MariaDB Corporation and MindsDB, the leader in in-database machine learning, today together announced a technology collaboration that makes machine learning predictions easy and accessible to cloud database users. By using MindsDB in SkySQL, MariaDB's fully managed cloud database service, data science and data engineering teams can increase their organization's predictive capabilities to plan for and address real-world business issues. MariaDB has been downloaded over one billion times and is used by 75% of the Fortune 500, touching the lives of more than a billion people every day. MariaDB database users will now be able to add machine learning based predictions directly into their datasets stored in SkySQL. "We are excited to work with MindsDB to unlock the genius in the cloud by giving customers seamless and easy-to-use machine learning capabilities available through MariaDB SkySQL," said Jags Ramnarayan, Vice President and General Manager of SkySQL, MariaDB Corporation.

MindsDB announces an integration with MariaDB to enable machine learning to the wildly popular open source relational database, furthering the mission to democratize machine learning. MindsDB, the open source AI layer for existing databases, today announced their official integration with the widely used open source relational database, MariaDB Community Server. This integration fills a longstanding demand of database users for the ability to bring machine learning capabilities to the database and democratize ML use. MindsDB helps apply machine learning models straight in the database by providing an AI layer that allows database users to deploy state-of-the-art machine learning models using standard SQL queries. The use of AI-Tables helps database users leverage predictive data inside the database for easier and more effective machine learning projects.

Machine learning is one area that cannot succeed without data. Traditionally, machine learning frameworks read it from CSV files or similar data sources. This brings an interesting set of challenges because in most cases the data is stored in databases, not simple raw files. It takes time and effort to move data from one format to another. Additionally, one needs to write some code (usually python) to prepare the data just like the ML framework expects it.

Let's set up the required configuration and start MindsDB. If you are following this tutorial with your own data, you can skip to the next section. For this example we will use the Audi Car Price dataset from the 100k used cars scraped data. The dataset contains information on price, transmission, mileage, fuel type, road tax, miles per gallon (mpg), and engine size of the used cars in the UK. The idea is to predict the price depending on the above features. The first thing we need to do is to create the table.