-
Data Collection
-
Data Checks to perform
-
Exploratory data analysis
-
Data Pre-Processing
-
Model Training
-
Choose best model
-
This project understands how the student's performance (test scores) is affected by other variables such as Gender, Ethnicity, Parental level of education, Lunch and Test preparation course.
-
Data Collection
Dataset Source - https://www.kaggle.com/datasets/spscientist/students-performance-in-exams?datasetId=74977
The data consists of 8 column and 1000 rows.
For Deployment: (AWS Elastic Beanstalk) (step by step) make: make a folder: .ebextension>python.config>
option_settings:
"aws:elasticbeanstalk:container:python":
WSGIPath: application:application
make a folder then application.py> copy full code of app.py Then push it on Github
- open aws then sign in
- Search for Elastic Beanstalk open application icon
- create application
- application name: , platform = python
- click on sample application then create application
- search on aws, "codepipeline", click on CodePipeline, create pipeline, pipeline name: , click next
- source provider: Github (version 1), click connect to the Github, confirm it
- select repository name, branch: main, Github webhooks, click next
- Build Provider: Skip
- Deploy provider: AWS Elastic Beanstalk, region, application name, environment name, next
- Review: create pipeline
- if error occurs: delete app.py file
- Deployment Success.
For Deployment: (Azure)
- open azure, sign-in, create the resource
- create Web App, subscription name:, resource group:, name:, publish: code, runtiome: python 3.8, next
- continuous deployment: enable, configure with your github account, organisation: github username, repository: repo name, branch: main, review+create, create
- wait then reload github project page.
- .github/workflows will be created on your repository, click on it
- .yaml fill would be created
- go to github actions, add or update azure....
- Deployment Completed.