This repository consists of files required to deploy a Machine Learning Web App for salary prediction created with Streamlit and deployed on Heroku platform.
If you want to view the deployed model, click on the heroku deployed button above or in the following link:
Deployed at: https://salary-prediction-st.herokuapp.com/
The data are available from the 2021 stack overflow survey: Download Full Data Set(CSV)
In order to create the model the pycaret library used with data for full time developers having income less than 250000 and greter than 10000. The application makes predictions using the following features (columns):
- Country
- Education Level
- Professional Level
- Years of experience
To recreate this web app on your own computer without deployment on heroku, do the following.
Firstly, we will create a conda environment called myenv
conda create -n myenv python=3.7.11
Secondly, we will login to the myenv environement
conda activate myenv
Download requirements.txt file
wget https://raw.githubusercontent.com/quartermaine/Salary-prediction-deploy/main/requirements.txt
Pip install libraries
pip install -r requirements.txt
Download and unzip contents from https://github.com/quartermaine/Salary-prediction-deploy/archive/refs/heads/main.zip
streamlit run app.py
----- Important Note -----
If the webapp is not working and you get the message as shown in the picture given below, it is occuring just because free dynos for this particular month provided by Heroku have been completely used. You can access the webpage on 1st of the next month.
