Skip to content

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

# Correlation Analysis of Sample Superstore Dataset

## Overview

This project presents an exploratory data analysis of the Sample Superstore dataset with a focus on identifying relationships between numerical variables. Pearson correlation analysis and visualization techniques were used to examine how business metrics such as Sales, Profit, Quantity, and Discount are related. The project demonstrates practical data analysis skills using Python and widely adopted data science libraries.

---

## Objectives

- Load and explore the Sample Superstore dataset.

- Identify numerical features suitable for correlation analysis.

- Calculate the Pearson correlation matrix.

- Visualize feature relationships using a correlation heatmap.

- Examine pairwise relationships through scatter plots and distributions.

- Interpret the strongest positive and negative correlations.

- Present insights to support business decision-making.

---

## Dataset

The analysis was performed using the Sample Superstore dataset, which contains transactional information including customer details, product categories, sales, discounts, quantities, and profits.

---

## Technologies Used

- Python

- Pandas

- NumPy

- Matplotlib

- Seaborn

- Jupyter Notebook

---

## Project Structure


Syntecxhub\_Correlation\_Analysis

│

├── Data

│   └── SampleSuperstore.csv

│

├── Images

│   ├── correlation\_heatmap.png

│   └── pairplot.png

│

├── Notebook

│   └── Correlation\_Analysis.ipynb

│

├── Readme.md

├── Requirements.txt

├── summary.txt

├── License.txt

└── .gitignore

---

## Methodology

The project followed a structured exploratory data analysis workflow:

1. Imported the required Python libraries.

2. Loaded the dataset into a Pandas DataFrame.

3. Explored the dataset structure and summary statistics.

4. Selected numerical columns for analysis.

5. Computed the Pearson correlation matrix.

6. Created a professional correlation heatmap.

7. Generated pairplots to examine pairwise relationships.

8. Identified the strongest positive and negative correlations.

9. Summarized the findings and conclusions.

---

## Results

The analysis produced the following outputs:

- Pearson Correlation Matrix

- Correlation Heatmap

- Pairplot of Numerical Features

- Correlation Summary

Key observations include:

- Sales and Profit exhibit a moderate positive correlation.

- Discount has a negative relationship with Profit.

- Quantity has a relatively weak relationship with Sales and Profit.

- The visualizations provide a clear understanding of relationships among the numerical variables.

---

## Conclusion

Correlation analysis is an essential step in exploratory data analysis because it helps identify relationships between variables before predictive modeling. Through the use of Pearson correlation, heatmaps, and pairplots, this project provides meaningful insights into the Sample Superstore dataset and demonstrates practical data analysis techniques commonly used in business intelligence and data science.

---

## Future Enhancements

Possible improvements for this project include:

- Correlation analysis by product category and region.

- Interactive dashboards using Plotly or Power BI.

- Feature engineering for predictive modeling.

- Machine learning models for sales and profit prediction.

---

## Author

**Nitheeshwaran V**

Artificial Intelligence & Data Science Student

GitHub: https://github.com/V-Nitheeshwaran

About

A Python-based exploratory data analysis project that examines relationships between numerical variables in the Sample Superstore dataset using Pearson correlation, correlation heatmaps, and pairplots.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages