Question 1

What is data cleaning?

Accepted Answer

Raw data is messy and hard to analyze, so we have to “clean” it by filling in missing values, correcting mistakes and improper formatting, fitting it into the right rows and columns, and other methods you’ll learn in this course.

Question 2

Why do we need to clean data?

Accepted Answer

Data needs to be prepped and formatted before you can use it. You’ll come across a lot of missing and inaccurate values as you go through raw data, and they can throw off your analyses if left unresolved.

Question 3

How do you clean data?

Accepted Answer

Most of the work around cleaning data involves finding and fixing incomplete or missing values. Once that’s handled and the data’s (mostly) accurate, it needs to be shaped and organized into rows and columns.

Question 4

Who’s responsible for cleaning data?

Accepted Answer

There’s a saying that Data Scientists spend 80% of their time cleaning and manipulating data and only 20% of their time analyzing it or building models from it, and Machine Learning Engineers spend much of their time building and maintaining pipelines that automatically collect, clean, and organize data into a usable format. Outside of tech, there are a ton of jobs that involve (or can benefit from) working with data, and cleaning data is one of the first steps toward putting it to good use.

Question 5

What else should I study if I am learning about cleaning data?

Accepted Answer

Learning a little about statistics can help you sharpen your data skills. There are a couple of popular methods for cleaning data that you’ll explore in your studies, and they’ll take you pretty far — but there are various statistical methods you can use when working with numerical data that all have different effects on your analyses.

How to Clean Data with Python

About this course

Syllabus