05. Unclean Data: Dirty vs. Messy 2

Unclean Data: Dirty vs. Messy

There are two types of unclean data:

• Dirty data, also known as low quality data. Low quality data has content issues .
• Messy data, also known as untidy data. Untidy data has structural issues .

In this lesson, you are going to assess both dirty and messy data. Your job right now is to start to distinguish between those two now, even though quality and tidiness (the latter, especially) may not be 100% solidified in your mind yet.

Answer the following quizzes, distinguishing between low quality and untidy data, to set yourself up for success in this lesson.

Note: the data pictured in the animation is a simplified version of the actual dataset used in this lesson.

Quiz 1

Use the image below to answer the first quiz.

QUIZ QUESTION: :

Which of the following cleanliness issues in a bedroom are dirty? Which are messy? Please match accordingly.

ANSWER CHOICES:

Crumbs on the floor

Clothes on the floor

Unmade bed

Banana peel on the floor

Cleanliness Issue	Dirty or Messy?
Messy
Messy
Dirty
Dirty

SOLUTION:

Cleanliness Issue	Dirty or Messy?
Messy	Clothes on the floor
Messy	Unmade bed
Messy	Clothes on the floor
Messy	Unmade bed
Dirty	Crumbs on the floor
Dirty	Banana peel on the floor
Dirty	Crumbs on the floor
Dirty	Banana peel on the floor

Quiz 2

Use the image below to answer the second quiz.

QUIZ QUESTION: :

Which of the following cleanliness issues in the pictured dataset are quality issues? Which are tidiness issues? Please match accordingly.

ANSWER CHOICES:

Dose typo (600 instead of 60)

Drug A, Drug B, Drug C columns

Duplicate Jane Citizen record

Patient information and drug information in same table

Cleanliness Issue	Quality or Tidiness Issue?
Quality
Tidiness
Tidiness
Quality

SOLUTION:

Cleanliness Issue	Quality or Tidiness Issue?
Quality	Dose typo (600 instead of 60)
Quality	Duplicate Jane Citizen record
Tidiness	Drug A, Drug B, Drug C columns
Tidiness	Patient information and drug information in same table
Tidiness	Drug A, Drug B, Drug C columns
Tidiness	Patient information and drug information in same table
Quality	Dose typo (600 instead of 60)
Quality	Duplicate Jane Citizen record