Data Science Tips and Tricks using Python and SQL – Boulder
The practice of Data Science has arrived and as data professionals we’re on the forefront of this change. The data we collect can now be used in new and exciting ways, providing more value than ever before. To get started in this field, a number of tools and methodologies must be employed to help you achieve predictive analytics success with your data. In this session, we will start by providing an introduction to Python, quickly becoming the defacto programming language for data scientists who want to create enterprise-ready solutions. Carlos will then cover predictive analytics using T-SQL and Python, providing a practical understanding of what it takes to develop your own predictive models making the most of the expertise you already have. The session includes an overview of definitions, concepts and terminology, successful applications of predictive analytics, and how predictive analytics fits into an analytics environment.
Prerequisites: Working knowledge of SQL Server, T-SQL and data integration and transformation concepts.
Carlos Bossy (MCTS, MCP BI, CBIP) is a data and cloud analytics architect with 25 years of experience in software and database development. As a principal of Datalere, Carlos focuses on developing BI, Data Science, and Advanced Analytics solutions, including modeling data warehouses and delivering predictive models, integration, and visualization. He has developed warehouses and BI solutions for a variety of industries and state agencies, including health insurance, solar energy, foster care, telecom, and manufacturing.