Hello folks !
I’m following the ML engineer path and at the moment I’m studying unsupervised learning methods.I’ve some troubles with PCA applications at Python.
Could someone suggest me a tutorial or an article that let me undestand better this item ?
Thank you very much since now.
What exactly about PCA are you having troubles with. The statistics of it, the linear algebra, the information theory aspect, how to apply it?
Thank for your help.
The problem is not on the single steps (I’m quite good in maths generally) , but I’ m looking for “something” in which theoric descriptions are mixed with the application codes in Python.
This will help me to make a sketch on the item in order to minimize learning time.
I would go straight to the documentation and then see anything linked by it (as a starting point).
For example, scikit-learn has: sklearn.decomposition.PCA — scikit-learn 1.2.2 documentation
Since you have a fairly good idea in the maths and all you need is code examples, I might even ask chat-gpt for more code examples. Obviously this needs to be cross-checked for blind-spots but the most important ones are mathematical. You could try looking at people’s projects in Kaggle but I find that places like kaggle have sometimes varying levels of technique.
Thank you for your reply.
I will try to check on scikit-learn site as you suggested.
I would like to make this effort because these items aren’‘t so easy.
I would try to schematize items : if there are 10 theory steps to arrive at our goal , I would like to put an example code after each step.
At the moment I’ m not still able to see projects on Kaggle because I’m at 30 percent of the course.