Diffprivlib v0.5

Differential-Privacy

The Dataset contains details about bank customers who are withdrawing their accounts. The dataset includes personal information like Age, Income, Sex, Type of Credit card used.

Goal

The goal of this repository is to predict the attrition of the customer after adding noise to the personal details of the customers.

This project addresses the following Data Analysis topics:

Data Exploration and Preparation-

Learn about the dataset:

• Is there missing data?
• Is it categorical/ordinal?

Data Visualization and Presentation-

• Plotting relational heatmaps of features

Data Representation and Transformation-

• Droping some of the columns which many not contribute much to our analysis
• Encoding features into ordinal values
• Encoding features using One Hot Encoding
• Adding noise to features using the Differenial Privacy Library
• Prediction

Installation and Usage

• Python 3 and pip.
• Set up a virtual environment (optional, but recommended).
• Install dependencies using pip: pip install -r requirements.txt.

Libraries/Dependencies

Visualisation

• Seaborn
• Matplotlib
• Diffprivlib

Analysis

• Scikit Learn

Data

• NumPy
• Pandas

Tools/Environments

• Jupyter
• Python3