Introduction to EDA

Exploratory Data Analysis (EDA) is the process of investigating a dataset to summarise its main characteristics, often using visual and statistical methods, before applying any formal modeling.

Why EDA Comes First

Jumping straight into modeling without exploring the data first is risky - you might miss missing values, outliers, or incorrect data types that could silently distort your results.

What EDA Typically Covers

• Understanding the shape and structure of the dataset (rows, columns, data types)
• Checking for missing values and duplicates
• Summarising each variable using measures of central tendency and spread
• Visualising distributions with histograms, box plots, and scatter plots
• Studying relationships between variables, such as correlation

A Quick Example

import pandas as pd

df = pd.read_csv("sales.csv")

print(df.info())
print(df.describe())
print(df.isnull().sum())

Coming Up Next

Next, you'll start diving into the four business moment decisions, beginning with the first - measures of central tendency.