Every day new data is created. New parts are made and shipped from factories, people continuously tweet, and companies grow and fluctuate causing major changes in the market. With the addition of more data comes the difficulty of being able to process that data. As humans, we can understand complex scenarios, but computers are much better at being able to analyze large datasets. In this workshop, you will get a glimpse into how we can teach machines to analyze complex scenarios at a much larger scale than we're able to. After you've cleaned and organized your data, you will have an opportunity to train and test machine learning models, and even publish your predictor online for others to explore.
You do not need any prior experience with data science to attend this workshop. You are likely someone who has ~1 year experience coding, preferrably in Python, but not a requirement. You are interested in learning how to use Python libraries to call machine learning models and make predictions on your data.
You should have your own laptop (Windows or Mac) with an Internet browser. You will be using Azure Notebooks, a cloud-based Jupyter Notebooks instance, and Azure Machine Learning Studio. All you will need is a Microsoft Account, which only requires an email address and for which you can sign up for at the event.
This workshop is meant to be highly interactive. The instructor will lead you in two interactive teaching styles:
Notice: Various interactive cues are called out in the Notebooks. These are suggestions and at the instructor's discression.
The primary source of content will be relatively bare Azure Notebooks where the instructor will guide you through discovering the different features of Python, NumPy, Pandas, and general data cleaning and manipulation. There is also a folder called "Reference Material" which has all of the same content in the primary notebooks, plus written explanations and additional features not covered in this workshop.
Azure Notebooks is still in Preview. This means that there are some times when it will fail. Here are some tips for avoiding losing your work:
Additionally, if you need a referesher on how to code in Python or work with NumPy or Pandas, we recommend you check out the materials from our other Reactor Wowrkshop: Data Science 1: Introduction to Python for Data Science