Principal Components Analysis (PCA) System

A Principal Components Analysis (PCA) System is a matrix decomposition algorithm that applies a PCA algorithm to solve a PCA task.

• Context:
  • It can range from being a Single-Thread PCA System to being a Distributed PCA System.
  • …
• Example(s):
  • sklearn.decomposition.PCA(n_components) [1].
  • org.apache.spark.mllib.linalg.distributed.RowMatrix.computePrincipalComponents() [2].
  • …
• Counter-Example(s):
  • an SVD System.
  • a QR Decomposition System.
• See: Spark MLlib.

---

---

References

2017

• http://mahout.apache.org/release-notes/Apache-Mahout-0.13.0-Release-Notes.pdf
  • QUOTE: Mahout has historically focused on highly scalable algorithms, and since moving on from MapReduce-based jobs, Mahout now includes some Mahout-Samsara based implementations:
    • Distributed Principal Component Analysis (PCA)

2015

• http://scikit-learn.org/stable/modules/decomposition.html#principal-component-analysis-pca
  • QUOTE: PCA is used to decompose a multivariate dataset in a set of successive orthogonal components that explain a maximum amount of the variance. In scikit-learn, PCA is implemented as a transformer object that learns n components in its fit method, and can be used on new data to project it on these components.

2015

• http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html
  • QUOTE:

  from sklearn.decomposition import PCA
  iris = datasets.load_iris()
  X = iris.data
  pca = sklearn.decomposition.PCA(n_components=2)
  X_r = pca.fit(X).transform(X)
  

---