[P] Machine Learning for Classification (production grade)

Published on :

Hi. I want to share my experience of building an effective automotive classification process (in Dataiku) using machine learning process. ​ Git: https://github.com/elegantwist/catalog_classifier ​ One has to build a classifier of elements of a dictionary (company) based on a text description of the element company scope of interest. The classification […]

Cloudera: Instrumented Data Analytics

Published on :

Sizing clusters for jobs, finding bottlenecks or getting insight into failures after they have run in Apache Spark isn’t easy. In this episode of ‘This is My Architecture’ – https://amzn.to/2MCyvh1, Wing from Cloudera explains how they use telemetry to optimize analytics workloads on AWS to make those headaches disappear. Host: […]