Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jnyambok/student_performance_predictor
Automated ML Training and Deployment to Azure & GitHub Actions
https://github.com/jnyambok/student_performance_predictor
azure azure-devops ci-cd machinelearning python
Last synced: about 1 month ago
JSON representation
Automated ML Training and Deployment to Azure & GitHub Actions
- Host: GitHub
- URL: https://github.com/jnyambok/student_performance_predictor
- Owner: Jnyambok
- Created: 2024-06-05T17:23:09.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-11-02T10:35:44.000Z (2 months ago)
- Last Synced: 2024-11-02T11:24:18.453Z (2 months ago)
- Topics: azure, azure-devops, ci-cd, machinelearning, python
- Language: Jupyter Notebook
- Homepage:
- Size: 1.32 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CI/CD Pipeline for Student Performance Prediction on Microsoft Azure using Github Actions
This Machine Learning project seeks to predict the math scores of students by assessing various dependent factors and has been deployed through:
* Microsoft Azure Cloud Platform
* Running Locally through Flask.
## Disclaimer : Please note that this error arises because I have deleted the resources on Azure to save on costs
Refer to this screenshot for the last successful deployment
To understand the business case of this project, navigate to the EDA notebook
### Built With
[](https://skillicons.dev)
## 1. Local Deployment
Clone this repo and open the project via your preferred IDE.
* Clone this repo :
```sh
https://github.com/Jnyambok/end_to_end_azure_ml_project.git
```
* Install Flask through pip:
```sh
pip install flask
```
* Then navigate to the "app.py" file in the directory and run:
```sh
python app.py
```
* Open your preferred browser and run paste :
```sh
http://127.0.0.1:5000/predictdata
```
## 2. Deployment through Microsoft Azure Cloud Platform
* Fork this repo and proceed to https://azure.microsoft.com/en-in/free/ to sign up for a free Microsoft Azure account
* Navigate to the resource page and search for "Web App". This should take you to the navigation page. Your free subscription will be pre-filled. Select "create new" at the resource group level and provide your preferred name. Provide a web app name that will appear on the search bar name.
* Select **python 3.8** as the runtime stack and select the region **closest to your physical location**
* Navigate to the **Deployment** section and select **enable**. You will be prompted to link your GitHub account and your forked repo. A workflow configurations file will be added to your repo which will be used to initiate your CI/CD pipeline. To the bottom, ensure basic authentication is off
* You should get the following success message. On your repo, you will find a **.yml** file created for you. This file contains all the necessary metadata for configuring a CI/CD pipeline in Azure through GitHub actions
* Navigate to your GitHub repo and go to the **Actions** tab. Your CI/CD pipeline has been set up for you.
* Click the link provided on the **deployment** action and voila:
* **Do not forget to delete your Azure resource after you're done. Cloud resources are not cheap!**. Navigate to your resource group on the Azure homepage and delete it.
## Future Works and Considerations
- [ ] "Beautify" the home page
- [ ] Deploy through AWS