STAT 94

Foundations of Data Science
Fall 2015

Principal Instructor:
Ani Adhikari
Co-Instructors:
John DeNero
Michael I. Jordan
Tapan Parikh
David Wagner




Project 1

Part 1 Instructions

To run the tests, temporarily turn on "Edit Mode" and change the final cell of project1_part1_v2.ipynb (make sure you are using version 2, it is the one we will pull your code from) to read

# ok
!ok --local --config 01.ok -v 2>/dev/null

Then, turning off edit mode and clicking "Run ok tests" will then correctly run the tests.

A Note On Water Districts (must read!)

You may have noticed that some of the tables involved in part 1 have different numbers of water districts. Here is what we are expecting for the tests:

Test Descriptions

Not all tests are worth equal points; harder ones are worth more.

  1. Number of income labels
  2. Correct income labels
  3. Correct income labels
  4. Correct income labels
  5. Correct income labels
  6. Correct EITC calculation
  7. Number of income rows
  8. Number of usage_totals rows
  9. Correct population for usage_totals
  10. Correct total_water for usage_totals
  11. Number of wd_income rows
  12. Correct income_prop for wd_income
  13. Correct number of nonzeros in income_50 for wd_income
  14. Correct income_50 for wd_income

Part 2 Instructions

As in part 1, make your changes in project1_part2_v2.ipynb. To run the ok tests properly, your last cell must contain:

# ok
!ok --local --timeout 20 --config 02.ok -v 2>/dev/null

-----