エンジニアリングのブログ

Hyperopt is a powerful tool for tuning ML models with Apache Spark. Read on to learn how to define and execute (and debug) the tuning optimally! So, you want to build a model. You've solved the harder problems of accessing data, cleaning it and selecting features. Now, you just need to fit a model, and...

What expedites the process of learning new concepts, languages or systems? When learning a new task, do you look for analogs from skills you already possess? Across all learning endeavors, three favorable characteristics stand out: familiarity, clarity and simplicity. Familiarity eases the transition because of a recognizable link between the old and new ways of...

For most financial service institutions (FSI), fraud prevention often implies a complex ecosystem made of various components –- a mixture of traditional rules-based controls and artificial intelligence (AI) and a patchwork of on-premises systems, proprietary frameworks and open source cloud technologies. Combined with strict regulatory requirements (such as model explainability), high governance frameworks, low latency...

Koalas is a data science library that implements the pandas APIs on top of Apache Spark so data scientists can use their favorite APIs on datasets of all sizes. This blog post compares the performance of Dask’s implementation of the pandas API and Koalas on PySpark. Using a repeatable benchmark, we have found that Koalas...

Advances in time series forecasting are enabling retailers to generate more reliable demand forecasts. The challenge now is to produce these forecasts in a timely manner and at a level of granularity that allows the business to make precise adjustments to product inventories. Leveraging Apache Spark™ and Facebook Prophet, more and more enterprises facing these...

Traditionally, generic MLflow Python models only supported DataFrame input and output. While DataFrames are a convenient interface when dealing with classical models built over tabular data, it is not convenient when working with deep learning models that expect multi-dimensional input and/or produce multidimensional output. In the newly-released MLflow 1.14, we’ve added support for tensors, which...

Quick link to notebooks referenced through this post. Personalization is heralded as the gold standard of customer engagement. Organizations successfully personalizing their digital experiences are cited as driving 5 to 15% higher revenues and 10 to 30% greater returns on their marketing spend. And now many customer experience leaders are beginning to extend personalization to...

Genomics data has exploded in recent years, especially as some datasets, such as the UK Biobank, become freely available to researchers anywhere. Genomics data is leveraged for high-impact use cases – gene discovery, research and development prioritization, and to conduct randomized controlled trials. These use cases will help in developing the next generation of therapeutics....

What a difference a year makes. One year ago, Databricks Runtime version (DBR) 6.4 was released -- followed by 8 more DBR releases. But now it’s time to plan for an upgrade to 7.3 for Long-Term Support (LTS) and compatibility, as support for DBR 6.4 will end on April 1, 2021. (Note that a new...

This post was written in collaboration betweeen Eric Gieseke, principal software engineer at Algorand, and Anindita Mahapatra, solutions architect, Databricks.   Algorand is a public, decentralized blockchain system that uses a proof of stake consensus protocol. It is fast and energy efficient, with a transaction commit time under five seconds and a throughput of one...