Nothing much, really... only an associate.. but nice :) I feel like sharing :) I'm discovering that I do like the "low level" stuff...

I post this article because i think they did a very good job in describing why MLOps is complicated and what a real production pipeline for machine learning and AI should look like. The creation of features and their versioning is a lot of work and it should be open to integration in more model experiments and applications. On the other hand, we are always pushed to try new tools that create over-engineered systems that no one wants to use. https://www.hopsworks.ai/post/mlops-to-ml-systems-with-fti-pipelines

Hi there, I dont know what this means but adding cookiecutter did not go as expected as illustrated in the video: Chapter 2/Project structure I ran this pip install cookiecutter-data-science cookiecutter https://github.com/drivendata/cookiecutter-data-science It failed so I ran ccds https://github.com/drivendata/cookiecutter-data-science These are the many options I was presented with. I just guessed and plugged away. Does anyone know what this is all about? C:\Users\carls>ccds https://github.com/drivendata/cookiecutter-data-science You've downloaded C:\Users\carls\.cookiecutters\cookiecutter-data-science before. Is it okay to delete and re-download it? [y/n] (y): y project_name (project_name): new_project repo_name (new_project): new_project module_name (new_project): new_project author_name (Your name (or your organization/company/team)): carl description (A short description of the project.): new_project_template python_version_number (3.10): Select dataset_storage 1 - none 2 - azure 3 - s3 4 - gcs Choose from [1/2/3/4] (1): 1 Select environment_manager 1 - virtualenv 2 - conda 3 - pipenv 4 - none Choose from [1/2/3/4] (1): 1 Select dependency_file 1 - requirements.txt 2 - environment.yml 3 - Pipfile Choose from [1/2/3] (1): 1 Select pydata_packages 1 - none 2 - basic Choose from [1/2] (1): 2 Select open_source_license 1 - No license file 2 - MIT 3 - BSD-3-Clause Choose from [1/2/3] (1): 2 Select docs 1 - mkdocs 2 - none Choose from [1/2] (1): 2 - none Choose from [1/2] (1): 2 Select include_code_scaffold 1 - Yes 2 - No Choose from [1/2] (1): 1 C:\Users\carls>

I just wanted to share the win here. I've been quiet here lately, but that's because I've been neck deep studying the Microsoft Azure learning path for the AI-102 exam. I took the exam today and passed it. Link to the exam and study materials if anyone else is interested: https://learn.microsoft.com/en-us/credentials/certifications/azure-ai-engineer/?practice-assessment-type=certification P.S. I've used Azure before for 2-3 years and considered myself proficient in it, but AI is new and it felt like learning Azure all over again. Very useful skill to have, imho.

What are some best practices for handling missing data(can you mention an example) in large datasets, and how do you decide which method to use?