Agile Data Science Class

Welcome to the Agile Data Science 2.0 Class! During this course we will walk you through how to iteratively create big data applications using agile methods.

The hero's journey is from Joseph Campbell's Hero of a Thousand Faces. It expresses the monomyth, a story that spans all human civilizations in which a hero undergoes a cycle of change and emerges a hero with a boon to bestow unto his society. Agile methods fit with the cycle of the monomyth, and indeed with the nature of reality itself. That is why they work!

Chapter 2: Agile Tools

Now that we've covered the material on the theory of agile methods for data science, lets get acquainted with our tools! We'll go over the major components of the agile data science stack and introduce you to each one. We'll get started executing code right away!

Check out Chapter 2: Agile Tools

Chapter 3: Data

Now the presenter will offer a quick presentation of the data itself.

Part II: Climbing the Pyramid

Now check out Part II - Climbing the Pyramid, your introduction to the process of iterative data refinement!

Chapter 4: Collecting and Displaying Records

Now we will collect our data and setup plumbing through our software stack onto the web. Check out Chapter 4: Collecting and Displaying Records now!

Chapter 5: Visualizing Data wiith Tables and Charts

Now we will start to process our data to extract higher level information through aggregation, visualization and mathematics. Check out Chapter 5: Visualizing Data with Tables and Charts.

Chapter 6: Exploring Data with Reports

Once we have multiple charts on a single web page, when we have multiple entity pages linking together to enable drilldown, when we add search and exploration of data... we arrive at the level of the interactive report. Check out Chapter 6: Exploring Data with Reports.

Chapter 7: Making Predictions

In the next level of the data value pyramid, we take what we've learned at the lower levels and apply it to creating predictions with our data. Check out Chapter 7: Making Predictions.

Chapter 8: Deploying Predictive Systems

Most predictions die in the lab. To ensure this doesn't happen to your predictions, we next deploy a prediction as a full-blown predictive system on the web using Apache Kafka and Spark Streaming. Check out Chapter 8: Deploying Predictive Systems.

Chapter 9: Improving Predictions

When a prediction proves useful, it then becomes your job to improve it. Check out Chapter 9: Improving Predictions.


In [ ]: