Sales Project - Online Retail II Analysis

This project performs an end-to-end data analysis on the Online Retail II (2010-2011) dataset. The workflow includes data cleaning, storage in a relational database (SQLite), and advanced visualization using Python.

📊 Analysis Performed

1. Top 10 Customers by Spending Identifies high-value customers using SQL aggregation. A logarithmic scale is applied to the bar plot to better visualize differences despite the highly skewed distribution.

2. Top 10 Best-Selling Products Analyzes inventory movement by identifying the most frequently purchased items.

3. Monthly Sales Trends Tracks revenue over time for the main geographical markets (UK, Netherlands, EIRE, Germany) to identify seasonal patterns.

4. Geographical Sales Heatmap A normalized heatmap showing the percentage of monthly sales contributed by each country, allowing for a direct comparison of market performance.

⚙️ How to Run

1. Clone the repository:

   git clone [https://github.com/your-username/SALES_PROJECT_GH.git](https://github.com/your-username/SALES_PROJECT_GH.git)
   cd SALES_PROJECT_GH
   
   

2. Install dependencies: It is recommended to use a virtual environment. pip install -r requirements.txt

3. Database Creation: Run the first script to process the raw data and generate the SQLite database: python3 NOTEBOOKS/sales_1.py

4. Run Analysis: Execute the analysis script to generate insights and view the charts: python3 NOTEBOOKS/sales_project_analysis.py

📌Technical Notes

Data Handling: Used SQLite to demonstrate the ability to manage data through relational queries within a Python workflow.

Visualization: Matplotlib and Seaborn were used for the plots. Logarithmic scaling was chosen for bar charts to handle outliers effectively.

Scalability: The separation of ETL (sales_1.py) and Analysis (sales_project_analysis.py) ensures a modular and clean code structure.