Module 4 — Educational Machine Learning & Data Science
AI & Data Science Playground
Explore client-side, interactive machine learning models: Ordinary Least Squares regression, K-Nearest Neighbors 2D decision boundaries, Decision Tree impurity splits, K-Means clustering, Confusion Matrices, and Feature Normalization.
Linear Regression & Ordinary Least Squares (OLS)
Click canvas to add data points, or step Gradient Descent to optimize cost function.
Equation: y = 1.429x + 9.286
R² Score: 0.9963
MSE: 3.06
RMSE: 1.75
Tip: Click anywhere inside the canvas to add a new observation point (x, y).
K-Nearest Neighbors (KNN) 2D Classifier
Click anywhere on the coordinate plane to position query point X and classify.
Query Point X: (150, 100)
Predicted: Class A
Radius to K-th: 42.5 px
Decision Tree Feature Splitting & Impurity
Calculates Information Gain and Gini Impurity reduction across candidate split features.
K-Means Clustering & Centroid Convergence
Step-by-step centroid updates and cluster boundary recalculations.
Iteration: 0
Inertia (SSE): 0
Status: Initialized
Interactive 2x2 Confusion Matrix & Evaluation Metrics
Adjust True/False classifications to compute Accuracy, Precision, Recall, Specificity & F1-Score.
Data Normalization & Feature Scaling Workbench
Compare Min-Max Normalization [0, 1], Z-Score Standardization (μ=0, σ=1), and Robust Scaling.
