Welcome to "Employee Churn Analysis Project". This is the second project of Capstone Project Series, which we will be able to build our own classification models for a variety of business settings.
Also we will research what is Employee Churn?, How it is different from customer churn, Exploratory data analysis and visualization of employee churn dataset using matplotlib and seaborn, model building and evaluation using python scikit-learn and Tensorflow-Keras packages.
We will be able to implement classification techniques in Python. Using Scikit-Learn allowing we to successfully make predictions with Distance Based, Bagging, Boosting algorithms for this project. On the other hand, for Deep Learning you will use Tensorflow-Keras.
At the end of the project, we will have the opportunity to deploy our model using Streamlit.
Before diving into the project, please take a look at the determines and project structure.
NOTE: This project assumes that we already know the basics of coding in Python and are familiar with model deployement as well as the theory behind Distance Based, Bagging, Boosting algorithms, and Confusion Matrices.
First of all we connect our computer to the GitHub with these codes:(we use them just once before the work)
git config --global user.name <username>
git config --global user.email <useremail>
- git clone link
- cd FileName dosyanın içine gir
- git checkout -b new-feature-2 yeni branch acip icine gir
- git branch new-feature-2 eger yeni branch in icinde degilsek oraya gidip değişiklikleri yapiyoruz.
- git add .
- git commit -m "commit"
- git push -u origin new-feature-2 => bunu sadece ilk değişiklikte yapıyoruz. Daha sonrasında tekrar değişiklik yapılırsa sadece git push kullanılır.vs code çalışınca link veriyor. o linke tıklayıp create pull request e tıklıyoruz.sonra merge ediyoruz.
git config --global credential.helper store
# pull / push yaparken, tekrar tekrar sifre sormamasi icin (token süresi bitene kadar) bu komutu kullaniriz