lightuse / sparkify

Table of Contents

1. Installation
2. Project Motivation
3. File Descriptions
4. Medium Blog Post
5. Acknowledgements

Installation

This project requires Python 3.11 and the following Python libraries installed:

• PySpark 3.5
• pyspark.ml
• pyspark.sql
• SynapseML
• Pandas
• Seaborn
• Matplotlib

Project Motivation

The SaaS business must manage churn. Getting subscriptions to continue is becoming central to business. In addition, we can stop services that should be unnecessary if we know the criteria for stopping unwanted subscriptions. I am very interested in how we deal with churn as I am also in this business.

File Descriptions

Sparkify.ipynb
Sparkify.html
data
|- mini_sparkify_event_data.json

Medium Blog Post

The main findings of the code can be found at the post available here.

Acknowledgements

• Udacity for providing an excellent Data Scientist training program and the project along with the data.