AWS sagemaker tutorial ML model train and deploy and test End-to-End

educational AWS sagemaker ML model train and deploy
MAKE SURE YOU KNOW
1 HOW TO USE ONLY .JOBLIB TO SAVE AND USE ML MODEL FOR BOTH HYPERS AND END POINT CREATION
2 USE ONLY JUPYTER FOR CODE, NO USE .PY FILE . ALL CODE CAN BE EXECUTED LINE BY
3 PROVE YOU CAN DO IT, SHARE LINK TO SIMILARE PROJECT




you provide python code and written step by step instructions
it is educational project, acceptance criteria I can do all on my local computer by myself
Find code and provide instructions for code how to create job lib file from only jupyter notebook. Not like Provided code unnecessary creates script.py file and then run it using command line
like in
https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-python-sdk/scikit_learn_randomforest/Sklearn_on_SageMaker_end2end.ipynb
0) use only jupyter notebook , execute lines one by one to create joblib file (better pkl file is possible ) to create ML model code. Use custom ML model code.
For example
https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-python-sdk/scikit_learn_randomforest/Sklearn_on_SageMaker_end2end.ipynb
do not create script.py file and then run it using command line
like in
https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-python-sdk/scikit_learn_randomforest/Sklearn_on_SageMaker_end2end.ipynb
1) train ML model saved in joblib file (use sklearn and specific custom ) using many AWS instances for parallel hyperparamters finding. read data train and test data from current folder for s3 bucket
As base can be used
https://github.com/aws/amazon-sagemaker-examples/blob/main/advanced_functionality/scikit_learn_bring_your_own_model/scikit_learn_bring_your_own_model.ipynb
2) create end point with A) best parameters found B) autoscaling . autoscaling is fast as possible to support load change from several requests per second to hundreds requests per second during few seconds
3) how to send as many as needed requests to sagmeker endpoint from my local laptop from any computer on web without AWS credentials , with from several requests per second to hundreds requests per second during few seconds. Prove all requests processed correctly: prediction from code running locally is the same as prediction done by sagemaker running on AWS. provide python code for testing on my local computer

---------------------------------------------------------------------------------------------
I do not provide my ASW credentials
you do develop all code on your own AWS set up and then teach me how to do on my AWS account
teaching may be don during online meeting
-----------------------------------------------------------------------------------------------

you have 7 days to do

https://github.com/aws/amazon-sagemaker-examples/blob/main/advanced_functionality/scikit_learn_bring_your_own_model/scikit_learn_bring_your_own_model.ipynb

https://github.com/RamVegiraju/SageMaker-Deployment/blob/master/RealTime/Script-Mode/Sklearn/Regression/sklearn-script.ipynb

https://towardsdatascience.com/deploying-a-pre-trained-sklearn-model-on-amazon-sagemaker-826a2b5ac0b6

https://github.com/RamVegiraju/Pre-Trained-Sklearn-SageMaker

https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/random_cut_forest/random_cut_forest.ipynb






I'm looking for an experienced freelancer who can create a tutorial demonstrating the end-to-end deployment, testing, and training of a machine learning model using AWS SageMaker.

Key requirements:
- The tutorial should be aimed at intermediate users who have some knowledge of machine learning but are not yet experts.
- It should provide clear, step-by-step instructions on how to use SageMaker for deploying and testing a machine learning model.
- I would like the tutorial to cover the use of at least one specific type of machine learning model (regression, classification, or clustering), with a focus on practical application.
- The tutorial should be engaging and easy to follow, with plenty of examples and illustrations.

Ideal skills and experience:
- Extensive knowledge and experience with AWS SageMaker.
- Strong background in machine learning, with the ability to explain complex concepts in a simple and clear way.
- Experience creating educational content or tutorials.
- Previous work with targeting intermediate-level users.
- Familiarity with a variety of machine learning models.