Patterns for ML Models in Production

Jeff Fletcher shows four patterns for productionalizing Machine Learning models, as well as some things to take care of once you’re in production:

Operational Databases
This option is sometimes considered to be  real-time as the information is provided “as its needed,” but it is still a batch method. Using our telco example, a batch process can be run at night that will make a prediction for each customer, and an operational database is updated with the most recent prediction. The call center agent software can then fetch this prediction for the customer when they call in, and the agent can take action accordingly.

Read on for more.

Sales Predictions with Pandas

Megan Quinn shows how you can use Pandas and linear regression to predict sales figures:

Pandas is an open-source Python package that provides users with high-performing and flexible data structures. These structures are designed to make analyzing relational or labeled data both easy and intuitive. Pandas is one of the most popular and quintessential tools leveraged by data scientists when developing a machine learning model. The most crucial step in the machine learning process is not simply fitting a model to a given data set. Most of the model development process takes place in the pre-processing and data exploration phase. An accurate model requires good predictors and, in order to acquire them, the user must understand the raw data. Through Pandas’ numerous data wrangling and analysis tools, this important step can easily be achieved. The goal of this blog is to highlight some of the central and most commonly used tools in Pandas while illustrating their significance in model development. The data set used for this demo consists of a supermarket chain’s sales across multiple stores in a variety of cities. The sales data is broken down by items within the stores. The goal is to predict a certain item’s sale.

Click through for an example of the process, including data cleansing and feature extraction, data analysis, and modeling.

The Banality of Containers

Grant Fritchey points out that containers hosting SQL Server are, in and of themselves, banal:

I’m only half joking when I say containers are boring and dull. They’re not. The technology is amazing. However, that technology doesn’t fundamentally change what you’re dealing with. It’s SQL Server. How do you capture detailed performance metrics in a container? Extended Events. How do you capture aggregated performance metrics and query plans in a container? Query Store. What’s the backup syntax for a database in a container? BACKUP DATABASE. We can keep going on this, but I won’t.

To a great extent, this is the same as SQL Server on Linux: once you have it installed, it works just like the Windows version (well, save for the things which aren’t there yet). All of the magical parts are in getting there.

Embedding Refresh Times in Power BI Reports

Marc Lelijveld shows how you can embed Power BI Dataflow refresh times in your Power BI reports:

But maybe you want to visualize this as part of your report as well. With a really simple piece of Power Query code you can easily generate a date/time at the moment that your dataset is processed. Kasper de Jonge wrote a blog post on that, so I’m not going to elaborate on that. However, when we add this as a separate entity to each dataflow, it results in a last successful refresh date/time for each dataflows.

Since each dataflow will be refreshed on it’s own, likewise as a dataset, the entity with your last date/time will always the last date/time for the whole dataflow, no matter how many entities are in there.

Read on to see how to combine and display these refresh times.

Trailing Spaces and String Comparisons

Kevin Feasel

2019-06-19

T-SQL

Bert Wagner shows how SQL Server handles trailing spaces when comparing two strings:

The LEN() function shows the number of characters in our string, while the DATALENGTH() function shows us the number of bytes used by that string.

In this case, DATALENGTH is equal to 10. This result is due to the padded spaces occurring after the character “a” in order to fill the defined CHAR length of 10. We can confirm this by converting the value to hexadecimal. We see the value 61 (“a” in hex) followed by nine “20” values (spaces).

Click through to see what happens and why it works the way it does.

Breaking Down the MAXDOP Guidance Change

Joe Obbish digs into Microsoft’s new guidance for maximum degree of parallelism:

I’ve heard some folks claim that keeping all parallel workers on a single hard NUMA nodes can be important for query performance. I’ve even seen some queries experience reduced performance when thread 0 is on a different hard NUMA node than parallel worker threads. I haven’t heard of anything about the importance of keeping all of a query’s worker threads on a single soft-NUMA node. It doesn’t really make sense to say that query performance will be improved if all worker threads are on the same soft-NUMA node. Soft-NUMA is a configuration setting. Suppose I have a 24 core hard NUMA node and my goal is to get all of a parallel query’s worker threads on a single soft-NUMA node. To accomplish that goal the best strategy is to disable auto soft-NUMA because that will give me a NUMA node size of 24 as opposed to 8. So disabling auto soft-NUMA will increase query performance?

Joe takes a careful look at the documentation and brings up some really good questions.

Categories

June 2019
MTWTFSS
« May Jul »
 12
3456789
10111213141516
17181920212223
24252627282930