Margriet is a Data Scientist and Developer Advocate for IBM Cloud. She has a background in Climate Science where she explored large observational datasets of carbon uptake by forests and the output of global scale weather and climate models. Now she explores ways to simplify working with diverse data using cloud databases, data warehouses, Spark, and Python notebooks.
Weather is part of our everyday lives. Who doesn’t check the rain radar before heading out, or the weather forecast when planning a weekend away? But where does this data come from, and what is it made of? The answer is a mix of measurements, models and statistics, meaning that the use of weather and climate data can get complex very quickly.
This session provides a brief overview of the science behind weather and climate forecasts and provides you with the tools to get started with weather data even if you aren't a meteorologist. Learn how to connect weather data to other data sources, how to visualize weather and climate data in an interactive weather dashboard embedded in a Python notebook, and other ways you can use weather data for yourself, from examples using weather APIs, maps, PixieDust and Machine Learning.
In order to move past the hype and achieve the full potential of machine learning, data scientists and software developers need to work more closely together towards their common goal of delivering well architected, data driven applications. Every industry is in the process of being transformed by software and data. It is in the collaboration between data scientists and software developers where the real value can be found by creating integrated data workflows that benefit from the unique knowledge and skillsets of each discipline.
Writing and notebooks go hand in hand, but what if your story relies on data? Instead of having your data research and writing scattered over many different tools and documents it is possible to do everything in one document with a Jupyter notebook. In this session you will learn how to get started. Examples will show you how to load and analyze data with some Python code and then create data visualizations and dashboards with the open source package PixieDust.
Data Science deals with the extraction of valuable insights from an incredible number of sources in an endless number of formats. This session will go through a typical workflow using practical tools and tricks. This will give you a basic understanding of Data Science in the Cloud. The examples will show the steps that are needed to build and deploy a model to predict traffic collisions with weather data.
- This session gives an overview of a Data Science workflow
- Store and access data in the Cloud
- Work with this data in notebooks to wrangle, analyse, model and visualise data
- Deploy the machine learning model to be used as an easy accessible API