integration Runtime – It’s software with basically the same code as Azure Integration runtime, but it’s installed on on- premises systems or virtual machines over virtual networks.
• Azure SSIS Integration Runtime – It helps to execute SSIS packages in a managed environment. So when we lift and shift the SSIS packages to the data factory, we use Azure SSIS Integration Runtime.

13. What are the different components used in Azure Data Factory?

Azure Data Factory consists of several numbers of components. Some components are as follows:

• Pipeline: The pipeline is the logical container of the activities.
• Activity: It specifies the execution step in the Data Factory pipeline, which is substantially used for data ingestion and metamorphosis.
• Dataset: A dataset specifies the pointer to the data used in the pipeline conditioning.
• Mapping Data Flow: It specifies the data transformation UI logic.
• Linked Service: It specifies the descriptive connection string for the data sources used in the channel conditioning.  Let‘s say we’ve an SQL server, so we need a connecting string connected to an external device, and we will mention the source and the destination for it.
• Trigger: It specifies the time when the pipeline will be executed.
• Control flow: It’s used to control the execution flow of the pipeline activities

14. What is the key difference between the Dataset and Linked Service in Azure Data Factory?

Dataset specifies a source to the data store described by the linked service. When we put data to the dataset from a SQL Server instance, the dataset indicates the table’s name that contains the target data or the query that returns data from dissimilar tables.

Linked service specifies a definition of the connection string used to connect to the data stores. For illustration, when we put data in a linked service from a SQL Server instance, the linked service contains the name for the SQL Server instance and the credentials used to connect to that case.

15. What is the difference between Azure Data Lake and Azure Data Warehouse?

Azure Data Lake	Data Warehouse
Data Lake is a capable way of storing any type, size, and shape of data.	Data Warehouse acts as a repository for already filtered data from a specific resource.
It is mainly used by Data Scientists.	It is more frequently used by Business Professionals.
It is highly accessible with quicker updates.	It becomes a pretty rigid and costly task to make changes in Data Warehouse.
It defines the schema after when the data is stored successfully.	Datawarehouse defines the schema before storing the data.
It uses ELT (Extract, Load and Transform) process.	It uses ETL (Extract, Transform and Load) process.
It is an ideal platform for doing in-depth analysis.	It is the best platform for operational users.

16. Difference between Data Lake Storage and Blob Storage.

Data Lake Storage	Blob Storage
It is an optimized storage solution for big data analytics workloads.	Blob Storage is general-purpose storage for a wide variety of scenarios. It can also do Big Data Analytics.
It follows a hierarchical file system.	It follows an object store with a flat namespace.
In Data Lake Storage, data is stored as files inside folders.	Blob storage lets you create a storage account. Storage account has containers that store the data.
It can be used to store Batch, interactive, stream analytics,  and machine learning data.	We can use it to store text files, binary data, media storage for streaming and general purpose data.

16. What are the steps to create an ETL process in Azure Data Factory?

The ETL (Extract, Transform, Load) process follows four main steps:

i) Connect and Collect: Connect to the data source/s and move data to local and crowdsource data storage.

ii) Data transformation using computing services such as HDInsight, Hadoop, Spark, etc.

iii) Publish: To load data into Azure data lake storage, Azure SQL data warehouse, Azure SQL databases, Azure Cosmos DB, etc.

iv)Monitor: Azure Data Factory has built-in support for pipeline monitoring via Azure Monitor, API, PowerShell, Azure Monitor logs, and health panels on the Azure portal.

17. What are the key differences between the Mapping data flow and Wrangling data flow transformation activities in Azure Data Factory?

In Azure Data Factory, the main dissimilarity between the Mapping data flow and the Wrangling data flow transformation activities is as follows

The Mapping data flow activity is a visually allowed data transformation activity that facilitates users to plan graphical data transformation logic. It does not need the users to be expert developers. It’s executed as an activity within the ADF pipeline on an ADF completely managed scaled-out Spark cluster.

On the other hand, the Wrangling data flow activity is a code–free data preparation activity. It’s integrated with Power Query Online to make the Power Query M functions available for data wrangling using spark execution.

18. Can we pass parameters to a pipeline run?

Yes definitely, we can very easily pass parameters to a pipeline run. Pipeline runs are the first-class, top-level concepts in Azure Data Factory. We can define parameters at the pipeline level, and then we can pass the arguments to run a pipeline.

You can also define default values for the parameters in the pipeline.

19. Can an activity in a pipeline consume arguments that are passed to a pipeline run?

Each activity within the pipeline can consume the parameter value that’s passed to the pipeline and run with the @parameter construct.

Parameters are a first-class, top-level concept in Data Factory. We can define parameters at the pipeline level and pass arguments as you execute the pipeline run on demand or using a trigger. 

20. Can an activity output property be consumed in another activity?

An activity output can be consumed in a subsequent activity with the @activity construct.

21. How do I gracefully handle null values in an activity output?

You can use the @coalesce construct in the expressions to handle the null values gracefully.

23. What has changed from private preview to limited public preview in regard to data flows?

There are a couple of things which have been changed mentioned below:

• You are no longer required to bring your own Azure Databricks Clusters.
• Data Factory will manage cluster creation and tear down process.
• We can still use Data Lake Storage Gen 2 and Blob Storage to store those files. You can use the appropriate linked services. You can also use the appropriate linked services for those of the storage engines.
• Blob data sets and Azure Data Lake storage gen 2 are separated into delimited text and Apache Parquet datasets.

24. What is Azure SSIS Integration Runtime?

Azure SSIS Integration is a fully managed cluster of virtual machines that are hosted in Azure and dedicated to run SSIS packages in the data factory. We can easily scale up the SSIS nodes by configuring the node size or scaled out by configuring the number of nodes on the Virtual Machine’s cluster.

We must create an SSIS integration runtime and an SSISDB catalog hosted in the Azure SQL server database or Azure SQL-managed instance before executing an SSIS package

25. An Azure Data Factory Pipeline can be executed using three methods. Mention these methods.

Methods to execute Azure Data Factory Pipeline:

• Debug Mode
• Manual execution using trigger now
• Adding schedule, tumbling window/event trigger

26. Can we monitor and manage Azure Data Factory Pipelines?

Yes, we can monitor and manage ADF Pipelines using the following steps:

• Click on the monitor and manage on the data factory tab.
• Click on the resource manager.
• Here, you will find- pipelines, datasets, and linked services in a tree format.

27. What are the steps involved in the ETL process?

ETL (Extract, Transform, Load) process follows four main steps:

• Connect and Collect – helps in moving the data on-premises and cloud source data stores
• Transform – lets users collect the data by using compute services such as HDInsight Hadoop, Spark etc.
• Publish – Helps in loading the data into Azure data warehouse, Azure SQL database, and Azure Cosmos DB etc
• Monitor – It helps support the pipeline monitoring via Azure Monitor, API and PowerShell, Log Analytics, and health panels on the Azure Portal.

28. What are the different ways to execute pipelines in Azure Data Factory?

There are three ways in which we can execute a pipeline in Data Factory:

• Debug mode can be helpful when trying out pipeline code and acts as a tool to test and troubleshoot our code.
• Manual Execution is what we do by clicking on the ‘Trigger now’ option in a pipeline. This is useful if you want to run your pipelines on an ad-hoc basis.
• We can schedule our pipelines at predefined times and intervals via a Trigger. As we will see later in this article, there are three types of triggers available in Data Factory. 

29. What is the purpose of Linked services in Azure Data Factory?

Linked services are used majorly for two purposes in Data Factory:

1. For a Data Store representation, i.e., any storage system like Azure Blob storage account, a file share, or an Oracle DB/ SQL Server instance.
2.  For Compute representation, i.e., the underlying VM will execute the activity defined in the pipeline. 

30. Can you Elaborate more on Data Factory Integration Runtime?

The Integration Runtime, or IR, is the compute infrastructure for Azure Data Factory pipelines. It is the bridge between activities and linked services. The linked Service or Activity references it and provides the computing environment where the activity is run directly or dispatched. This allows the activity to be performed in the closest region to the target data stores or computing Services.

The following diagram shows the location settings for Data Factory and its integration runtimes:

Azure Data Factory supports three types of integration runtime, and one should choose based on their data integration capabilities and network environment requirements.

1. Azure Integration Runtime: To copy data between cloud data stores and send activity to various computing services such as SQL Server, Azure HDInsight, etc.
2. Self-Hosted Integration Runtime: Used for running copy activity between cloud data stores and data stores in private networks. Self-hosted integration runtime is software with the same code as the Azure Integration Runtime but installed on your local system or machine over a virtual network. 
3. Azure SSIS Integration Runtime: You can run SSIS packages in a managed environment. So, when we lift and shift SSIS packages to the data factory, we use Azure SSIS Integration Runtime. 

31. What are ARM Templates in Azure Data Factory? What are they used for?

An ARM template is a JSON (JavaScript Object Notation) file that defines the infrastructure and configuration for the data factory pipeline, including pipeline activities, linked services, datasets, etc. The template will contain essentially the same code as our pipeline.

ARM templates are helpful when we want to migrate our pipeline code to higher environments, say Production or Staging from Development, after we are convinced that the code is working correctly.

32. What are the two types of compute environments supported by Data Factory to execute the transform activities?

Below are the types of computing environments that Data Factory supports for executing transformation activities: –

i) On-Demand Computing Environment: This is a fully managed environment provided by ADF. This type of calculation creates a cluster to perform the transformation activity and automatically deletes it when the activity is complete.

ii) Bring Your Environment: In this environment, you can use ADF to manage your computing environment if you already have the infrastructure for on-premises services. 

33. If you want to use the output by executing a query, which activity shall you use? 

Look-up activity can return the result of executing a query or stored procedure.

The output can be a singleton value or an array of attributes, which can be consumed in subsequent copy data activity, or any transformation or control flow activity like ForEach activity.

34. What are some useful constructs available in Data Factory?

• parameter: Each activity within the pipeline can consume the parameter value passed to the pipeline and run with the @parameter construct.
• coalesce: We can use the @coalesce construct in the expressions to handle null values gracefully.
• activity: An activity output can be consumed in a subsequent activity with the            @activity construct. 

35. Can we push code and have CI/CD (Continuous Integration and Continuous Delivery) in ADF?

Data Factory fully supports CI/CD of your data pipelines using Azure DevOps and GitHub. This allows you to develop and deliver your ETL processes incrementally before publishing the finished product. After the raw data has been refined into a business-ready consumable form, load the data into Azure Data Warehouse or Azure SQL Azure Data Lake, Azure Cosmos DB, or whichever analytics engine your business uses can point to from their business intelligence tools.

36. What do you mean by variables in the Azure Data Factory?

Variables in the Azure Data Factory pipeline provide the functionality to hold the values. They are used for a similar reason as we use variables in any programming language and are available inside the pipeline.

Set variables and append variables are two activities used for setting or manipulating the values of the variables. There are two types of variables in a data factory: –

i) System variables:  These are fixed variables from the Azure pipeline. For example, pipeline name, pipeline id, trigger name, etc. You need these to get the system information required in your use case.

ii) User variable: A user variable is declared manually in your code based on your pipeline logic.

37. What are the different activities you have used in Azure Data Factory?

Here you can share some of the significant activities if you have used them in your career, whether your work or college project. Here are a few of the most used activities :

1. Copy Data Activity to copy the data between datasets.
2. ForEach Activity for looping.
3. Get Metadata Activity that can provide metadata about any data source.
4. Set Variable Activity to define and initiate variables within pipelines.
5. Lookup Activity to do a lookup to get some values from a table/file.
6. Wait Activity to wait for a specified amount of time before/in between the pipeline run.
7. Validation Activity will validate the presence of files within the dataset.
8. Web Activity to call a custom REST endpoint from an ADF pipeline.

38. How can I schedule a pipeline?

You can use the time window or scheduler trigger to schedule a pipeline. The trigger uses a wall-clock calendar schedule, which can schedule pipelines periodically or in calendar-based recurrent patterns (for example, on Mondays at 6:00 PM and Thursdays at 9:00 PM).

 Currently, the service supports three types of triggers:

• Tumbling window trigger: A trigger that operates on a periodic interval while retaining a state.
• Schedule Trigger: A trigger that invokes a pipeline on a wall-clock schedule.
• Event-Based Trigger: A trigger that responds to an event. e.g., a file getting placed inside a blob.
  Pipelines and triggers have a many-to-many relationship (except for the tumbling window trigger). Multiple triggers can kick off a single pipeline, or a single trigger can kick off numerous pipelines.

39. How can you access data using the other 90 dataset types in Data Factory?

The mapping data flow feature allows Azure SQL Database, Azure Synapse Analytics, delimited text files from Azure storage account or Azure Data Lake Storage Gen2, and Parquet files from blob storage or Data Lake Storage Gen2 natively for source and sink data source. Use the Copy activity to stage data from any other connectors and then execute a Data Flow activity to transform data after it’s been staged.

40. Can a value be calculated for a new column from the existing column from mapping in ADF?

We can derive transformations in the mapping data flow to generate a new column based on our desired logic. We can create a new derived column or update an existing one when developing a derived one. Enter the name of the column you’re making in the Column textbox.

You can use the column dropdown to override an existing column in your schema. Click the Enter expression textbox to start creating the derived column’s expression. You can input or use the expression builder to build your logic.

41. How is the lookup activity useful in the Azure Data Factory?

In the ADF pipeline, the Lookup activity is commonly used for configuration lookup purposes, and the source dataset is available. Moreover, it retrieves the data from the source dataset and then sends it as the activity output. Generally, the output of the lookup activity is further used in the pipeline for making decisions or presenting any configuration as a result.

Simply put, lookup activity is used for data fetching in the ADF pipeline. The way you would use it entirely relies on your pipeline logic. Obtaining only the first row is possible, or you can retrieve the complete rows depending on your dataset or query.

42. Elaborate more on the Get Metadata activity in Azure Data Factory.

The Get Metadata activity is used to retrieve the metadata of any data in the Azure Data Factory or a Synapse pipeline. We can use the output from the Get Metadata activity in conditional expressions to perform validation or consume the metadata in subsequent activities.

It takes a dataset as input and returns metadata information as output. Currently, the following connectors and the corresponding retrievable metadata are supported. The maximum size of returned metadata is 4 MB. 

Please refer to the snapshot below for supported metadata which can be retrieved using the Get Metadata activity.

43. What does it mean by the breakpoint in the ADF pipeline?

To understand better, for example, you are using three activities in the pipeline, and now you want to debug up to the second activity only. You can do this by placing the breakpoint at the second activity. To add a breakpoint, click the circle present at the top of the activity.

44. Can you share any difficulties you faced while getting data from on-premises to Azure cloud using Data Factory?

One of the significant challenges we face while migrating from on-prem to the cloud is throughput and speed. When we try to copy the data using Copy activity from on-prem, the process rate could be faster, and hence we need to get the desired throughput. 

There are some configuration options for a copy activity, which can help in tuning this process and can give desired results.

i) We should use the compression option to get the data in a compressed mode while loading from on-prem servers, which is then de-compressed while writing on the cloud storage.

ii) Staging area should be the first destination of our data after we have enabled the compression. The copy activity can decompress before writing it to the final cloud storage buckets.

iii) Degree of Copy Parallelism is another option to help improve the migration process. This is identical to having multiple threads processing data and can speed up the data copy process.

There is no right fit-for-all here, so we must try different numbers like 8, 16, or 32 to see which performs well.

iv) Data Integration Unit is loosely the number of CPUs used, and increasing it may improve the performance of the copy process. 

45. How to copy multiple sheet data from an Excel file?

When using an Excel connector within a data factory, we must provide a sheet name from which we must load data. This approach is nuanced when we have to deal with a single or a handful of sheets of data, but when we have lots of sheets (say 10+), this may become a tedious task as we have to change the hard-coded sheet name every time!

However, we can use a data factory binary data format connector for this and point it to the Excel file and need not provide the sheet name/s. We’ll be able to use copy activity to copy the data from all the sheets present in the file.

46. Is it possible to have nested looping in Azure Data Factory?

There is no direct support for nested looping in the data factory for any looping activity (for each / until). However, we can use one for each/until loop activity which will contain an execute pipeline activity that can have a loop activity. This way, when we call the looping activity, it will indirectly call another loop activity, and we’ll be able to achieve nested looping.

47. How to copy multiple tables from one datastore to another datastore?

An efficient approach to complete this task would be:

• Maintain a lookup table/ file containing the list of tables and their source, which needs to be copied.
• Then, we can use the lookup activity and each loop activity to scan through the list.
• Inside the for each loop activity, we can use a copy activity or a mapping dataflow to copy multiple tables to the destination datastore.

48. What are some performance-tuning techniques for Mapping Data Flow activity?

We could consider the below set of parameters for tuning the performance of a Mapping Data Flow activity we have in a pipeline.

i) We should leverage partitioning in the source, sink, or transformation whenever possible. Microsoft, however, recommends using the default partition (size 128 MB) selected by the Data Factory as it intelligently chooses one based on our pipeline configuration.

Still, one should try out different partitions and see if they can have improved performance.

ii) We should not use a data flow activity for each loop activity. Instead, we have multiple files similar in structure and processing needs. In that case, we should use a wildcard path inside the data flow activity, enabling the processing of all the files within a folder.

iii) The recommended file format to use is ‘. parquet’. The reason being the pipeline will execute by spinning up spark clusters, and Parquet is the native file format for Apache spark thus, it will generally give good performance.

iv) Multiple logging modes are available: Basic, Verbose, and None.

We should only use verbose mode if essential, as it will log all the details about each operation the activity performs. e.g., It will log all the details of the operations performed for all our partitions. This one is useful when troubleshooting issues with the data flow.

The basic mode will give out all the necessary basic details in the log, so try to use this one whenever possible.

v)  Try to break down a complex data flow activity into multiple data flow activities. Let’s say we have several transformations between source and sink, and by adding more, we think the design has become complex. In this case, try to have it in multiple such activities, which will give two advantages:

• All activities will run on separate spark clusters, decreasing the run time for the whole task.
• The whole pipeline will be easy to understand and maintain in the future. 

49. What are some of the limitations of ADF?

Azure Data Factory provides great functionalities for data movement and transformations. However, there are some limitations as well.

i) We can’t have nested looping activities in the data factory, and we must use some workaround if we have that sort of structure in our pipeline. All the looping activities come under this: If, Foreach, switch, and until activities.

ii) The lookup activity can retrieve only 5000 rows at a time and not more than that. Again, we need to use some other loop activity along with SQL with the limit to achieve this sort of structure in the pipeline.

iii) We can have 40 activities in a single pipeline, including inner activity, containers, etc. To overcome this, we should modularize the pipelines regarding the number of datasets, activities, etc.

50. How are all the components of Azure Data Factory combined to complete an ADF task?

The below diagram depicts how all these components can be clubbed together to fulfill Azure Data Factory ADF tasks.

51. How do you send email notifications on pipeline failure?

There are multiple ways to do this:

1. Using Logic Apps with Web/Webhook activity.
   Configure a logic app that, upon getting an HTTP request, can send an email to the required set of people for failure. In the pipeline, configure the failure option to hit the URL generated by the logic app.
2. Using Alerts and Metrics from pipeline options.
   We can set up this from the pipeline itself, where we get numerous options for email on any activity failure within the pipeline.

52. Imagine you need to process streaming data in real time and store the results in an Azure Cosmos DB database. How would you design a pipeline in Azure Data Factory to efficiently handle the continuous data stream and ensure it is correctly stored and indexed in the destination database? 

Here are the steps to design a pipeline in Azure Data Factory to efficiently handle streaming data and store it in an Azure Cosmos DB database. 

1. Set up an Azure Event Hub or Azure IoT Hub as the data source to receive the streaming data. 
2. Use Azure Stream Analytics to process and transform the data in real time using Stream Analytics queries.
3. Write the transformed data to a Cosmos DB collection as an output of the Stream Analytics job.
4. Optimize query performance by configuring appropriate indexing policies for the Cosmos DB collection.
5. Monitor the pipeline for issues using Azure Data Factory’s monitoring and diagnostic features, such as alerts and logs.

54. How can one combine or merge several rows into one row in ADF? Can you explain the process?

In Azure Data Factory (ADF), you can merge or combine several rows into a single row using the “Aggregate” transformation. 

55. How do you copy data as per file size in ADF?

You can copy data based on file size by using the “FileFilter” property in the Azure Data Factory. This property allows you to specify a file pattern to filter the files based on size. 

Here are the steps you can follow to copy data based on the file size: 

• Create a dataset for the source and destination data stores.
• Now, set the “FileFilter” property to filter the files based on their size in the source dataset. 
• In the copy activity, select the source and destination datasets and configure the copy behavior per your requirement.
• Run the pipeline to copy the data based on the file size filter.

56. How can you insert folder name and file count from blob into SQL table?

You can follow these steps to insert a folder name and file count from blob into the SQL table: 

• Create an ADF pipeline with a “Get Metadata” activity to retrieve the folder and file details from the blob storage.
• Add a “ForEach” activity to loop through each folder in the blob storage.
• Inside the “ForEach” activity, add a “Get Metadata” activity to retrieve the file count for each folder.
• Add a “Copy Data” activity to insert the folder name and file count into the SQL table.
• Configure the “Copy Data” activity to use the folder name and file count as source data and insert them into the appropriate columns in the SQL table.
• Run the ADF pipeline to insert the folder name and file count into the SQL table.

57. What are the various types of loops in ADF?

Loops in Azure Data Factory are used to iterate over a collection of items to perform a specific action repeatedly. There are three major types of loops in Azure Data Factory: 

• For Each Loop: This loop is used to iterate over a collection of items and perform a specific action for each item in the collection. For example, if you have a list of files in a folder and want to copy each file to another location, you can use a For Each Loop to iterate over the list of files and copy each file to the target location.
• Until Loop: This loop repeats a set of activities until a specific condition is met. For example, you could use an Until Loop to keep retrying an operation until it succeeds or until a certain number of attempts have been made.
• While Loop: This loop repeats a specific action while a condition is true. For example, if you want to keep processing data until a specific condition is met, you can use a While Loop to repeat the processing until the condition is no longer true.

58. What is Data factory parameterization?

Data factory allows for parameterization of pipelines via three elements:

• Parameters
• Variables
• Expression

Parameter:

Parameters are simply input values for operations in data factory. Each action has a set of predefined parameters that need to be supplied.

Additionally, some blocks like pipeline and datasets allow you to define custom parameters.

Variables:

Variable, set values inside the pipelines using Set variable function. Variables are temporary values that are used within pipeline and workflow to control execution of the workflow.

Variable can be modified through expression using Set variable action during the execution of the work flow.

Variables support 3 data types: string, bool and array. We refer these user variable as below @variables(‘variableName’)

Expression:

Expression is a JSON based formula, which allow for modification of variable or any parameters for pipeline, action or connection in data factory.

Typical scenario:

Most common scenarios that mandate parameterization are:

• Dynamic input file name coming from external service
• Dynamic output table name
• Appending date to output
• Changing connection parameter name like database name
• Conditional programming
• And many more…

59. What are the different Slowly changing dimension types?

Star schema design theory refers to common SCD types. The most common are Type 1 and Type 2. In practice a dimension table may support a combination of history tracking methods, including Type 3 and Type 6.

Type 1 SCD:

A Type 1 SCD always reflects the latest values, and when changes in source data are detected, the dimension table data is overwritten. This design approach is common for columns that store supplementary values, like the email address or phone number of a customer. When a customer email address or phone number changes, the dimension table updates the customer row with the new values. It’s as if the customer always had this contact information. The key field, such as CustomerID, would stay the same so the records in the fact table automatically link to the updated customer record.

Type 2 SCD:

A Type 2 SCD supports versioning of dimension members. Often the source system doesn’t store versions, so the data warehouse load process detects and manages changes in a dimension table. In this case, the dimension table must use a surrogate key to provide a unique reference to a version of the dimension member. It also includes columns that define the date range validity of the version (for example, StartDate and EndDate) and possibly a flag column (for example, IsCurrent) to easily filter by current dimension members.

Type 3 SCD:

A Type 3 SCD supports storing two versions of a dimension member as separate columns. The table includes a column for the current value of a member plus either the original or previous value of the member. So Type 3 uses additional columns to track one key instance of history, rather than storing additional rows to track each change like in a Type 2 SCD.

This type of tracking may be used for one or two columns in a dimension table. It is not common to use it for many members of the same table. It is often used in combination with Type 1 or Type 2 members.

Type 6 SCD:

A Type 6 SCD combines Type 1, 2, and 3. When a change happens to a Type 2 member you create a new row with appropriate StartDate and EndDate. In Type 6 design you also store the current value in all versions of that entity so you can easily report on the current value or the historical value.

Using the sales region example, you split the Region column into CurrentRegion and HistoricalRegion. The CurrentRegion always shows the latest value and the HistoricalRegion shows the region that was valid between the StartDate and EndDate. So for the same salesperson, every record would have the latest region populated in CurrentRegion while HistoricalRegion works exactly like the region field in the Type 2 SCD example.

60.What is the difference between the Mapping data flow and Wrangling data flow transformation activities in Data Factory?

Mapping data flow activity is a visually designed data transformation activity that allows us to design a graphical data transformation logic without the need to be an expert developer, and executed as an activity within the ADF pipeline on an ADF fully managed scaled-out Spark cluster.

Wrangling data flow activity is a code-free data preparation activity that integrates with Power Query Online in order to make the Power Query M functions available for data wrangling using spark execution.

61.When copying data from or to an Azure SQL Database using Data Factory, what is the firewall option that we should enable to allow the Data Factory to access that database?

Allow Azure services and resources to access this server firewall option.

62. Which activity should you use if you need to use the results from running a query?

A look-up activity can give you results from a query or a program. These results can be a single thing, a list of stuff, or something related to how your program works. You can then use these results in another copy data activity.

63. How are the remaining 90 dataset types in Data Factory used for data access?

You can easily use Azure Synapse Analytics, Azure SQL Database, and certain storage accounts for your data in the mapping data flow feature. It also supports Parquet files from blob storage or Data Lake Storage Gen2. However, for data from other sources, you’ll need to first copy it using the Copy activity before you can work with it in a Data Flow activity.

64. Give more details about the Azure Data Factory’s Get Metadata activity

The Azure Data Factory’s “Get Metadata” activity is a fundamental component of Azure Data Factory (ADF) that allows you to retrieve metadata information about various data-related objects within your data factory or linked services. Metadata includes information about datasets, tables, files, folders, or other data-related entities. Here are some key details about the Get Metadata activity:

Purpose:

• Metadata Retrieval: It is used to retrieve metadata information without moving or processing the actual data. This information can be used for control flow decisions, dynamic parameterization, or for designing complex data workflows.

Use Cases:

• Dynamic Execution: You can use the metadata retrieved by this activity to dynamically control which datasets or files to process or copy in subsequent activities.
• Validation: It can be used to check the existence of datasets or files before attempting to use them, ensuring your pipeline only processes existing resources.

Output:

• The Get Metadata activity outputs the metadata as structured JSON data, which includes details like file names, sizes, column names, table schemas, and more, depending on the metadata type and source.

Dynamic Expressions:

• You can use dynamic expressions within the activity configuration to parameterize your metadata retrieval. For example, you can use expressions to construct folder paths or table names at runtime.

In summary, the Get Metadata activity in Azure Data Factory is a powerful tool for gathering information about your data sources and structures, enabling dynamic and data-driven ETL (Extract, Transform, Load) workflows within your data factory pipelines. It helps you make informed decisions and perform data operations based on the state of your data sources.