Week 10: The Dataset

In this week, the team selected the dataset to be used, that would fit well in the the problem presented in the first week of this challenge.

The Dataset contains unique, high-resolution data collected from instrumentation that Pecan Street installed in approximately 1,000 homes, of which about 750 are located in Texas, 50 in Colorado, 50 in California, 100 in New York, and 50 in other U.S. states. Over the course of 2020, an additional 100 homes in New York State and 100 homes in California with be added to Dataport. All data is anonymized and stripped of personally-identifiable information (PII). But we selected 28 homes from 01/01/2018 to 12/31/2018, located in the cities of San Diego and Austin. The selection was made so that all records are from the same period, as the data set Dataport data is distributed in periods that are not synchronous.