Principal Component Analysis

Interactive visualization of PCA dimensionality reduction with simulated projections from classic ML datasets

Speed:
Samples:
Components:

Datasets

Iris Dataset (1936)

📊 Simulated 2D/3D projection of 4D iris measurements

Original features: sepal length, sepal width, petal length, petal width

Classes: Setosa, Versicolor, Virginica

Real PCA typically preserves ~95% variance in 2 components

How PCA Works

Step 1: Center data by subtracting mean

Step 2: Compute covariance matrix

Step 3: Find eigenvalues/eigenvectors

Step 4: Select principal components

Step 5: Transform data

K-Means Clustering

Clustering

Unsupervised clustering

Learn more →

DBSCAN

Clustering

Density-based spatial clustering

Learn more →

Anomaly Detection

Outlier Detection

Identify outliers using various algorithms

Learn more →

Understanding Principal Component Analysis (PCA)