Udacity Machine Learning DevOps Engineer project.
REPO: https://github.com/dbaeza0/DRASystem/tree/master
Case of a company concerned about attrition risk: the risk that some of their clients will exit their contracts and decrease the company's revenue. If the client management team is small they're not able to stay in close contact with all their clients.
The company could find helpful to create, deploy, and monitor a risk assessment ML model that will estimate the attrition risk of each of the company's clients. If the model created and deployed is accurate, it will enable the client managers to contact the clients with the highest risk and avoid losing clients and revenue.
Creating and deploying the model isn't the end of our work, though. Most industries are dynamic and constantly changing, and a model that was created a year or a month ago might not still be accurate today. Because of this, we need to set up regular monitoring of the model to ensure that it remains accurate and up-to-date. We need to set up processes and scripts to re-train, re-deploy, monitor, and report on th ML model, so that the company can get risk assessments that are as accurate as possible and minimize client attrition.
- Python 3.11
- Poetry
To install Poetry, you can follow the instructions on the official website: Poetry Installation Guide.
Once Poetry is installed, navigate to your project directory and run the following command to initialize a new Poetry project:
poetry install- We need to define the folder that will be used for storing new data and saving the model. For that purpose, we need
to define in the config.json file:
input_folder_pathentry for storing new dataoutput_model_pathentry for storing production models- Executing wsgi.py will start the API:
python3 app.py
- We then run fullprocess.py:
python3 fullprocess.py