Heads up! To view this whole video, sign in with your Courses account or enroll in your free 7-day trial. Sign In Enroll

Preparing Data for Analysis

Well done!

You have completed Preparing Data for Analysis!

Sign up for Treehouse Back to Library
Preview
Video Player
00:00
00:00
00:00
  1. 2x 2x
  2. 1.75x 1.75x
  3. 1.5x 1.5x
  4. 1.25x 1.25x
  5. 1.1x 1.1x
  6. 1x 1x
  7. 0.75x 0.75x
  8. 0.5x 0.5x
Use Up/Down Arrow keys to increase or decrease volume.

Context

1:59 with Megan Amendola

Determine the context necessary for working with our dataset.

Understanding the context behind your analysis may affect how you clean 0:00
the data. 0:05
Here are a few questions to ask yourself when reviewing the dataset. 0:06
[MUSIC] 0:10
Do you know enough about the topic of the dataset? 0:13
Why are you working with this dataset? 0:17
How do you plan on using the dataset? 0:19
What questions do you need to answer? 0:23
Who will be viewing the analysis? 0:25
For instance, when sharing analysis with people from the US, you'll probably wanna 0:30
have numbers in a format they're familiar with like inches or pounds. 0:35
If you're presenting the information to people from really anywhere else in 0:39
the world, it might make sense to share the numbers in centimeters or kilograms. 0:44
Understanding the context also means knowing enough about the topic to be able 0:49
to make accurate predictions and assumptions about the data. 0:54
Let's use the Pokemon dataset as an example, 0:58
you can find a link to the dataset in the teacher's notes below. 1:01
If I were going to use this dataset for analysis but 1:05
I didn't know anything about Pokemon, I would start looking for 1:08
resources to help me understand what Pokemon are. 1:12
What does a weakness or type mean and how do they interact with one another? 1:15
Understanding the terminology of the dataset and how different elements relate 1:21
to each other will also help you clean the dataset properly and 1:26
start building out questions for your analysis. 1:29
With this dataset for example, once I understand how weaknesses and 1:33
types work, I could answer questions like, 1:37
what type of Pokemon has the most weaknesses on average? 1:40
Or which weakness shows up the most? 1:44
Once you feel you have enough context to move on you can start looking for 1:48
what needs to be cleaned. 1:52
Let's take a look at the different types of bad data to look out for 1:54
in the next video. 1:57