Exploratory data analysis (EDA)

What is EDA?

Exploratory data analysis is the first step in any data analysis process. It allows summarizing all the main characteristics of data using both statistical and graphical tools. EDA helps determine essential properties of data, its distribution, spotting anomalies, and discovering patterns. 

Why is it important?

EDA is used to get the first glimpse of data, get familiar with it, see its main properties. EDA can significantly simplify further analysis by giving an overview of what data looks like. It is often used to formulate hypotheses about data that can lead to new experiments. EDA can save much time during the following analysis by identifying obvious errors, outliers, etc.