[Day 189] I finished the Car Insurance Fraud MLOps project. Thank you MLOps zoomcamp for teaching me so much!

 Hello :)
Today is Day 189!


A quick summary of today:
  • completed the project and wrote project description



The whole project and all info is on my repo

Here is a project diagram I created using lucid.app


Well ~ today I added some final things to my project. 


First I added terraform code to create GCP buckets for mlflow articats and raw data, and also start a VM.

The last one is kind of cool because when we start the VM, mlflow starts automatically as well because the code to start mlflow is included in the `metadata_startup_script` which is:

I also added the whole terraform init, plan and apply setup in the project's Makefile for easy set and start up. So now the make help looks like:


Next, I added pylint

Following the suggestions from MLOps zoomcamp, I added pylint and fixed a lot of whitespace, and import order lines of code as per pylint's suggestions. 

Next, I tried to add some tests using pytest

I added 5 simple tests to some of the prefect flows. 
The exact tests are:
  • test_read_new_data
  • test_predict
  • test_save_predictions
  • test_batch_model_predict
  • test_local_to_gcs
But there is work to be done for more thorough testing. One thing Mage.ai was nice for is that in every block of code, at the end of it there was a dedicated test place so adding tests was very easy (which is not the case for Prefect)

Next, I added python documentation

I used sphinx back in my placement year with Lloyds Banking Group, and I have been adding small docstrings to my code, so adding a sphinx python docs seemed like a nice little addition. I easily set it up, but I could not get github actions to automate this, so I used an alternative:

Use a new branch where the _build folder (normally not uploaded to github because it has many files) is uploaded and netlify watches that branch and updates the docs

Here is the link to the netlify hosted python docs for the project.


Finally, I added some basic git pre-commit hooks

  • trailing-whitespace
  • end-of-file-fixer
  • check-yaml
  • check-added-large-files
  • pytest-check
  • pylint

These are ran and checked before every commit, and the commit is stopped if one fails.



After this, I started putting things together and writing the README of the project, and creating the project diagram (top of this blog).

There are things to improve, but nevertheless DataTalksClub - THANK YOU SO MUCH! MLOps zoomcamp is such an amazing course, and it taught me amazing tools to build amazing things.

From now on, I will continue learning the ongoing LLM zoomcamp - hopefully I will build an amazing project from there as well!


That is all for today!

See you tomorrow :)

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[미리 공부] 기초 통계 복습 (Day 1는 1월2일)

Image
모험을 시작하기 전에 기초 지식을 복습하고자 했다. 오늘 SPSS 대안 프로그램을 찾아보려고 해서 JASP에 대해 알게 되었다. 유용한 프로그램인 것 같아서 선회귀와 기술통계를 내려고 했는데 재미있었다. 그런데 JASP에 대해 더 알기 전에 '기초 통계 지식을 좀 복습을 하고자 하면 좋을 것 같아'란 생각을 들었다. 다행히, Coursera에서 Stanford University의 Guenther Walther 교수님께서 진행된  Introduction to Statistics  무료 강좌가 있다.  좀 부족한 부분은 다양한 검정통계 하는 거고 (F test, t-test, chi-square 등) 이제 JASP 아니면 다른 통계 프로그램 사용하게 되어도 이런 부분을 좀 더 자세히 집중하여 공부하면 된다.  특히 homoscedasticity 및 heteroscedasticity 개념을 기억에 남았다. Homoscedasticity (선): Definition: In a homoscedastic dataset, the variance of the errors (residuals) is constant across all levels of the independent variable(s). In simpler terms, the spread of the residuals is the same throughout the range of predictor values. Heteroscedasticity (악): Definition: Heteroscedasticity occurs when the variance of the errors is not constant across all levels of the independent variable(s). In other words, the spread of residuals changes as the values of the independent variable(s) change. (Udemy 사진) 강의
Read more

[Day 61] Stanford CS224N (NLP with DL): Machine translation, seq2seq + a side CDCGAN mini project

Image
 Hello :) Today is Day 61! A quick summary of today: Covered Lecture 7 : machine translation, seq2seq, attention from Stanford CS224N Tried to make a conditional DCGAN to generate MNIST numbers ( colab ) ( kaggle ) I will first cover the GAN story (then will share my notes from the lecture) So... while watching and taking notes today, I started thinking, what if I can use my notes as data to a model and afterwards, when I want, I can give it raw string text and it will output text in the format of my notes (with my handwriting). Well I started looking around and actually the first model architecture that came to my mind was the GAN (specifically conditional GAN) - I remembered there was a GAN architecture that alongside the pictures, we can give it the labels, and then on-demand generate. In retrospect, there are of course others, but I decided to go with GAN.  For maybe 2 hours I busted my head trying to make a simple model with the EMNIST dataset (english characters), and I kept gett
Read more