SF Data Weekly - ML for Hip-Hop Popularity, K-Means Clustering and #DuBoisChallenge

The author built a tool to help his cousin, a hip-hop artist named “KC Makes Music,“ assess whether his unreleased songs would be successful on Spotify.

How the AWS Glue Schema Registry can be used to centrally publish, discover, control, validate and evolve schemas for stream processing applications for a number of Amazon apps, including MSK (Kafka).

If you have outgrown Salesforce Data Loader and the Salesforce Data Import Wizard - you need a more scalable solution. Check out Integrate.io’s Salesforce capabilities. [Sponsored]

This scary piece details how the author found thousands of ElasticSearch databases and Kibana dashboards in just one day.

BigQuery recently announced that it will support JSON as a data type. This piece explores what that means for BigQuery users.

Example code showing the basics of stored procedures in Snowflake.

The second installment in the Explaining Machine Learning Algorithms to 10-year Olds series tackles K-Means Clustering. The first one explains XGBoost Classification.

Using Excel or Google Sheets to implement a simple Neural Network model for exploration and learning purposes.

In February 2021, people on Twitter were challenged to re-create the historical data visualizations of W. Du Bois. A year later, this piece looks at the wide variety of visualizations created as part of the challenge.

It’s not too late to submit your visualization to Outlier 2022.

Uber uses Apache Parquet as the file format for its data lake. This piece shows the different strategies used to store data more efficiently, including compression, column deletion and column re-ordering.