search

Nikronic / Machine-Learning-Models

In This repository I made some simple to complex methods in machine learning. Here I try to build template style code.
MIT License
32 stars 11 forks source link

where is to learn about this ECLAT? #2

Open Sandy4321 opened 4 years ago

Sandy4321 commented 4 years ago

where is to learn about this ECLAT? what sources you used for this https://github.com/Nikronic/Machine-Learning-Models/tree/master/Part%205%20-%20Association%20Rule%20Learning/Section%2017%20-%20Eclat

Nikronic commented 4 years ago

@Sandy4321 Hi, I used the documentation and tutorials of mlxtend library itself. Here is the one.

Also if you want to get into details here you can find them.

Bests

Sandy4321 commented 4 years ago

Great thanks Actually I asked about tutorial like material Something more educational....

Nikronic commented 4 years ago

@Sandy4321 Sorry, do you mean a course or something like that?

Acutally I think if you have good programming background and just want to extend your knowledge and gain a skill in particular area like machine learning, it is better to get introduced to topics by watching youtube videos then following a university course and doing their assignments. That is the way I learn stuff and particularly about ECLAT or all content in my github.

Precisly, I google for a full course like what available in MIT Open Course website or Stanford University then look at the syllabes of content they want to teach or a famous book and I read the index of content, then youtube for every single item that I thing is interesting and if I need more details, I go through university assignments and videos. One more way to get introduced to content is Coursera, Edx, Udacity, etc but you cannot find some of materials like ECLAT there (I could not at the time working on this repo).

By the way, I think the tutorial of mlxtend library itself have covered both theoretical and practical aspects of the idea very well, give it a shot. https://rasbt.github.io/mlxtend/user_guide/frequent_patterns/association_rules/

Sandy4321 commented 4 years ago

but you cannot find some of materials like ECLAT there (I could not at the time working on this repo).

Exactly There is no such a material And on yurtube neither Mlextend giving material how to use code

What looks strange Or complicated papers or nothing educational

Nikronic commented 4 years ago

@Sandy4321 The point is association rule learning is a old topic which currently people do not use it because it fails and large scale problems. And one more thing you need to prepare yourself to get ideas and solution from papers. If I want to be frank with you, I learned many things from papers and implemented them myself. Unfortunately I cannot remember anything from these stuff to help.

Sandy4321 commented 4 years ago

nice slides http://fuzzy.cs.ovgu.de/studium/ida/txt/ida_rules.pdf including Eclat, but wo code example :(

Nikronic commented 4 years ago

@Sandy4321 u just need to match notations with one the libraries. I do not think it's hard. The good part is there are examples in the slide so you can config same example for a implemented ECLAT model and track the code to get the idea. That is what I do most of the times.