Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon

How-To Tutorials - Data Science

7 Articles
article-image-building-trust-in-ai-the-role-of-rag-in-data-security-and-transparency
Keith Bourne
13 Dec 2024
15 min read
Save for later

Building Trust in AI: The Role of RAG in Data Security and Transparency

Keith Bourne
13 Dec 2024
15 min read
This article is an excerpt from the book, "Unlocking Data with Generative AI and RAG", by Keith Bourne. Master Retrieval-Augmented Generation (RAG), the most popular generative AI tool, to unlock the full potential of your data. This book enables you to develop highly sought-after skills as corporate investment in generative AI soars.IntroductionAs the adoption of Retrieval-Augmented Generation (RAG) continues to grow, its potential to address key security challenges in AI-driven applications is becoming evident. Far from merely introducing risks, RAG offers a robust framework to enhance data protection, ensure accuracy, and maintain transparency in content generation. This article delves into the multifaceted security benefits of RAG, while also addressing the unique challenges it poses and strategies to mitigate them.How RAG can be leveraged as a security solutionLet’s start with the most positive security aspect of RAG. RAG can actually be considered a solution to mitigate security concerns, rather than cause them. If done right, you can limit data access via user, ensure more reliable responses, and provide more transparency of sources.Limiting dataRAG applications may be a relatively new concept, but you can still apply the same authentication and database-based access approaches you can with web and similar types of applications. This provides the same level of security you can apply in these other types of applications. By implementing userbased access controls, you can restrict the data that each user or user group can retrieve through the RAG system. This ensures that sensitive information is only accessible to authorized individuals. Additionally, by leveraging secure database connections and encryption techniques, you can safeguard the data at rest and in transit, preventing unauthorized access or data breaches.Ensuring the reliability of generated contentOne of the key benefits of RAG is its ability to mitigate inaccuracies in generated content. By allowing applications to retrieve proprietary data at the point of generation, the risk of producing misleading or incorrect responses is substantially reduced. Feeding the most current data available through your RAG system helps to mitigate inaccuracies that might otherwise occur.With RAG, you have control over the data sources used for retrieval. By carefully curating and maintaining high-quality, up-to-date datasets, you can ensure that the information used to generate responses is accurate and reliable. This is particularly important in domains where precision and correctness are critical, such as healthcare, finance, or legal applications.Maintaining transparencyRAG makes it easier to provide transparency in the generated content. By incorporating data such as citations and references to the retrieved data sources, you can increase the credibility and trustworthiness of the generated responses.When a RAG system generates a response, it can include links or references to the specific data points or documents used in the generation process. This allows users to verify the information and trace it back to its original sources. By providing this level of transparency, you can build trust with your users and demonstrate the reliability of the generated content.Transparency in RAG can also help with accountability and auditing. If there are any concerns or disputes regarding the generated content, having clear citations and references makes it easier to investigate and resolve any issues. This transparency also facilitates compliance with regulatory requirements or industry standards that may require traceability of information.That covers many of the security-related benefits you can achieve with RAG. However, there are some security challenges associated with RAG as well. Let’s discuss these challenges next.RAG security challengesRAG applications face unique security challenges due to their reliance on large language models (LLMs) and external data sources. Let’s start with the black box challenge, highlighting the relative difficulty in understanding how an LLM determines its response.LLMs as black boxesWhen something is in a dark, black box with the lid closed, you cannot see what is going on in there! That is the idea behind the black box when discussing LLMs, meaning there is a lack of transparency and interpretability in how these complex AI models process input and generate output. The most popular LLMs are also some of the largest, meaning they can have more than 100 billion parameters. The intricate interconnections and weights of these parameters make it difficult to understand how the model arrives at a particular output.While the black box aspects of LLMs do not directly create a security problem, it does make it more difficult to identify solutions to problems when they occur. This makes it difficult to trust LLM outputs, which is a critical factor in most of the applications for LLMs, including RAG applications. This lack of transparency makes it more difficult to debug issues you might have in building an RAG application, which increases the risk of having more security issues.There is a lot of research and effort in the academic field to build models that are more transparent and interpretable, called explainable AI. Explainable AI aims at making the operations of A I systems transparent and understandable. It can involve tools, frameworks, and anything else that, when applied to RAG, helps us understand how the language models that we use produce the content they are generating. This is a big movement in the field, but this technology may not be immediately available as you read this. It will hopefully play a larger role in the future to help mitigate black box risk, but right now, none of the most popular LLMs are using explainable models. So, in the meantime, we will talk about other ways to address this issue.You can use human-in-the-loop, where you involve humans at different stages of the process to provide an added line of defense against unexpected outputs. This can often help to reduce the impact of the black box aspect of LLMs. If your response time is not as critical, you can also use an additional LLM to perform a review of the response before it is returned to the user, looking for issues. We will review how to add a second LLM call in code lab 5.3, but with a focus on preventing prompt attacks. But this concept is similar, in that you can add additional LLMs to do a number of extra tasks and improve the security of your application.Black box isn’t the only security issue you face when using RAG applications though; another very important topic is privacy protection.Privacy concerns and protecting user dataPersonally identifiable information (PII) is a key topic in the generative AI space, with governments a round the world trying to determine the best path to balance user privacy with the data-hungry needs of these LLMs. As this gets worked out, it is important to pay attention to the laws and regulations that are taking shape where your company is doing business and make sure all of the technologies you are integrating into your RAG applications adhere. Many companies, such as Google and Microsoft , are taking these efforts into their own hands, establishing their own standards of protection for their user data and emphasizing them in training literature for their platforms.At the corporate level, there is another challenge related to PII and sensitive information. As we have said many times, the nature of the RAG application is to give it access to the company data and combine that with the power of the LLM. For example, for financial institutions, RAG represents a way to give their customers unprecedented access to their own data in ways that allow them to speak naturally with technologies such as chatbots and get near-instant access to hard-to-find answers buried deep in their customer data.In many ways, this can be a huge benefit if implemented properly. But given that this is a security discussion, you may already see where I am going with this. We are giving unprecedented access to customer data using a technology that has artificial intelligence, and as we said previously in the black box discussion, we don’t completely understand how it works! If not implemented properly, this could be a recipe for disaster with massive negative repercussions for companies that get it wrong. Of course, it could be argued that the databases that contain the data are also a potential security risk. Having the data anywhere is a risk! But without taking on this risk, we also cannot provide the significant benefits they represent.As with other IT applications that contain sensitive data, you can forge forward, but you need to have a healthy fear of what can happen to data and proactively take measures to protect that data. The more you understand how RAG works, the better job you can do in preventing a potentially disastrous data leak. These steps can help you protect your company as well as the people who trusted your company with their data.This section was about protecting data that exists. However, a new risk that has risen with LLMs has been the generation of data that isn’t real, called hallucinations. Let’s discuss how this presents a new risk not common in the IT world.HallucinationsWe have discussed this in previous chapters, but LLMs can, at times, generate responses that sound coherent and factual but can be very wrong. These are called hallucinations and there have been many shocking examples provided in the news, especially in late 2022 and 2023, when LLMs became everyday tools for many users.Some are just funny with little consequence other than a good laugh, such as when ChatGPT was asked by a writer for The Economist, “When was the Golden Gate Bridge transported for the second time across Egypt?” ChatGPT responded, “The Golden Gate Bridge was transported for the second time across Egypt in October of 2016” (https://www.economist.com/by-invitation/2022/09/02/artificialneural-networks-today-are-not-conscious-according-to-douglashofstadter).Other hallucinations are more nefarious, such as when a New York lawyer used ChatGPT for legal research in a client’s personal injury case against Avianca Airlines, where he submitted six cases that had been completely made up by the chatbot, leading to court sanctions (https://www. courthousenews.com/sanctions-ordered-for-lawyers-who-relied-onchatgpt-artificial-intelligence-to-prepare-court-brief/). Even worse, generative AI has been known to give biased, racist, and bigoted perspectives, particularly when prompted in a manipulative way.When combined with the black box nature of these LLMs, where we are not always certain how and why a response is generated, this can be a genuine issue for companies wanting to use these LLMs in their RAG applications.From what we know though, hallucinations are primarily a result of the probabilistic nature of LLMs. For all responses that an LLM generates, it typically uses a probability distribution to determine what token it is going to provide next. In situations where it has a strong knowledge base of a certain subject, these probabilities for the next word/token can be 99% or higher. But in situations where the knowledge base is not as strong, the highest probability could be low, such as 20% or even lower. In these cases, it is still the highest probability and, therefore, that is the token that has the highest probability to be selected. The LLM has been trained on stringing tokens together in a very natural language way while using this probabilistic approach to select which tokens to display. As it strings together words with low probability, it forms sentences, and then paragraphs that sound natural and factual but are not based on high probability data. Ultimately, this results in a response that sounds very plausible but is, in fact, based on very loose facts that are incorrect.For a company, this poses a risk that goes beyond the embarrassment of your chatbot saying something wrong. What is said wrong could ruin your relationship(s) with your customer(s), or it could lead to the LLM offering your customer something that you did not intend to offer, or worse, cannot afford to offer. For example, when Microsoft released a chatbot named Tay on Twitter in 2016 with the intention of learning from interactions with Twitter users, users manipulated this spongy personality trait to get it to say numerous racist and bigoted remarks. This reflected poorly on Microsoft, which was promoting its expertise in the AI area with Tay, causing significant damage to its reputation at the time (https://www.theguardian.com/technology/2016/mar/26/microsoftdeeply-sorry-for-offensive-tweets-by-ai-chatbot).Hallucinations, threats related to black box aspects, and protecting user data can all be addressed through red teaming.ConclusionRAG represents a promising avenue for enhancing security in AI applications, offering tools to limit data access, ensure reliable outputs, and promote transparency. However, challenges such as the black box nature of LLMs, privacy concerns, and the risk of hallucinations demand proactive measures. By employing strategies like user-based access controls, explainable AI, and red teaming, organizations can harness the advantages of RAG while mitigating risks. As the technology evolves, a thoughtful approach to its implementation will be crucial for maintaining trust, compliance, and the integrity of data-driven solutions.Author BioKeith Bourne is a senior Generative AI data scientist at Johnson & Johnson. He has over a decade of experience in machine learning and AI working across diverse projects in companies that range in size from start-ups to Fortune 500 companies. With an MBA from Babson College and a master’s in applied data science from the University of Michigan, he has developed several sophisticated modular Generative AI platforms from the ground up, using numerous advanced techniques, including RAG, AI agents, and foundational model fine-tuning. Keith seeks to share his knowledge with a broader audience, aiming to demystify the complexities of RAG for organizations looking to leverage this promising technology.
Read more
  • 0
  • 0
  • 929

article-image-revolutionize-power-bi-queries-with-openai
Gus Frazer
11 Dec 2024
10 min read
Save for later

Revolutionize Power BI Queries with OpenAI

Gus Frazer
11 Dec 2024
10 min read
This article is an excerpt from the book, Data Cleaning with Power BI, by Gus Frazer. Unlock the full potential of your data by mastering the art of cleaning, preparing, and transforming data with Power BI for smarter insights and data visualizations.IntroductionDiscover the transformative potential of leveraging Azure OpenAI, integrated with ChatGPT functionality, to enhance Power BI's M query capabilities. In this article, we delve into how this powerful combination offers expert guidance, efficient solutions, and insightful recommendations for optimizing data transformation tasks. From generating M queries to streamlining complex transformations, explore how Azure OpenAI with ChatGPT empowers users to boost productivity and efficiency in Power BI.Using OpenAI for M queriesAzure OpenAI, with ChatGPT functionality within it, can be a helpful tool for generating M queries in Power BI by providing suggestions, helping with syntax, and offering insights into data transformation tasks. In the following example, you will learn about how you can leverage the chat playground within OpenAI to improve your productivity and efficiency when writing M queries. We will do this by asking a series of questions directly within Azure OpenAI.Complete the next steps to  follow along with the example in your own environment:1. Click on Deployment on the left-hand side and then select Create new deployment to get started.2. Select a model from the base models, in this case, select gpt-35-turbo, and then name your deployment. In this example, name it CleaningDataOpenAI.3. Select Chat playground from the Azure OpenAI Studio home screen or from the Playground tab on the left of your screen. This should open the following view:Figure 15.4 – Screenshot of the chat playground from within Azure OpenAINow that you have set up an instance of OpenAI, here’s an example conversation taken from OpenAI, where the chat functionality has been used to assist with writing M queries in Power BI:User: Hi, I’m working on a Power BI project, and I need to transform some data using M queries. I have a table with sales data, and I want to calculate the total sales for each product category. Can you help me with the M query for that?ChatGPT: Of course! To calculate the total sales for each product category, you can use the Group By transformation in Power BI’s Power Query Editor. Here’s a sample M snippet for your scenario:let Source = YourDataSource, GroupedTable = Table.Group(Source, {"ProductCategory"}, {{"TotalSales", each List.Sum([Sales]), type number}}) in GroupedTableReplace YourDataSource with the actual name of your data source. This code groups the data by the ProductCategory column and calculates the total sales for each group.User: Thanks! That’s a great starting point. What if I want to filter out products with sales less than $1,000  before calculating the total sales?ChatGPT: You can add a filtering step before the Group By transformation. Here’s an updated version of the M:let Source = YourDataSource, FilteredTable = Table.SelectRows(Source, each [Sales] >= 1000), GroupedTable = Table.Group(FilteredTable, {"ProductCategory"}, {{"TotalSales", each List.Sum([Sales]), type number}}) in GroupedTableThis code filters out rows where sales are less than $1,000 before grouping the data by product category and calculating the total sales.User: Perfect! This is really helpful. One more thing – what if I want to sort the results in descending order based on total sales?ChatGPT: You can add a sorting step using the Table.Sort function. Here’s the modified M:let Source = YourDataSource, FilteredTable = Table.SelectRows(Source, each [Sales] >= 1000), GroupedTable = Table.Group(FilteredTable, {"ProductCategory"}, {{"TotalSales", each List.Sum([Sales]), type number}}), SortedTable = Table.Sort(GroupedTable,{{"TotalSales", Order. Descending}}) in SortedTableThis code sorts the grouped table in descending order based on the “TotalSales” column.This interaction represents a simple example of how those who can leverage the power of tools such as OpenAI and C hatGPT will be able to quickly upskill in areas such as coding. It has to be said, though, that while this is still in its infancy, it’s important to always test and validate the answers provided before implementing them in production. Also, ensure that you take precautions when using the publicly available ChatGPT model to avoid sharing sensitive data publicly. If you would like to use sensitive data or you want to ensure that requests are given within a secured governed environment, make sure to use the ChatGPT model within your own Azure OpenAI instance.In more complex examples, optimizing Power Query transformations could involve efficient interaction with Azure OpenAI. This includes streamlining API calls, managing large datasets, and incorporating caching mechanisms for repetitive queries, ensuring a seamless and performant data cleaning process.As we begin to explore the use cases where this technology can be most effective, there are a number of clear early winners:Optimizing query plans: ChatGPT’s natural language understanding can assist in formulating more efficient Power Query plans. By describing the desired transformations in natural language, users can interact with ChatGPT to generate optimized query plans. This involves selecting the most suitable Power Query functions and structuring transformations for performance gains.Caching strategies for repetitive queries: ChatGPT can guide users in devising effective caching strategies. By understanding the context of data transformations, it can recommend where to implement caching mechanisms to store and reuse intermediate results, minimizing redundant API calls and computations. The following is an example of just this, where I have asked Azure OpenAI to verify and optimize my query from the Power Query Advanced Editor. The model suggested I use the Table.Buffer function to help cache the table in memory and optimize the query.Figure – An example request to OpenAI to help optimize my query for Power Query                                                        Figure – An example response from OpenAI to help optimize my query for Power QueryNow as we highlighted in Chapter 11, M Query Optimization, Table.Buffer can indeed improve the performance of your queries and refreshes, but this really depends on the data you are working with. In the previous example, the model doesn’t take the characteristics, size, or complexity of your data into consideration as it isn’t plugged into your data at this stage. Also linking back to the example you walked through in Chapter 11, the placement of where you add Table.Buffer can really impact how your query performs. In the previous example, if you were connecting to a small dataset, you would likely cause it to run slower by adding the Table.Buffer function as the second variable in the query.Lastly, it’s worth mentioning that how you prompt these models is crucially important. In the previous example, we didn’t specify what type of data source we were using in our query. As such, the model hasn’t provided an insight or overview that using Table.Buffer on a data source supporting query folding will cause it to break the fold. Again, this is not so much of a problem if Table.Buffer is placed at the end of your query for smaller datasets, but it is a problem if you add it nearer to the beginning of the query, like in the previous example.Handling large datasets: Dealing with large datasets often poses a challenge in Power Query. OpenAI models, including ChatGPT, can provide insights into dividing and conquering large datasets. This includes strategies for parallel processing, filtering data early in the transformation pipeline, and using aggregations to reduce computational load.Dynamic query adjustments: ChatGPT’s interactive nature allows users to dynamically adjust queries based on evolving requirements. It can assist in crafting queries that adapt to changing data scenarios, ensuring that Power Query transformations remain flexible and responsive to varied datasets.Guidance on complex transformations: Power Query oft en involves intricate transformations. ChatGPT can act as a virtual assistant, guiding users through the process of complex transformations. It can suggest optimal function compositions, advise on conditional logic placement, and assist in structuring transformations to enhance efficiency. The best example of this can be seen in the following two screenshots of an active use case seen in many businesses. The example begins with a user asking the model for a description of what the query is doing. OpenAI then provides a breakdown of what the query is doing in each step to help the user interpret the code. It helps to break down the barriers to coding and also helps to decipher code that has not been documented well by previous employees.                                                     Figure – An example request to OpenAI to help translate my queryFigure – An example response from OpenAI to help describe my queryError handling strategies: Optimizing Power Query also entails robust error handling. ChatGPT can provide recommendations for anticipating and handling errors gracefully within a query. This includes strategies for logging errors, implementing fallback mechanisms, and ensuring the stability of the overall data preparation process.In this section, you learned how to optimize Power Query transformations with Azure OpenAI efficiently. Key takeaways include using ChatGPT for natural-language-based query planning and effective caching strategies. Insights include handling large datasets through parallel processing, early filtering, and aggregations. This knowledge equips you to streamline and enhance your Power Query processes effectively.In the next section, you will learn about Microsoft  Copilot, how to set up a Power BI instance with Copilot activated, and also how you can use this new AI technology to help clean and prepare your data.ConclusionIn conclusion, Azure OpenAI with ChatGPT presents a game-changing solution for maximizing Power BI's potential. From query optimization to error-handling strategies, this integration streamlines processes and enhances productivity. As users navigate complex data transformations, the guidance provided fosters efficient decision-making and empowers users to tackle challenges with confidence. With Azure OpenAI and ChatGPT, the possibilities for revolutionizing Power BI workflows are endless, offering a glimpse into the future of data transformation and analytics.Author BioGus Frazer is a seasoned Analytics Consultant focused on Business Intelligence solutions. With over 7 years of experience working for the two market-leading platforms, Power BI & Tableau, has amassed a wealth of knowledge and expertise. Gus has helped hundreds of customers to drive their digital and data transformations, scope data requirements, drive actionable insights, and most important of all, cleanse data ready for analysis. Most recently helping to set up, organize and run the Power BI UK community at Microsoft. He holds 6 Azure and Power BI certifications, including the PL-300 and DP-500 certifications. In this book, Gus offers readers invaluable guidance on ingesting, preparing, and cleansing data for analysis in Power BI. --This text refers to an out of print or unavailable edition of this title.
Read more
  • 0
  • 0
  • 334

article-image-mastering-performance-tuning-with-dax-studio-and-vertipaq-analyzer
Thomas LeBlanc, Bhavik Merchant
03 Dec 2024
15 min read
Save for later

Mastering Performance Tuning with DAX Studio and VertiPaq Analyzer

Thomas LeBlanc, Bhavik Merchant
03 Dec 2024
15 min read
This article is an excerpt from the book, "Microsoft Power BI Performance Best Practices - Second Edition", by Thomas LeBlanc, Bhavik Merchant. Overcome common challenges in data management, visualization, and security with this updated edition of Microsoft Power BI Performance Best Practices, and ramp-up your Power BI solutions, achieve faster insights, and drive better business outcomes.IntroductionOptimizing performance and storage in Power BI and Analysis Services can be a complex task. However, tools like DAX Studio and VertiPaq Analyzer simplify this process by providing insightful metrics and performance-tuning capabilities. This article explores how to leverage these tools to analyze semantic models, identify performance bottlenecks, and optimize DAX queries. We'll discuss key features such as viewing model metrics, capturing and analyzing query traces, and testing optimizations using DAX Studio's query editor.Tuning with DAX Studio and VertiPaq AnalyserDAX Studio, as the name implies, is a tool centered on DAX queries. It provides a simple yet intuitive interface with powerful features to browse and query Analysis Services semantic models. We will cover querying later in this section. For now, let’s look deeper into semantic models.The Analysis Services engine has supported dynamic management views (DMVs) for over a decade. These views refer to SQL-like queries that can be executed on Analysis Services to return information about semantic model objects and operations.VertiPaq Analyzer is a utility that uses publicly documented DMVs to display essential information about which structures exist inside the semantic model and how much space they occupy. It started life as a standalone utility, published as a Power Pivot for an Excel workbook, and still exists in that form today. In this chapter, we will refer to its more recent incarnation as a built-in feature of DAX Studio 3.0.11.It is interesting to note that VertiPaq is the original name given to the compressed column store engine within Analysis Services (Verti referring to columns and Paq referring to compression).Analyzing model size with VertiPaq AnalyzerVertiPaq Analyzer is built into DAX Studio as the View Metrics features, found in the Advanced tab of the toolbar. You simply click the icon to have DAX Studio run the DMVs for you and display statistics in a tabular form. This is shown in the following figure:Figure 6.8 – Using View Metrics to generate VertiPaq Analyzer statsYou can switch to the Summary tab of the VertiPaq Analyzer pane to get an idea of the overall total size of the model along with other summary statistics, as shown in the following figure:Figure 6.9 – Summary tab of VertiPaq AnalyzerThe Total Size metric provided in the previous figure will often be larger than the size of the semantic model on disk (as a .pbix file or Analysis Services .abf backup). This is because there are additional structures required when the model is loaded into memory, which is particularly true of Import mode semantic models.In Chapter 2, Exploring Power BI Architecture and Configuration, we learned about Power BI’s compressed column storage engine. The DMV statistics provided by VertiPaq Analyzer let us see just how compressible columns are and how much space they are taking up. It also allows us to observe other objects, such as relationships.The Columns tab is a great way to see whether you have any columns that are very large relative to others or the entire dataset. The following figure shows the columns view for the same model we saw in Figure 6.9. You can see how from 238 columns, a single column called SalesOrderNumber takes up a staggering 22.40% of the whole model size! It’s interesting to see its Cardinality (or uniqueness) value is about twelve times lower than the next largest column (SalesKey):|Figure 6.10 – Two columns monopolizing the semantic modelIn Figure 6.10, we can also see that Data Type is String for Online Sale-SalesOrderNumber, which was a column suggested by Tabular Editor to have a large dictionary footprint. These statistics would lead you to deduce that this column contains long, unique test values that do not compress well because there is a large cardinality. Indeed, in this case, the column contains a sales order number that is unique to each order plus is not used to group or slice analytical data in a Power BI report well.This analysis may lead you to re-evaluate the need for this level of reporting in the analysis of sales data. You’d need to ask yourself whether the extra storage space and time taken to build compressed columns and potentially other structures is worth it for your business case. In cases of highly detailed data such as this where you do not need detail-level sales order data, consider limiting the analysis to customer-related data such as demographics or date attributes such as year and month.Now, let’s learn about how DAX Studio can help us with performance analysis and improvement.Performance tuning the data model and DAXThe first-party option for capturing Analysis Services traces is SQL Server Profiler. When starting a trace, you must identify exactly which events to capture, which requires some knowledge of the trace events and what they contain. Even with this knowledge, working with the trace data in Profi ler can be tough since the tool was designed primarily to work with SQL Server application traces. The good news is that DAX Studio can start an Analysis Services server trace and then parse and format all the data to show you relevant results in a well-presented way within its user interface. It allows us to both tune and measure queries in a single place and provides features for Analysis Services that make it a good alternative SQL profiler for tuning semantic models.Capturing and replaying queriesThis All Queries command in the Traces section of the DAX Studio toolbar will start a trace against the semantic model you have connected to. Figure 6.11 shows the result when a trace is successfully started:Figure 6.11 – Query trace successfully started in DAX StudioOnce your trace has started, you can interact with the semantic model outside DAX Studio, and it will capture queries for you. How you interact with the semantic model depends on where it is. For a semantic model running on your computer in Power BI Desktop, you would simply interact with the report. This would generate queries that DAX Studio will see. The All Queries tab at the bottom of the tool is where the captured queries are listed in time order with durations in milliseconds. The following figure shows two queries captured when opening the Unique by Account No page from the Slow vs Fast Measures.pbix sample file:Figure 6.12 – Queries captured by DAX StudioThe preceding queries come from a screen that has the same table results in a visual, but two different DAX measures that calculate the aggregation. These measures make one table come back in less than a second while the other returns in about 17 seconds. The following figure shows the page in the report:Figure 6.13 – Tables with the same results but from using different measuresThe following screenshot shows the results of the Performance Analyzer for the tables previously.Observe how one query took over 17 seconds, whereas the other took under 1 second:Figure 6.14 – Vastly different query durations for the same visual resultIn Figure 6.12, the second query was double-clicked to bring the DAX text to the editor. You can modify this query in DAX Studio to test performance changes. We see here that the DAX expression for the UniqueRedProducts_Slow measure was not efficient. We’ll learn a technique to optimize queries soon, but first, we need to learn about capturing query performance traces.Obtaining query timingsTo get detailed query performance information, you can use the Server Timings command shown in Figure 6.11. After starting the trace, you can run queries and then use the Server Timings tab to see how the engine executed the query, as shown in the following figure:Figure 6.15 – Server Timings showing detailed query performance statisticsFigure 6.15 gives very useful information. FE and SE refer to the formula engine and storage engine. The storage engine is fast and multi-threaded, and its job is fetching data. It can apply basic logic such as filtering data to retrieve only what is needed. The formula engine is single-threaded, and it generates a query plan, which is the physical steps required to compute the result. It also performs calculations on the data such as joins, complex filters, aggregations, and lookups. We want to avoid queries that spend most of the time in the formula engine, or that execute many queries in the storage engine. The bottom-left section of Figure 6.15 shows that we executed almost 4,900 SE queries. The list of queries to the right shows many queries returning only one result, which is suspicious.For comparison, we look at timing for the fastest version of the query and we see the following:Figure 6.16 – Server Timings for a fast version of the queryIn Figure 6.16, we can see that only three server engine queries were run this time, and the result was obtained much faster (milliseconds compared to seconds).The faster DAX measure was as follows:UniqueRedProducts_Fast = CALCULATE( DISTINCTCOUNT('SalesOrderDetail'[ProductID]), 'Product'[Color] = "Red" )The slower DAX measure was as follows:UniqueRedProducts_Slow = CALCULATE( DISTINCTCOUNT('SalesOrderDetail'[ProductID]), FILTER('SalesOrderDetail', RELATED('Product'[Color]) = "Red"))TipThe Analysis Services engine does use data caches to speed up queries. These caches contain uncompressed query results that can be reused later to save time fetching and decompressing data. You should use the Clear Cache button in DAX Studio to force these caches to be cleared and get a proper worst-case performance measure. This is visible in the menu bar in Figure 6.11.We will build on these concepts when we look at DAX and model optimizations in later chapters. Now, let’s look at how we can experiment with DAX and query changes in DAX Studio.Modifying and tuning queriesEarlier in this section, we saw how we could capture a query generated by a Power BI visual and then display its text. A nice trick we can use here is to use query-scoped measures to override the measure definition and see how performance differs.The following figure shows how we can search for a measure, right-click, and then pull its definition into the query editor of DAX Studio:Figure 6.17 – The Define Measure option and result in the Query paneWe can now modify the measure in the query editor, and the engine will use the local definition instead of the one defined in the model! This technique gives you a fast way to prototype DAX enhancements without having to edit them in Power BI and refresh visuals over many iterations.Remember that this technique does not apply any changes to the dataset you are connected to. You can optimize expressions in DAX Studio, then transfer the definition to Power BI Desktop/Visual Studio when ready. The following figure shows how we changed the definition of UniqueRedProducts_ Slow in a query-scoped measure to get a huge performance boast:Figure 6.18 – Modified measure giving better resultsThe technique described here can be adapted to model changes too. For example, if you wanted to determine the impact of changing a relationship type, you could run the same queries in DAX Studio before and after the change to draw a comparison.Here are some additional tips for working with DAX Studio:Isolate measure: When performance tuning a query generated by a report visual, comment out complex measures and then establish a baseline performance score. Th en, add each measure back to the query individually and check the speed. This will help identify the slowest measures in the query and visual context.Work with Desktop Performance Analyzer traces: DAX Studio has a facility to import the trace files generated by Desktop Performance Analyzer. You can import trace files using the Load Perf Data button located next to All Queries highlighted in Figure 6.12. This trace can be captured by one person and then shared with a DAX/modeling expert who can use DAX Studio to analyze and replay their behavior. The following figure shows how DAX Studio formats the data to make it easy to see which visual component is taking the most time. It was generated by viewing each of the three report pages in the Slow vs Fast Measures.pbix sample file:Figure 6.19 – Performance Analyzer trace shows the slowest visual in the reportExport/import model metrics: DAX Studio has a facility to export or import the VertiPaq model metadata using .vpax files. These files do not contain any of your data. They contain table names, column names, and measure definitions. If you are not concerned with sharing these definitions, you can provide .vpax files to others if you need assistance with model optimizationConclusionDAX Studio and VertiPaq Analyzer are indispensable tools for anyone working with Power BI or Analysis Services models. From detailed model size analysis to advanced performance tuning, these tools empower users to identify inefficiencies and implement optimizations effectively. By using their robust features, such as the ability to view metrics, trace query performance, and prototype query changes, professionals can ensure their models are both efficient and scalable. Mastery of these tools lays a solid foundation for building high-performing, resource-efficient analytical solutions.Author BioThomas LeBlanc is a seasoned Business Intelligence Architect at Data on the Geaux, where he applies his extensive skillset in dimensional modeling, data visualization, and analytical modeling to deliver robust solutions. With a Bachelor of Science in Management Information Systems from Louisiana State University, Thomas has amassed over 30 years of experience in Information Technology, transitioning from roles as a software developer and database administrator to his current expertise in business intelligence and data warehouse architecture and management.Throughout his career, Thomas has spearheaded numerous impactful projects, including consulting for various companies on Power BI implementation, serving as lead database administrator for a major home health care company, and overseeing the implementation of Power BI and Analysis Service for a large bank. He has also contributed his insights as an author to the Power BI MVP book.Thomas is recognized as a Microsoft Data Platform MVP and is actively engaged in the tech community through his social media presence, notably as TheSmilinDBA on Twitter and ThePowerBIDude on Bluesky and Mastodon. With a passion for solving real-world business challenges with technology, Thomas continues to drive innovation in the field of business intelligence.Bhavik Merchant has nearly 18 years of deep experience in Business Intelligence. He is currently the Director of Product Analytics at Salesforce. Prior to that, he was at Microsoft, first as a Cloud Solution Architect and then as a Product Manager in the Power BI Engineering team. At Power BI, he led the customer-facing insights program, being responsible for the strategy and technical framework to deliver system-wide usage and performance insights to customers. Before Microsoft, Bhavik spent years managing high-caliber consulting teams delivering enterprise-scale BI projects. He has provided extensive technical and theoretical BI training over the years, including expert Power BI performance training he developed for top Microsoft Partners globally.
Read more
  • 0
  • 0
  • 2900
Banner background image

article-image-mastering-transfer-learning-fine-tuning-bert-and-vision-transformers
Sinan Ozdemir
27 Nov 2024
15 min read
Save for later

Mastering Transfer Learning: Fine-Tuning BERT and Vision Transformers

Sinan Ozdemir
27 Nov 2024
15 min read
This article is an excerpt from the book, "Principles of Data Science", by Sinan Ozdemir. This book provides an end-to-end framework for cultivating critical thinking about data, performing practical data science, building performant machine learning models, and mitigating bias in AI pipelines. Learn the fundamentals of computational math and stats while exploring modern machine learning and large pre-trained models.IntroductionTransfer learning (TL) has revolutionized the field of deep learning by enabling pre-trained models to adapt their broad, generalized knowledge to specific tasks with minimal labeled data. This article delves into TL with BERT and GPT, demonstrating how to fine-tune these advanced models for text classification and image classification tasks. Through hands-on examples, we illustrate how TL leverages pre-trained architectures to simplify complex problems and achieve high accuracy with limited data.TL with BERT and GPTIn this article, we will take some models that have already learned a lot from their pre-training and fine-tune them to perform a new, related task. This process involves adjusting the model’s parameters to better suit the new task, much like fine-tuning a musical instrument:Figure 12.8 – ITLITL takes a pre-trained model that was generally trained on a semi-supervised (or unsupervised) task and then is given labeled data to learn a specific task.Examples of TLLet’s take a look at some examples of TL with specific pre-trained models.Example – Fine-tuning a pre-trained model for text classificationConsider a simple text classification problem. Suppose we need to analyze customer reviews and determine whether they’re positive or negative. We have a dataset of reviews, but it’s not nearly large enough to train a deep learning (DL) model from scratch. We will fine-tune BERT on a text classification task, allowing the model to adapt its existing knowledge to our specific problem.We will have to move away from the popular scikit-learn library to another popular library called transformers, which was created by HuggingFace (the pre-trained model repository I mentioned earlier) as scikit-learn does not (yet) support Transformer models.Figure 12.9 shows how we will have to take the original BERT model and make some minor modifications to it to perform text classification. Luckily, the transformers package has a built-in class to do this for  us called BertForSequenceClassification:Figure 12.9 – Simplest text classification caseIn many TL cases, we need to architect additional layers. In the simplest text classification case, we add a classification layer on top of a pre-trained BERT model so that it can perform the kind of classification we want.The following code block shows an end-to-end code example of fine-tuning BERT on a text classification task. Note that we are also using a package called datasets, also made by HuggingFace, to load a sentiment classification task from IMDb reviews. Let’s  begin by loading up the dataset:# Import necessary libraries from datasets import load_dataset from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments # Load the dataset imdb_data = load_dataset('imdb', split='train[:1000]') # Loading only 1000 samples for a toy example # Define the tokenizer tokenizer = BertTokenizer.from_pretrained('bert-base-uncased') # Preprocess the data def encode(examples): return tokenizer(examples['text'], truncation=True, padding='max_ length', max_length=512) imdb_data = imdb_data.map(encode, batched=True) # Format the dataset to PyTorch tensors imdb_data.set_format(type='torch', columns=['input_ids', 'attention_ mask', 'label'])With our dataset loaded up, we can run some training code to update our BERT model on our labeled data:# Define the model model = BertForSequenceClassification.from_pretrained( 'bert-base-uncased', num_labels=2) # Define the training arguments training_args = TrainingArguments( output_dir='./results', num_train_epochs=1, per_device_train_batch_size=4 ) # Define the trainer trainer = Trainer(model=model, args=training_args, train_dataset=imdb_ data) # Train the model trainer.train() # Save the model model.save_pretrained('./my_bert_model')Once we have our saved model, we can use the following code to run the model against unseen data:from transformers import pipeline # Define the sentiment analysis pipeline nlp = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer) # Use the pipeline to predict the sentiment of a new review review = "The movie was fantastic! I enjoyed every moment of it." result = nlp(review) # Print the result print(f"label: {result[0]['label']}, with score: {round(result[0] ['score'], 4)}") # "The movie was fantastic! I enjoyed every moment of it." # POSITIVE: 99%Example – TL for image classificationWe could take a pre-trained model such as ResNet or the Vision Transformer (shown in Figure 12.10), initially trained on a large-scale image dataset such as ImageNet. This model has already learned to detect various features from images, from simple shapes to complex objects. We can take advantage of this knowledge, fi ne-tuning  the model on a custom image classification task:Figure 12.10 – The Vision TransformerThe Vision Transformer is like a BERT model for images. It relies on many of the same principles, except instead of text tokens, it uses segments of images as “tokens” instead.The following code block shows an end-to-end code example of fine-tuning the Vision Transformer on an image classification task. The code should look very similar to the BERT code from the previous section because the aim of the transformers library is to standardize training and usage of modern pre-trained models so that no matter what task you are performing, they can offer a relatively unified training and inference experience.Let’s begin by loading up our data and taking a look at the kinds of images we have (seen in Figure 12.11). Note that we are only going to use 1% of the dataset to show that you really don’t need that much data to get a lot out of pre-trained models!# Import necessary libraries from datasets import load_dataset from transformers import ViTImageProcessor, ViTForImageClassification from torch.utils.data import DataLoader import matplotlib.pyplot as plt import torch from torchvision.transforms.functional import to_pil_image # Load the CIFAR10 dataset using Hugging Face datasets # Load only the first 1% of the train and test sets train_dataset = load_dataset("cifar10", split="train[:1%]") test_dataset = load_dataset("cifar10", split="test[:1%]") # Define the feature extractor feature_extractor = ViTImageProcessor.from_pretrained('google/vitbase-patch16-224') # Preprocess the data def transform(examples): # print(examples) # Convert to list of PIL Images examples['pixel_values'] = feature_ extractor(images=examples["img"], return_tensors="pt")["pixel_values"] return examples # Apply the transformations train_dataset = train_dataset.map( transform, batched=True, batch_size=32 ).with_format('pt') test_dataset = test_dataset.map( transform, batched=True, batch_size=32 ).with_format('pt')We can similarly use the model using the following code:Figure 12.11 – A single example from CIFAR10 showing an airplaneNow, we can train our pre-trained Vision Transformer:# Define the model model = ViTForImageClassification.from_pretrained( 'google/vit-base-patch16-224', num_labels=10, ignore_mismatched_sizes=True ) LABELS = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'] model.config.id2label = LABELS # Define a function for computing metrics def compute_metrics(p): predictions, labels = p preds = np.argmax(predictions, axis=1) return {"accuracy": accuracy_score(labels, preds)} # Define the training arguments training_args = TrainingArguments( output_dir='./results', num_train_epochs=5, per_device_train_batch_size=4, load_best_model_at_end=True, # Save and evaluate at the end of each epoch evaluation_strategy='epoch', save_strategy='epoch' ) # Define the trainer trainer = Trainer( model=model, args=training_args, train_dataset=train_dataset, eval_dataset=test_dataset )Our final model has about 95% accuracy on 1% of the test set. We can now use our new classifier on unseen images, as in this next code block:from PIL import Image from transformers import pipeline # Define an image classification pipeline classification_pipeline = pipeline( 'image-classification', model=model, feature_extractor=feature_extractor ) # Load an image image = Image.open('stock_image_plane.jpg') # Use the pipeline to classify the image result = classification_pipeline(image)Figure 12.12 shows the result of this single classification, and it looks like it did pretty well:Figure 12.12 – Our classifier predicting a stock image of a plane correctlyWith minimal labeled data, we can leverage TL to turn models off the shelf into powerhouse predictive models.ConclusionTransfer learning is a transformative technique in deep learning, empowering developers to harness the power of pre-trained models like BERT and the Vision Transformer for specialized tasks. From sentiment analysis to image classification, these models can be fine-tuned with minimal labeled data, offering impressive performance and adaptability. By using libraries like HuggingFace’s transformers, TL streamlines model training, making state-of-the-art AI accessible and versatile across domains. As demonstrated in this article, TL is not only efficient but also a practical way to achieve powerful predictive capabilities with limited resources.Author BioSinan is an active lecturer focusing on large language models and a former lecturer of data science at the Johns Hopkins University. He is the author of multiple textbooks on data science and machine learning including "Quick Start Guide to LLMs". Sinan is currently the founder of LoopGenius which uses AI to help people and businesses boost their sales and was previously the founder of the acquired Kylie.ai, an enterprise-grade conversational AI platform with RPA capabilities. He holds a Master’s Degree in Pure Mathematics from Johns Hopkins University and is based in San Francisco.
Read more
  • 0
  • 0
  • 1553

article-image-airflow-ops-best-practices-observation-and-monitoring
Dylan Intorf, Kendrick van Doorn, Dylan Storey
12 Nov 2024
15 min read
Save for later

Airflow Ops Best Practices: Observation and Monitoring

Dylan Intorf, Kendrick van Doorn, Dylan Storey
12 Nov 2024
15 min read
This article is an excerpt from the book, "Apache Airflow Best Practices", by Dylan Intorf, Kendrick van Doorn, Dylan Storey. With practical approach and detailed examples, this book covers newest features of Apache Airflow 2.x and it's potential for workflow orchestration, operational best practices, and data engineering.IntroductionIn this article, we will continue to explore the application of modern “ops” practices within Apache Airflow, focusing on the observation and monitoring of your systems and DAGs after they’ve been deployed.We’ll divide this observation into two segments – the core Airflow system and individual DAGs. Each segment will cover specific metrics and measurements you should be monitoring for alerting and potential intervention.When we discuss monitoring in this section, we will consider two types of monitoring – active and suppressive.In an active monitoring scenario, a process will actively check a service’s health state, recording its state and potentially taking action directly on the return value.In a suppressive monitoring scenario, the absence of a state (or state change) is usually meaningful. In these scenarios, the monitored application sends an active schedule to a process to inform it that it is OK, usually suppressing an action (such as an alert) from occurring.This chapter covers the following topics:Monitoring core Airflow componentsMonitoring your DAGsTechnical requirementsBy now, we expect you to have a good understanding of Airflow and its core components, along with functional knowledge in the deployment and operation of Airflow and Airflow DAGs.We will not be covering specific observability aggregators or telemetry tools; instead, we will focus on the activities you should be keeping an eye on. We strongly recommend that you work closely with your ops teams to understand what tools exist in your stack and how to configure them for capture and alerting your deployments.Monitoring core Airflow componentsAll of the components we will discuss here are critical to ensuring a functioning Airflow deployment. Generally, all of them should be monitored with a bare minimum check of Is it on? and if a component is not, an alert should surface to your team for investigation. The easiest way to check this is to query the REST API on the web server at `/health/`; this will return a JSON object that can be parsed to determine whether components are healthy and, if not, when they were last seen.SchedulerThis component needs to be running and working effectively in order for tasks to be scheduled for execution.When the scheduler service is started, it also starts a `/health` endpoint that can be checked by an external process with an active monitoring approach.The returned signal does not always indicate that the scheduler is working properly, as its state is simply indicative that the service is up and running. There are many scenarios where the scheduler may be operating but unable to schedule jobs; as a result, many deployments will include a canary dag to their deployment that has a single task, acting to suppress an external alert from going off.Import metrics that airflow exposes for you include the following:scheduler.scheduler_loop_duration: This should be monitored to ensure that your scheduler is able to loop and schedule tasks for execution. As this metric increases, you will see tasks beginning to schedule more slowly, to the point where you may begin missing SLAs because tasks fail to reach a schedulable state.scheduler.tasks.starving: This indicates how many tasks cannot be scheduled because there are no slots available. Pools are a mechanism that Airflow uses to balance large numbers of submitted task executions versus a finite amount of execution throughput. It is likely that this number will not be zero, but being high for extended periods of time may point to an issue in how DAGs are being written to schedule work.scheduler.tasks.executable: This indicates how many tasks are ready for execution (i.e., queued). This number will sometimes not be zero, and that is OK, but if the number increases and stays high for extended periods of time, it indicates that you may need additional computer resources to handle the load. Look at your executor to increase the number of workers it can run. Metadata databaseThe metadata database is used to store and track all of the metadata for your Airflow deployments’ previous DAG/task executions, along with information about your environment’s roles and permissions. Losing data from this database can interrupt normal operations and cause unintended consequences, with DAG runs being repeated.While critical, because it is architecturally ubiquitous, the database is also least likely to encounter issues, and if it does, they are absolutely catastrophic in nature.We generally suggest you utilize a managed service for provisioning and operating your backing database, ensuring that a disaster recovery plan for your metadata database is in place at all times.Some active areas to monitor on your database include the following:Connection pool size/usage: Monitor both the connection pool size and usage over time to ensure appropriate configuration, and identify potential bottlenecks or resource contention arising from Airflow components’ concurrent connections.Query performance: Measure query latency to detect inefficient queries or performance issues, while monitoring query throughput to ensure effective workload handling by the database.Storage metrics: Monitor the disk space utilization of the metadata database to ensure that it has sufficient storage capacity. Set up alerts for low disk space conditions to prevent database outages due to storage constraints.Backup status: Monitor the status of database backups to ensure that they are performed regularly and successfully. Verify backup integrity and retention policies to mitigate the risk of data loss if there is a database failure.TriggererThe Triggerer instance manages all of the asynchronous operations of deferrable operators in a deferred state. As such, major operational concerns generally relate to ensuring that individual deferred operators don’t cause major blocking calls to the event loop. If this occurs, your deferrable tasks will not be able to check their state changes as frequently, and this will impact scheduling performance.Import metrics that airflow exposes for you include the following:triggers.blocked_main_thread: The number of triggers that have blocked the main thread. This is a counter and should monotonically increase over time; pay attention to large differences between recording (or quick acceleration) counts, as it’s indicative of a larger problem.triggers.running: The number of triggers currently on a triggerer instance. This metric should be monitored to determine whether you need to increase the number of triggerer instances you are running. While the official documentation claims that up to tens of thousands of triggers can be on an instance, the common operational number is much lower. Tune at your discretion, but depending on the complexity of your triggers, you may need to add a new instance for every few hundred consistent triggers you run.Executors/workersDepending on the executor you use, you will need to monitor your executors and workers a bit differently.The Kubernetes executor will utilize the Kubernetes API to schedule tasks for execution; as such, you should utilize the Kubernetes events and metrics servers to gather logs and metrics for your task instances. Common metrics to collect on an individual task are CPU and memory usage. This is crucial for tuning requests or mutating individual task resource requests to ensure that they execute safely.The Celery worker has additional components and long-lived processes that you need to metricize. You should monitor an individual Celery worker’s memory and CPU utilization to ensure that it is not over- or under-provisioned, tuning allocated resources accordingly. You also need to monitor the message broker (usually Redis or RabbitMQ) to ensure that it is appropriately sized. Finally, it is critical to measure the queue length of your message broker and ensure that too much “back pressure” isn’t being created in the system. If you find that your tasks are sitting in a queued state for a long period of time and the queue length is consistently growing, it’s a sign that you should start an additional Celery worker to execute on scheduled tasks. You should also investigate using the native Celery monitoring tool Flower (https://flower.readthedocs.io/en/latest/) for additional, more nuanced methods of monitoring.Web serverThe Airflow web server is the UI for not just your Airflow deployment but also the RESTful interface. Especially if you happen to be controlling Airflow scheduling behavior with API calls, you should keep an eye on the following metrics:Response time: Measure the time taken for the API to respond to requests. This metric indicates the overall performance of the API and can help identify potential bottlenecks.Error rate: Monitor the rate of errors returned by the API, such as 4xx and 5xx HTTP status codes. High error rates may indicate issues with the API implementation or underlying systems.Request rate: Track the rate of incoming requests to the API over time. Sudden spikes or drops in request rates can impact performance and indicate changes in usage patterns.System resource utilization: Monitor resource utilization metrics such as CPU, memory, disk I/O, and network bandwidth on the servers hosting the API. High resource utilization can indicate potential performance bottlenecks or capacity limits.Throughput: Measure the number of successful requests processed by the API per unit of time. Throughput metrics provide insights into the API’s capacity to handle incoming traffic.Now that you have some basic metrics to collect from your core architectural components and can monitor the overall health of an application, we need to monitor the actual DAGs themselves to ensure that they function as intended.Monitoring your DAGsThere are multiple aspects to monitoring your DAGs, and while they’re all valuable, they may not all be necessary. Take care to ensure that your monitoring and alerting stack match your organizational needs with regard to operational parameters for resiliency and, if there is a failure, recovery times. No matter how much or how little you choose to implement, knowing that your DAGs work and if and how they fail is the first step in fixing problems that will arise.LoggingAirflow writes logs for tasks in a hierarchical structure that allows you to see each task’s logs in the Airflow UI. The community also provides a number of providers to utilize other services for backing log storage and retrieval. A complete list of supported providers is available at https://airflow.apache.org/docs/apache-airflow-providers/core-extensions/logging.html.Airflow uses the standard Python logging framework to write logs. If you’re writing custom operators or executing Python functions with a PythonOperator, just make sure that you instantiate a Python logger instance, and then the associated methods will handle everything for you.AlertingAirflow provides mechanisms for alerting on operational aspects of your executing workloads that can be configured within your DAG:Email notifications: Email notifications can be sent if a task is put into a marked or retry state with the `email_on_failure` or `email_on_retry` state, respectively. These arguments can be provided to all tasks in the DAG with the `default_args` key work in the DAG, or individual tasks by setting the keyword argument individually.Callbacks: Callbacks are special actions that are executed if a specific state change occurs. Generally, these callbacks should be thoughtfully leveraged to send alerts that are critical operationally:on_success_callback: This callback will be executed at both the task and DAG levels when entering a successful state. Unless it is critical that you know whether something succeeds, we generally suggest not using this for alerting.on_failure_callback: This callback is invoked when a task enters a failed state. Generally, this callback should always be set and, in critical scenarios, alert on failures that require intervention and support.on_execute_callback: This is invoked right before a task executes and only exists at the task level. Use sparingly for alerting, as it can quickly become a noisy alert when overused.on_retry_callback: This is invoked when a task is placed in a retry state. This is another callback to be cautious about as an alert, as it can become noisy and cause false alarms.sla_miss_callback: This is invoked when a DAG misses its defined SLA. This callback is only executed at the end of a DAG’s execution cycle so tends to be a very reactive notification that something has gone wrong.SLA monitoringAs awesome of a tool as Airflow is, it is a well-known fact in the community that SLAs, while largely functional, have some unfortunate details with regard to implementation that can make them problematic at best, and they are generally regarded as a broken feature in Airflow. We suggest that if you require SLA monitoring on your workflows, you deploy a CRON job monitoring tool such as healthchecks (https://github.com/healthchecks/healthchecks) that allows you to create suppressive alerts for your services through its rest API to manage SLAs. By pairing this third- party service with either HTTP operators or simple requests from callbacks, you can ensure that your most critical workflows achieve dynamic and resilient SLA alerting.Performance profilingThe Airflow UI is a great tool for profiling the performance of individual DAGs:The Gannt chart view: This is a great visualization for understanding the amount of time spent on individual tasks and the relative order of execution. If you’re worried about bottlenecks in your workflow, start here.Task duration: This allows you to profile the run characteristics of tasks within your DAG over a historical period. This tool is great at helping you understand temporal patterns in execution time and finding outliers in execution. Especially if you find that a DAG slows down over time, this view can help you understand whether it is a systemic issue and which tasks might need additional development.Landing times: This shows the delta between task completion and the start of the DAG run. This is an un-intuitive but powerful metric, as increases in it, when paired with stable task durations in upstream tasks, can help identify whether a scheduler is under heavy load and may need tuning.Additional metrics that have proven to be useful (but may need to be calculated) include the following:Task startup time: This is an especially useful metric when operating with a Kubernetes executor. To calculate this, you will need to calculate the difference between `start_date` and `execution_date` on each task instance. This metric will especially help you identify bottlenecks outside of Airflow that may impact task run times.Task failure and retry counts: Monitoring the frequency of task failures and retries can help identify information about the stability and robustness of your environment. Especially if these types of failure can be linked back to patterns in time or execution, it can help debug interactions with other services.DAG parsing time: Monitoring the amount of time a DAG takes to parse is very important to understand scheduler load and bottlenecks. If an individual DAG takes a long time to load (either due to heavy imports or long blocking calls being executed during parsing), it can have a material impact on the timeliness of scheduling tasks.ConclusionIn this article, we covered some essential strategies to effectively monitor both the core Airflow system and individual DAGs post-deployment. We highlighted the importance of active and suppressive monitoring techniques and provided insights into the critical metrics to track for each component, including the scheduler, metadata database, triggerer, executors/workers, and web server. Additionally, we discussed logging, alerting mechanisms, SLA monitoring, and performance profiling techniques to ensure the reliability, scalability, and efficiency of Airflow workflows. By implementing these monitoring practices and leveraging the insights gained, operators can proactively manage and optimize their Airflow deployments for optimal performance and reliability.Author BioDylan Intorf is a solutions architect and data engineer with a BS from Arizona State University in Computer Science. He has 10+ years of experience in the software and data engineering space, delivering custom tailored solutions to Tech, Financial, and Insurance industries.Kendrick van Doorn is an engineering and business leader with a background in software development, with over 10 years of developing tech and data strategies at Fortune 100 companies. In his spare time, he enjoys taking classes at different universities and is currently an MBA candidate at Columbia University.Dylan Storey has a B.Sc. and M.Sc. from California State University, Fresno in Biology and a Ph.D. from University of Tennessee, Knoxville in Life Sciences where he leveraged computational methods to study a variety of biological systems. He has over 15 years of experience in building, growing, and leading teams; solving problems in developing and operating data products at a variety of scales and industries.
Read more
  • 2
  • 0
  • 3026

article-image-vertex-ai-workbench-your-complete-guide-to-scaling-machine-learning-with-google-cloud
Jasmeet Bhatia, Kartik Chaudhary
04 Nov 2024
15 min read
Save for later

Vertex AI Workbench: Your Complete Guide to Scaling Machine Learning with Google Cloud

Jasmeet Bhatia, Kartik Chaudhary
04 Nov 2024
15 min read
This article is an excerpt from the book, "The Definitive Guide to Google Vertex AI", by Jasmeet Bhatia, Kartik Chaudhary. The Definitive Guide to Google Vertex AI is for ML practitioners who want to learn Google best practices, MLOps tooling, and turnkey AI solutions for solving large-scale real-world AI/ML problems. This book takes a hands-on approach to help you become an ML rockstar on Google Cloud Platform in no time.Introduction While working on an ML project, if we are running a Jupyter Notebook in a local environment, or using a web-based Colab- or Kaggle-like kernel, we can perform some quick experiments and get some initial accuracy or results from ML algorithms very fast. But we hit a wall when it comes to performing large-scale experiments, launching long-running jobs, hosting a model, and also in the case of model monitoring. Additionally, if the data related to a project requires some more granular permissions on security and privacy (fine-grained control over who can view/access the data), it’s not feasible in local or Colab-like environments. All these challenges can be solved just by moving to the cloud. Vertex AI Workbench within Google Cloud is a JupyterLab-based environment that can be leveraged for all kinds of development needs of a typical data science project. The JupyterLab environment is very similar to the Jupyter Notebook environment, and thus we will be using these terms interchangeably throughout the book. Vertex AI Workbench has options for creating managed notebook instances as well as user-managed notebook instances. User-managed notebook instances give more control to the user, while managed notebooks come with some key extra features. We will discuss more about these later in this section. Some key features of the Vertex AI Workbench notebook suite include the following: Fully managed–Vertex AI Workbench provides a Jupyter Notebook-based fully managed environment that provides enterprise-level scale without managing infrastructure, security, and user-management capabilities. Interactive experience–Data exploration and model experiments are easier as managed notebooks can easily interact with other Google Cloud services such as storage systems, big data solutions, and so on. Prototype to production AI–Vertex AI notebooks can easily interact with other Vertex AI tools and Google Cloud services and thus provide an environment to run end-to-end ML projects from development to deployment with minimal transition. Multi-kernel support–Workbench provides multi-kernel support in a single managed notebook instance including kernels for tools such as TensorFlow, PyTorch, Spark, and R. Each of these kernels comes with pre-installed useful ML libraries and lets us install additional libraries as required. Scheduling notebooks–Vertex AI Workbench lets us schedule notebook runs on an ad hoc and recurring basis. This functionality is quite useful in setting up and running large-scale experiments quickly. This feature is available through managed notebook instances. More information will be provided on this in the coming sections. With this background, we can now start working with Jupyter Notebooks on Vertex AI Workbench. The next section provides basic guidelines for getting started with notebooks on Vertex AI. Getting started with Vertex AI Workbench Go to the Google Cloud console and open Vertex AI from the products menu on the left pane or by using the search bar on the top. Inside Vertex AI, click on Workbench, and it will open a page very similar to the one shown in Figure 4.3. More information on this is available in the official  documentation (https://cloud.google.com/vertex-ai/docs/workbench/ introduction).  Figure 4.3 – Vertex AI Workbench UI within the Google Cloud console As we can see, Vertex AI Workbench is basically Jupyter Notebook as a service with the flexibility of working with managed as well as user-managed notebooks. User-managed notebooks are suitable for use cases where we need a more customized environment with relatively higher control. Another good thing about user-managed notebooks is that we can choose a suitable Docker container based on our development needs; these notebooks also let us change the type/size of the instance later on with a restart. To choose the best Jupyter Notebook option for a particular project, it’s important to know about the common differences between the two solutions. Table 4.1 describes some common differences between fully managed and user-managed notebooks: Table 4.1 – Differences between managed and user-managed notebook instances Let’s create one user-managed notebook to check the available options:  Figure 4.4 – Jupyter Notebook kernel configurations As we can see in the preceding screenshot, user-managed notebook instances come with several customized image options to choose from. Along with the support of tools such as TensorFlow Enterprise, PyTorch, JAX, and so on, it also lets us decide whether we want to work with GPUs (which can be changed later, of course, as per needs). These customized images come with all useful libraries pre-installed for the desired framework, plus provide the flexibility to install any third-party packages within the instance. After choosing the appropriate image, we get more options to customize things such as notebook name, notebook region, operating system, environment, machine types, accelerators, and so on (see the following screenshot):  Figure 4.5 – Configuring a new user-managed Jupyter Notebook Once we click on the CREATE button, it can take a couple of minutes to create a notebook instance. Once it is ready, we can launch the Jupyter instance in a browser tab using the link provided inside Workbench (see Figure 4.6). We also get the option to stop the notebook for some time when we are not using it (to reduce cost):  Figure 4.6 – A running Jupyter Notebook instance This Jupyter instance can be accessed by all team members having access to Workbench, which helps in collaborating and sharing progress with other teammates. Once we click on OPEN JUPYTERLAB, it opens a familiar Jupyter environment in a new tab (see Figure 4.7):  Figure 4.7 – A user-managed JupyterLab instance in Vertex AI Workbench A Google-managed JupyterLab instance also looks very similar (see Figure 4.8):  Figure 4.8 – A Google-managed JupyterLab instance in Vertex AI Workbench Now that we can access the notebook instance in the browser, we can launch a new Jupyter Notebook or terminal and get started on the project. After providing sufficient permissions to the service account, many useful Google Cloud services such as BigQuery, GCS, Dataflow, and so on can be accessed from the Jupyter Notebook itself using SDKs. This makes Vertex AI Workbench a one-stop tool for every ML development need. Note: We should stop Vertex AI Workbench instances when we are not using them or don’t plan to use them for a long period of time. This will help prevent us from incurring costs from running them unnecessarily for a long period of time. In the next sections, we will learn how to create notebooks using custom containers and how to schedule notebooks with Vertex AI Workbench. Custom containers for Vertex AI Workbench Vertex AI Workbench gives us the flexibility of creating notebook instances based on a custom container as well. The main advantage of a custom container-based notebook is that it lets us customize the notebook environment based on our specific needs. Suppose we want to work with a new TensorFlow version (or any other library) that is currently not available as a predefined kernel. We can create a custom Docker container with the required version and launch a Workbench instance using this container. Custom containers are supported by both managed and user-managed notebooks. Here is how to launch a user-managed notebook instance using a custom container: 1. The first step is to create a custom container based on the requirements. Most of the time, a derivative container (a container based on an existing DL container image) would be easy to set up. See the following example Dockerfile; here, we are first pulling an existing TensorFlow GPU image and then installing a new TensorFlow version from the source: FROM gcr.io/deeplearning-platform-release/tf-gpu:latest RUN pip install -y tensorflow2. Next, build and push the container image to Container Registry, such that it should be accessible to the Google Compute Engine (GCE) service account. See the following source to build and push the container image: export PROJECT=$(gcloud config list project --format "value(core.project)") docker build . -f Dockerfile.example -t "gcr.io/${PROJECT}/ tf-custom:latest" docker push "gcr.io/${PROJECT}/tf-custom:latest"Note that the service account should be provided with sufficient permissions to build and push the image to the container registry, and the respective APIs should be enabled. 3. Go to the User-managed notebooks page, click on the New Notebook button, and then select Customize. Provide a notebook name and select an appropriate Region and Zone value. 4. In the Environment field, select Custom Container. 5. In the Docker Container Image field, enter the address of the custom image; in our case, it would look like this: gcr.io/${PROJECT}/tf-custom:latest 6. Make the remaining appropriate selections and click the Create button. We are all set now. While launching the notebook, we can select the custom container as a kernel and start working on the custom environment. Conclusion Vertex AI Workbench stands out as a powerful, cloud-based environment that streamlines machine learning development and deployment. By leveraging its managed and user-managed notebook options, teams can overcome local development limitations, ensuring better scalability, enhanced security, and integrated access to Google Cloud services. This guide has explored the foundational aspects of working with Vertex AI Workbench, including its customizable environments, scheduling features, and the use of custom containers. With Vertex AI Workbench, data scientists and ML practitioners can focus on innovation and productivity, confidently handling projects from inception to production. Author BioJasmeet Bhatia is a machine learning solution architect with over 18 years of industry experience, with the last 10 years focused on global-scale data analytics and machine learning solutions. In his current role at Google, he works closely with key GCP enterprise customers to provide them guidance on how to best use Google's cutting-edge machine learning products. At Google, he has also worked as part of the Area 120 incubator on building innovative data products such as Demand Signals, and he has been involved in the launch of Google products such as Time Series Insights. Before Google, he worked in similar roles at Microsoft and Deloitte.When not immersed in technology, he loves spending time with his wife and two daughters, reading books, watching movies, and exploring the scenic trails of southern California.He holds a bachelor's degree in electronics engineering from Jamia Millia Islamia University in India and an MBA from the University of California Los Angeles (UCLA) Anderson School of Management.Kartik Chaudhary is an AI enthusiast, educator, and ML professional with 6+ years of industry experience. He currently works as a senior AI engineer with Google to design and architect ML solutions for Google's strategic customers, leveraging core Google products, frameworks, and AI tools. He previously worked with UHG, as a data scientist, and helped in making the healthcare system work better for everyone. Kartik has filed nine patents at the intersection of AI and healthcare.Kartik loves sharing knowledge and runs his own blog on AI, titled Drops of AI.Away from work, he loves watching anime and movies and capturing the beauty of sunsets.
Read more
  • 1
  • 1
  • 2524
Unlock access to the largest independent learning library in Tech for FREE!
Get unlimited access to 7500+ expert-authored eBooks and video courses covering every tech area you can think of.
Renews at $19.99/month. Cancel anytime
article-image-essential-sql-for-data-engineers
Kedeisha Bryan, Taamir Ransome
31 Oct 2024
10 min read
Save for later

Essential SQL for Data Engineers

Kedeisha Bryan, Taamir Ransome
31 Oct 2024
10 min read
This article is an excerpt from the book, Cracking the Data Engineering Interview, by Kedeisha Bryan, Taamir Ransome. The book is a practical guide that’ll help you prepare to successfully break into the data engineering role. The chapters cover technical concepts as well as tips for resume, portfolio, and brand building to catch the employer's attention, while also focusing on case studies and real-world interview questions.Introduction In the world of data engineering, SQL is the unsung hero that empowers us to store, manipulate, transform, and migrate data easily. It is the language that enables data engineers to communicate with databases, extract valuable insights, and shape data to meet their needs. Regardless of the nature of the organization or the data infrastructure in use, a data engineer will invariably need to use SQL for creating, querying, updating, and managing databases. As such, proficiency in SQL can often the difference between a good data engineer and a great one. Whether you are new to SQL or looking to brush up your skills, this chapter will serve as a comprehensive guide. By the end of this chapter, you will have a solid understanding of SQL as a data engineer and be prepared to showcase your knowledge and skills in an interview setting. In this article, we will cover the following topics: Must-know foundational SQL concepts Must-know advanced SQL concepts Technical interview questions Must-know foundational SQL concepts In this section, we will delve into the foundational SQL concepts that form the building blocks of data engineering. Mastering these fundamental concepts is crucial for acing SQL-related interviews and effectively working with databases. Let’s explore the critical foundational SQL concepts every data engineer should be comfortable with, as follows: SQL syntax: SQL syntax is the set of rules governing how SQL statements should be written. As a data engineer, understanding SQL syntax is fundamental because you’ll be writing and reviewing SQL queries regularly. These queries enable you to extract, manipulate, and analyze data stored in relational databases. SQL order of operations: The order of operations dictates the sequence in which each of the following operators is executed in a query: FROM and JOIN WHERE GROUP BY HAVING SELECT DISTINCT ORDER BY LIMIT/OFFSET Data types: SQL supports a variety of data types, such as INT, VARCHAR, DATE, and so on. Understanding these types is crucial because they determine the kind of data that can be stored in a column, impacting storage considerations, query performance, and data integrity. As a data engineer, you might also need to convert data types or handle mismatches. SQL operators: SQL operators are used to perform operations on data. They include arithmetic operators (+, -, *, /), comparison operators (>, <, =, and so on), and logical operators (AND, OR, and NOT). Knowing these operators helps you construct complex queries to solve intricate data-related problems. Data Manipulation Language (DML), Data Definition Language (DDL), and Data Control  Language (DCL) commands: DML commands such as SELECT, INSERT, UPDATE, and DELETE allow you to manipulate data stored in the database. DDL commands such as CREATE, ALTER, and DROP enable you to manage database schemas. DCL commands such as GRANT and REVOKE are used for managing permissions. As a data engineer, you will frequently use these commands to interact with databases. Basic queries: Writing queries to select, filter, sort, and join data is an essential skill for any data engineer. These operations form the basis of data extraction and manipulation. Aggregation functions: Functions such as COUNT, SUM, AVG, MAX, MIN, and GROUP BY are used to perform calculations on multiple rows of data. They are essential for generating reports and deriving statistical insights, which are critical aspects of a data engineer’s role. The following section will dive deeper into must-know advanced SQL concepts, exploring advanced techniques to elevate your SQL proficiency. Get ready to level up your SQL game and unlock new possibilities in data engineering! Must-know advanced SQL concepts This section will explore advanced SQL concepts that will elevate your data engineering skills to the next level. These concepts will empower you to tackle complex data analysis, perform advanced data transformations, and optimize your SQL queries. Let’s delve into must-know advanced SQL concepts, as follows: Window functions: These do a calculation on a group of rows that are related to the current row. They are needed for more complex analyses, such as figuring out running totals or moving averages, which are common tasks in data engineering. Subqueries: Queries nested within other queries. They provide a powerful way to perform complex data extraction, transformation, and analysis, often making your code more efficient and readable. Common Table Expressions (CTEs): CTEs can simplify complex queries and make your code more maintainable. They are also essential for recursive queries, which are sometimes necessary for problems involving hierarchical data. Stored procedures and triggers: Stored procedures help encapsulate frequently performed tasks, improving efficiency and maintainability. Triggers can automate certain operations, improving data integrity. Both are important tools in a data engineer’s toolkit. Indexes and optimization: Indexes speed up query performance by enabling the database to locate data more quickly. Understanding how and when to use indexes is key for a data engineer, as it affects the efficiency and speed of data retrieval. Views: Views simplify access to data by encapsulating complex queries. They can also enhance security by restricting access to certain columns. As a data engineer, you’ll create and manage views to facilitate data access and manipulation. By mastering these advanced SQL concepts, you will have the tools and knowledge to handle complex data scenarios, optimize your SQL queries, and derive meaningful insights from your datasets. The following section will prepare you for technical interview questions on SQL. We will equip you with example answers and strategies to excel in SQL-related interview discussions. Let’s further enhance your SQL expertise and be well prepared for the next phase of your data engineering journey. Technical interview questions This section will address technical interview questions specifically focused on SQL for data engineers. These questions will help you demonstrate your SQL proficiency and problem-solving abilities. Let’s explore a combination of primary and advanced SQL interview questions and the best methods to approach and answer them, as follows: Question 1: What is the difference between the WHERE and HAVING clauses? Answer: The WHERE clause filters data based on conditions applied to individual rows, while the HAVING clause filters data based on grouped results. Use WHERE for filtering before aggregating data and HAVING for filtering after aggregating data. Question 2: How do you eliminate duplicate records from a result set? Answer: Use the DISTINCT keyword in the SELECT statement to eliminate duplicate records and retrieve unique values from a column or combination of columns. Question 3: What are primary keys and foreign keys in SQL? Answer: A primary key uniquely identifies each record in a table and ensures data integrity. A foreign key establishes a link between two tables, referencing the primary key of another table to enforce referential integrity and maintain relationships. Question 4: How can you sort data in SQL? Answer: Use the ORDER BY clause in a SELECT statement to sort data based on one or more columns. The ASC (ascending) keyword sorts data in ascending order, while the DESC (descending) keyword sorts it in descending order. Question 5: Explain the difference between UNION and UNION ALL in SQL. Answer: UNION combines and removes duplicate records from the result set, while UNION ALL combines all records without eliminating duplicates. UNION ALL is faster than UNION because it does not involve the duplicate elimination process. Question 6: Can you explain what a self join is in SQL? Answer: A self join is a regular join where a table is joined to itself. This is often useful when the data is related within the same table. To perform a self join, we have to use table aliases to help SQL distinguish the left from the right table. Question 7: How do you optimize a slow-performing SQL query? Answer: Analyze the query execution plan, identify bottlenecks, and consider strategies such as creating appropriate indexes, rewriting the query, or using query optimization techniques such as JOIN order optimization or subquery optimization.  Question 8: What are CTEs, and how do you use them? Answer: CTEs are temporarily named result sets that can be referenced within a query. They enhance query readability, simplify complex queries, and enable recursive queries. Use the WITH keyword to define CTEs in SQL. Question 9: Explain the ACID properties in the context of SQL databases. Answer: ACID is an acronym that stands for Atomicity, Consistency, Isolation, and Durability. These are basic properties that make sure database operations are reliable and transactional. Atomicity makes sure that a transaction is handled as a single unit, whether it is fully done or not. Consistency makes sure that a transaction moves the database from one valid state to another. Isolation makes sure that transactions that are happening at the same time don’t mess with each other. Durability makes sure that once a transaction is committed, its changes are permanent and can survive system failures. Question 10: How can you handle NULL values in SQL? Answer: Use the IS NULL or IS NOT NULL operator to check for NULL values. Additionally, you can use the COALESCE function to replace NULL values with alternative non-null values. Question 11: What is the purpose of stored procedures and functions in SQL? Answer: Stored procedures and functions are reusable pieces of SQL code encapsulating a set of SQL statements. They promote code modularity, improve performance, enhance security, and simplify database maintenance. Question 12: Explain the difference between a clustered and a non-clustered index. Answer: The physical order of the data in a table is set by a clustered index. This means that a table can only have one clustered index. The data rows of a table are stored in the leaf nodes of a clustered index. A non-clustered index, on the other hand, doesn’t change the order of the data in the table. After sorting the pointers, it keeps a separate object in a table that points back to the original table rows. There can be more than one non-clustered index for a table. Prepare for these interview questions by understanding the underlying concepts, practicing SQL queries, and being able to explain your answers. ConclusionThis article explored the foundational and advanced principles of SQL that empower data engineers to store, manipulate, transform, and migrate data confidently. Understanding these concepts has unlocked the door to seamless data operations, optimized query performance, and insightful data analysis. SQL is the language that bridges the gap between raw data and valuable insights. With a solid grasp of SQL, you possess the skills to navigate databases, write powerful queries, and design efficient data models. Whether preparing for interviews or tackling real-world data engineering challenges, the knowledge you have gained in this chapter will propel you toward success. Remember to continue exploring and honing your SQL skills. Stay updated with emerging SQL technologies, best practices, and optimization techniques to stay at the forefront of the ever-evolving data engineering landscape. Embrace the power of SQL as a critical tool in your data engineering arsenal, and let it empower you to unlock the full potential of your data. Author BioKedeisha Bryan is a data professional with experience in data analytics, science, and engineering. She has prior experience combining both Six Sigma and analytics to provide data solutions that have impacted policy changes and leadership decisions. She is fluent in tools such as SQL, Python, and Tableau.She is the founder and leader at the Data in Motion Academy, providing personalized skill development, resources, and training at scale to aspiring data professionals across the globe. Her other works include another Packt book in the works and an SQL course for LinkedIn Learning.Taamir Ransome is a Data Scientist and Software Engineer. He has experience in building machine learning and artificial intelligence solutions for the US Army. He is also the founder of the Vet Dev Institute, where he currently provides cloud-based data solutions for clients. He holds a master's degree in Analytics from Western Governors University.
Read more
  • 1
  • 0
  • 1356