https://github.com/farzeennimran/apriori-algorithm

Apriori Algorithm for Association Rule Mining
https://github.com/farzeennimran/apriori-algorithm

algorithm apriori apriori-algorithm apyori association-rule-mining association-rules data-analysis data-mining data-science numpy pandas python

Last synced: 7 days ago
JSON representation

Apriori Algorithm for Association Rule Mining

• Host: GitHub
• URL: https://github.com/farzeennimran/apriori-algorithm
• Owner: farzeennimran
• Created: 2024-06-11T14:34:14.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-06-11T14:56:39.000Z (7 months ago)
• Last Synced: 2024-11-07T02:16:01.590Z (about 2 months ago)
• Topics: algorithm, apriori, apriori-algorithm, apyori, association-rule-mining, association-rules, data-analysis, data-mining, data-science, numpy, pandas, python
• Language: Jupyter Notebook
• Homepage:
• Size: 650 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Apriori algorithm

## Introduction

The Apriori algorithm is a classic algorithm used in data mining to identify frequent itemsets and generate association rules. It is particularly useful for discovering relationships between variables in large datasets. This repository demonstrates the use of the Apriori algorithm to find patterns in a dataset and extract strong association rules.

## What's it About and Why?

This project focuses on the Apriori algorithm, which is widely used in market basket analysis, web usage mining, and bioinformatics. By applying the Apriori algorithm, we can uncover hidden patterns and associations within the data. These insights can help businesses make data-driven decisions, such as product placement strategies, customer segmentation, and targeted marketing campaigns.

## Explanation of the Code

1) Installation:

   To get started, we need to install the necessary libraries

2) Data Preparation:

   We begin by loading and preprocessing the dataset

3) Data Transformation:

   We convert the dataset into a suitable format for association rule mining

4) One-Hot Encoding:

   One-hot encoding is applied to convert categorical data into a binary matrix:

5) Generating and Analyzing Association Rules:

   We experiment with different support and confidence thresholds to find strong rules:

6) Interest Measure:

   We calculate the interest measure, i.e, confidence and lift to rank rules based on their interestingness

## Conclusion

This repository demonstrates the implementation of the Apriori algorithm to find frequent itemsets and generate association rules. By adjusting parameters such as support, confidence, and interest, we can uncover meaningful patterns and relationships within the data. These insights can provide valuable recommendations and help in making informed business decisions.