Principal Component Analysis, is one of the most useful data analysis and machine learning methods out there. It can be used to identify patterns in highly complex datasets and it can tell you what variables in your data are the most important. Lastly, it can tell you how accurate your new understanding of the data actually is.
Die einfachste Variante um Dimensionen zu reduzieren:
<aside> 💡 🚫 PCA ≠Feature Selection! 🚫 PCA reduces dimensionality by capturing most data variance in few PCs. But it does not assess feature importance. And, you still need all features for the PCs. Feature selection methods select variables without altering the data representation. PCA alters the data representation.
</aside>