data_science_nanodegree

This Repository is just for testing all the concepts learned during the nanodegree

In this project we are going to use the IBM telco churn dataset.

Project Motivation

I work for a telco company and this dataset in interesting because churn is a common problem in telco environment. Aside of that, It is a good working ground, where I can use most of the concepts that are discussed on the nanodegree and use a formal approach to a data science project.

Installation

To run this code you need to install the requirement file in this repository using conda:

conda install requirements.txt

Here is the file list in the repository:

.
└── data_science_nanodegre
├── LICENSE
├── README.md
├── checklist.txt
├── data
│   ├── src : Contain the images that give context to the results
│   │   ├── competition.png
│   │   ├── img
│   │   │   ├── churn distribution.png
│   │   │   └── correlation.png
│   │   ├── offer E high churn.png
│   │   ├── output.png
│   │   └── payment ciclye.png
│   └── telco.csv : Dataset containing all the data used for the analysis
├── notebook
│   └── eda.ipynb : Notebook file containing all the analysis
└── requirements.txt : Requirement file, with all the libraries used on the project

Results

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

Acknowledgments

Thank you IBM for providing a such a good dataset.

@misc{ibm_team_2024, title={Telco customer churn (11.1.3+)}, url={https://www.kaggle.com/dsv/8360350}, DOI={10.34740/KAGGLE/DSV/8360350}, publisher={Kaggle}, author={IBM Team}, year={2024} }