Exploring a Dataset

Methods for Exploring Data

Variable Classification
Descriptive Statistics
Visual Exploration

Types of Variables:

Nominal (A categorical variable that has 2 or more categories)
Ordinal (A categorical variable with natural ordered categories)
Interval (A numeric variable where differences are meaningful. i.e temperature equadistance
Ratio (A numeric variable with a clear definition of 0.0)
Temporal (Any Data related to Time or a date associated with it)
Spatial (Data with coordinates that exist somewhere)

Variable Type Examples:

Gender: Male or Female

PowerSource: On or Off

Income: < $50K, $50K to $100K, > $100K

Status: High, Medium or Low

SAT Score: 225 - 800

Temperature: 35 (Celcius) or 85 (Farenheit)

Length: 6ft 2Inches

Duration: 22 Minutes 13 seconds

Income: $65K

What's happening in the script above?

The above demonstrates examples of various variable types
The following will demonstrate various transforms that can be applied to each variable

Connect via LinkedIn

Kevin Regan

Have an article, idea, found a typo, want to contribute? Shoot me an email Here

Below are links to some Udemy Data Science Courses. I've been using Udemy for a number of years now, and I've found their courses super helpful, maybe you will also.