pca-analyzer

What problem does it solve?

PCA reduces high-dimensional data to a smaller set of uncorrelated components, preserving as much variance as possible and enabling simpler analysis and visualization.

Core Features & Use Cases

• Standardization and covariance preparation to enable meaningful PCA.
• Eigen-decomposition and projection onto top components to reveal latent structure.
• Use cases include exploratory data analysis, 2D/3D visualization, and preprocessing for clustering or regression to mitigate multicollinearity.

Quick Start

Run pca_analyzer(df, variance_threshold=0.90) to obtain the transformed_data, loadings, and explained_variance.