Algomine

Algomine is a web application designed to demonstrate and visualize fundamental data mining algorithms. Built with Flask, it provides an interactive interface for exploring Association Rule Mining (Apriori) and Clustering (K-Means).

Features

• Apriori Algorithm:

  • Analyze transaction data (Groceries dataset) to find frequent itemsets and association rules.
  • Interactive form to set Minimum Support and Minimum Confidence thresholds.
  • Visualizes the resulting association rules as a network graph.
  • Displays high-lift rules for product recommendations.

• K-Means Clustering:

  • Perform clustering on geographical data (Countries dataset).
  • Interactive input for the number of clusters (K).
  • Visualizes the clusters and centroids on a scatter plot.

Technologies Used

• Backend: Python, Flask
• Data Processing: Pandas, NumPy
• Machine Learning: mlxtend (for Apriori), scikit-learn (for K-Means)
• Visualization: Matplotlib, NetworkX
• Frontend: HTML, CSS (Templates)

Installation

1. Clone the repository:

   git clone https://github.com/thisisjackboi/Algomine.git
   cd Algomine

2. Install the required dependencies:

   pip install -r requirements.txt

3. Run the application:

   python app.py

4. Open your browser and navigate to http://127.0.0.1:5000.

Usage

• Navigate to the Apriori section to experiment with market basket analysis.
• Navigate to the K-Means section to explore clustering on country data.

Project Structure

• app.py: Main Flask application file containing routes and logic.
• templates/: HTML templates for the web pages.
• static/: Static assets (CSS, images) and datasets (groceries_dataset.csv, countries_exercise.csv).