churn demo

_notes.md

-A Notebook is a special type of Databricks folder that can be used to create Spark
-scripts. Notebooks can call the Notebook scripts to create a hierarchy of functionality.
-When created, the type of Notebook must be specified (Python, Scala, or SQL), and
-a cluster can then specify that the Notebook functionality can be run against it. The
-following screenshot shows the Notebook creation.
-
-
-

demo2/README.md

+## Demo Overview
+
+This demo is for **Customer Churn**.  Using the notebook we want to predict and prevent customer churn.  
+
+The goal is to predict a possible churn event, report it, and then provide strategies to prevent churn.  (Special offers).  
+
+This example is for mobile phone carriers.  
+
+Even if you or your customer knows nothing about mobile phone churn we want our notebook to help illustrate a story using our data.  
+
+The dataset is public domain "Customer Churn dataset" from [Kaggle](https://www.kaggle.com/c/customer-churn-prediction/data).  
+
+## Setup
+
+* Spin up a small cluster
+* Import the notebook
+* Copy the data files to either WASB or ADLS.  
+  * the notebook describes both methods of accessing the code
+  * We assume you can get the data into one of those two areas.  I give some pointers in the notebook.  
+
+* Each cell is well-documented and should be easy to demo.  
+
+
+## Next Steps
+
+* connect pbi to databricks.  Not hard.  [Documentation](https://medium.com/@mauridb/powerbi-and-azure-databricks-193e3dc567a)
\ No newline at end of file