Scribd
Upload
6 views2 pages

Exploratory Data Analysis

Exploratory Data Analysis (EDA) is a crucial process for gaining insights from data before conducting further analysis, akin to detective work. Its objectives include confirming data relevance, resolving quality issues, detecting outliers, and understanding data patterns. EDA can be categorized into univariate and multivariate types, both graphical and non-graphical, and plays a significant role in business analytics by informing decision-making through data visualization and storytelling.

Uploaded by

mariesarahkouakou2005
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
6 views2 pages

Exploratory Data Analysis

Exploratory Data Analysis (EDA) is a crucial process for gaining insights from data before conducting further analysis, akin to detective work. Its objectives include confirming data relevance, resolving quality issues, detecting outliers, and understanding data patterns. EDA can be categorized into univariate and multivariate types, both graphical and non-graphical, and plays a significant role in business analytics by informing decision-making through data visualization and storytelling.

Uploaded by

mariesarahkouakou2005
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Kouakou Marie Sarah

EXPLORATORY DATA ANALYSIS

 Introduction to Exploratory Data Analysis (EDA)


EDA or Exploratory Data Analysis is a processus to gather insight from
the data . EDA is the cornerstone, a very vital step before starting data
analysis. Doing EDA is like doing investigations like detectives. The more
you know and understand your data , the better your analysis. open-
minded exploration of data provides valuable information . Learning what
you can do using the data available will make the final analysis more
robust and effective.

 Objectives of EDA
The objectives of EDA is to understand which kind of solution or using the
machine learning approach will we use to solve the problem. EDA a pour
but de :
 Confirm if the data is making sense in the context of the
business problem.
 Uncover and resolve data quality issues.
 Get information about the data summary.
 Detect outliers and anomalies.
 Understand data patterns and correletions between
variables .
 Drop unwanted columns and derive new variables.

 Importance of EDA
EDA helps in uncovering underlying patterns and trending the data that
are not visible by just looking at the data . EDA can highlights
relationships between data points to gather insights. EDA also helps to in
restructuring the data according to the problem statement .
 Types of EDA
There two types of EDA in which we use a lot of tools . there’s :
 Univariate Non-Graphical

 Simple Tabulation (one-way tab)


 Central tendency ( for interval and ratio)
 Descriptive summary Statistics ( To get details like mean ,
mode or standard deviation
 Missing values need to be resolved before the analysis

 Multivariate Non-Graphical

 Cross tabulation reports for categorical data (used for


comparaison)

 Univariate Graphical

 Bar charts for binary and categorical data


 Histograms for quantitative data

 Multivariate Graphical

 Scatter plots numerical

EDA is generally cross-classified . it can be done non-graphically and is


further divided into either univariate or multivariate .

 EDA in business analytics

 Business / Question problem


 Data collection & Storage
 Data analysis
 Data visualization and Storytelling
 Business Decisions

You might also like