Data Cleaning & Analytics Project

Overview

This project demonstrates the complete process of cleaning, preparing, and structuring raw data for analysis.
The goal is to turn messy data into clean, automated, and actionable datasets ready for visualization and reporting.

Problem Statement

In real-world scenarios, datasets are often:

• Duplicated
• Inconsistent
• Incomplete
• Hard to analyze

This project simulates cleaning a business dataset to prepare it for dashboards and decision-making.

Dataset

• Source: Example business dataset (Excel/CSV)
• Key columns: Customer ID, Sales, Product, Region, Date
• Issues addressed: duplicates, nulls, formatting inconsistencies

Data Cleaning Process

1. Remove duplicates
2. Handle missing values
3. Standardize formats
4. Validate ranges and data types
5. Prepare dataset for analysis and dashboards

Automation

• SQL scripts automate cleaning and transformation
• Repeatable workflow ensures reproducibility

Visualization & Insights

• Dashboards created in Power BI or Tableau
• KPI tracking, interactive filters, and charts
• Example insights: sales trends, top products, regional performance

Tools & Technologies

• SQL
• Excel / CSV
• Power BI / Tableau

Project Structure

data_cleaning/
│
├── dataset/
│   └── raw_data.csv
├── scripts/
│   └── data_cleaning.sql
├── dashboards/
│   └── sales_dashboard.pbix
├── results/
│   └── cleaned_dataset.csv
└── README.md
Results

Cleaned and structured dataset

Automated SQL queries for repeatable cleaning

Ready for dashboard visualization and business insights

Future Improvements

Connect multiple data sources (CSV, Excel, databases)

Full ETL pipeline automation

Advanced dashboards with KPIs and alerts

Author

David Gol
Junior Data Analyst & BI Enthusiast