Data Preprocessing & Normalization

Master feature scaling concepts. Compare Min-Max scaling, Z-score standardization, Log transform, and Robust scaling. Drag points and see outlier clipping in real-time.

Interactive Sandbox

Data Scaling Timelines Visualizer

Click inside the top number line area to place raw feature points ($X$). Drag points horizontally, or double-click to remove. Choose a transformation scaling method and configure clipping bounds to manage outliers.

Timeline: Raw X vs Scaled X'

1. Select Data Preset

2. Select Normalization Method

Min-Max Range Target Min 0.0
Min-Max Range Target Max 1.0

3. Outlier Clipping (Winsorization)

Double-click on the top timeline area to add a point. Drag nodes horizontally to observe how parameters adjust.
Algebraic Solver

Preprocessing & Scaling Solver

Trace data statistics calculations and step-by-step scaling formulas used to transform raw features.

Step-by-Step Transformations


Raw Feature X Statistics


Central Tendencies

Mean (μ) 0.00
Median (Q2) 0.00

Dispersion & Spread

Std Deviation (σ) 0.00
Interquartile Range (IQR) 0.00

Extremes

Minimum Value (x_min) 0.00
Maximum Value (x_max) 0.00
Evaluation

Feature Scaling Quiz

Test your conceptual understanding of normalization, z-scores, log scale benefits, and outlier protection.

Question 1 of 5 Score: 0/0

Quiz question loading...

Correct Answer!

Explanation text...

Scaling Formulas


  • Min-Max: x' = (x - x_min) / (x_max - x_min)
  • Z-Score: z = (x - μ) / σ
  • Robust: x' = (x - median) / IQR