← Back to course
Data and Society 9-12 / Week 06 / Wednesday
3/6
Week 06 · Cleaning Data

Wednesday

Count Lab: Clean and log
// Fixing messy data without changing what it means
⏱ about 20 min

Wednesday: Count Lab: Clean and Log

The whole Q3 column is spread across the workbench, all 40 raw answers.

Comet has the rules taped to the wall. Wren has a fresh page titled Cleaning Log.

"Every time we decide something, it goes here," he says, tapping the page.

Comet reads M01. "Repair table. Is that the repair bench?"

"What do you notice about the other answers near it?" Wren asks.

"Lots of people want a place to fix things," Comet says. "I think it means the bench. But I will log it."

Nova hovers over the column. "Would you like a hint?" she asks. "When you finish, the totals should add up to 40. That is your check."

Your mission

You will clean all 40 raw Q3 answers into four categories, plus blank and invalid.

You will keep a cleaning log of every choice you had to think about.

  • Paper and a pencil
  • Two colored pencils, if you have them
  • The crew's six cleaning rules from Tuesday
  • The raw answer table below
  1. On a fresh page, write six labels: longer evening hours, quiet study room, repair bench, bike rack, blank, invalid.
  2. Start a second page titled Cleaning Log.
  3. Read each raw answer and follow the rules in order.
  4. Write the member ID under the right label.
  5. If you had to decide, add a log line: the ID, the raw answer, your choice and why.
  6. Count the IDs under each label.
  7. Add the six counts and check that the total is 40.
IDRaw Q3IDRaw Q3
M01repair tableM21Quiet study room
M02Longer evening hoursM22a rack for bikes
M03a quiet room to studyM23quiet study room
M04longer eveningsM24repair bench
M05a quiet room to studyM25longer evening hours
M06repair benchM26later hours
M07Repair BenchM27longer evening hours
M08quiet study roomM28repair bench
M09bike rackM29Longer evening hours
M10open laterM30Longer evening hours
M11study roomM31repiar bench
M12Bike rackM32longer evening hours
M13later hoursM33fix-it bench
M14bike rack!M34Repair Bench
M15quiet study roomM35Quiet study room
M16longer evening hoursM36repair bench
M17open laterM37bikes
M18(blank)M38study room
M19a launch padM39longer evenings
M20quiet study roomM40quiet room

This is made-up data from the Commons Count story.

PREDICT FIRST
  • Read the question.
  • Tap your answer.
Before you count: which category do you predict is the biggest?
CHECK YOUR TOTALS
  • Read the question.
  • Tap your answer.
How many answers clean to longer evening hours?
How many answers clean to quiet study room?
How many answers clean to repair bench?
How many answers clean to bike rack?
CHECK THE WHOLE COLUMN
  • Read the question.
  • Tap your answer.
What is 13 plus 11 plus 9 plus 5 plus 1 plus 1?
How many valid answers are there, leaving out the blank and the invalid one?
On paper, write your cleaning log neatly, with at least four lines: ID, raw answer, your choice and your reason.

Great lab work, data analyst. Tomorrow you will filter the sheet and transform a column.

← Tuesday