Wednesday, 16 August 2017

Data Clustering

Assalamu'alaikum and hi. Weww. Such a tiring days. List to do (today) à nothing 😂

Since Monday, I’ve been working on data clustering. I really don’t know how to do it. I’ve only made it until the scatter plot but the scatter plot only show the results of COICOP analysis. What is COICOP actually?😕 

Okay COICOP is the number that can determine the item’s code. This COICOP made up from COICOP 4,6 and 7. From the COICOP 4, it’s the classification that was identified. When it comes to COICOP 6, the item was named fully with it’s description. Apa yang ada dalam COICOP 6 pun ada dalam COICOP 7. So, it’s not really confusing on that. OK I’ll give the example. The class for Food and Beverages is 013 and  for Twisties’s COICOP 6 is 013013. That is just the example OK! Not the real data HAHAHA 😝 

But then, I need to use a software which is Orange Canvas to visualize my data. The real problem is, I need to determine the data clustering. The data clustering isn’t easy duhhhhh. Seriously! It is because the data collected are messy and also I don’t know how to identify the clustering based on tokens/words. I need to divide the word into group and classify it. I also need to identify the data based on the same words for different string.

To be exact, idk how to do it as the information on the Internet weren’t enough. Maybe it’s bcs my words or my searching technique wasn’t powerful enough? (Looks like someone gotta teach me how to optimized the use of Google search. LOL jk 😳) TU LA HARITU DOK KATA ORANG, KAN DAH SENDIRI PUN DAK BETOI 😆

Tapi kerja ni memang buatkan fokus tak berhenti (sebab urgent jugak haritu). I woke up from my bed and I realised that I have panda eyes. OMG. Teruk gila lebam bawah mata. Serious. Tak tipu. Haish. Nanti sambung. Ada kje. Huhu

No comments:

Post a Comment