Attrition Insight is a data application that allows users to interact with a machine learning model, view data visualizations on the data and see the values of their input saved for future use. It predicts the likelihood of an employee leaving the company based on various demographic and job-related factors.
Features
- Age: Age of employee
- Attrition: Employee attrition status
- Department: Department of work
- DistanceFromHome: what is their distance from hime
- Education: 1-Below College; 2- College; 3-Bachelor; 4-Master; 5-Doctor;
- EducationField: The field they studies in in the University
- EnvironmentSatisfaction: 1-Low; 2-Medium; 3-High; 4-Very High;
- JobSatisfaction: 1-Low; 2-Medium; 3-High; 4-Very High;
- MaritalStatus: Whether they are married, single or divorced
- MonthlyIncome: How much an employee makes a month
- NumCompaniesWorked: Number of companies worked prior to IBM
- WorkLifeBalance: 1-Bad; 2-Good; 3-Better; 4-Best;
- YearsAtCompany: Current years of service in IBM
GUI
Database
Language
Model
- A data application that presents visualizations on both the exploratory data and the KPIs
- A predicitons page to predict by specifying the model you want to use
- View proprietory data loaded in real-time form the remote server
- Predictions are save for further analysis in the future and users can view the history of their prediction input values
To get a local copy up and running, follow these steps.
In order to run this project you need:
- Python
Clone this repository to your desired folder:
cd my-folder
git clone https://github.com/coderacheal/Attrition-Meter.git
Change into the cloned repository
cd Attrition-Meter
Create a virtual environment
python -m venv env
Activate the virtual environment
env/Scripts/activate
Here, you need to recursively install the packages in the requirements.txt
file using the command below
pip install -r requirements.txt
To run the project, execute the following command:
streamlit run 1_๐ _Home.py
- A webpage opens up to view the app
- Login to the app with
username=coderacheal
andpassword:123456
- Finally test a prediction by clicking on the predicitons page
- Note: Users may not be able to access the View Data page as the secrets file is not checked into git
๐ต๐ฝโโ๏ธ Racheal Appiah-kubi
- GitHub: GitHub Profile
- Twitter: Twitter Handle
- LinkedIn: LinkedIn Profile
- Add a front end application for users
Contributions, issues, and feature requests are welcome!
Feel free to check the issues page.
If you like this project kindly show some love, give it a ๐ STAR ๐
I would like to thank all the free available resource made available online
This project is MIT licensed.