Process Improvement using Data

A Python package for multivariate data analysis, designed experiments, and process monitoring. It covers offline model-building (PCA, PLS, TPLS) and on-line, self-updating monitoring (adaptive PCA / PLS), a designed-experiments engine that reaches past the textbook catalogue (OMARS and D-/I-/A-optimal designs, with a design-quality scorer), control charts, batch-process analysis, and descriptive sensory-panel analysis. Companion to the online textbook Process Improvement using Data.

Contents

• Quick Start
  • Installation
  • PCA Example
  • PLS Example
  • Component Selection
  • On-line Monitoring (Adaptive PCA / PLS)
  • Optimal & OMARS Designs
  • DOE Strategy Example
• Architecture overview
  • Package layout
  • Conventions every subpackage follows
  • The multivariate estimator stack
  • The MCP tool layer
  • Where to make a change
• Scaling and memory
  • The in-memory assumption
  • Estimating the memory you need
  • When this is not the right tool
  • Roadmap
• User Guide
  • Multivariate Analysis
  • Cross-Validation
  • Model Evaluation and Visualization
  • Experimental Strategy Recommendation
  • Evaluating Design Quality
  • Generating OMARS Designs
  • Descriptive panel data: validate, check the panel, relate to the product
• API Reference
  • Multivariate Analysis
  • Univariate Statistics
  • Process Monitoring
  • Designed Experiments
  • Regression
  • Batch Data Analysis
  • Bivariate Analysis
  • Visualization

Applied DoE

• Applied DoE
  • Before you start
  • Phase A. Foundations
  • Phase B. Full factorial designs
  • Phase C. Doing less, learning more
  • Phase D. Optimization
  • Sources and attribution

Case studies

• Case studies
  • Latent variable modelling
  • Least squares modelling
  • Design and analysis of experiments
  • Process monitoring
  • Sources and attribution

Development

• Development
  • Authoring an MCP tool
  • Error-Handling Style Guide
  • Logging
  • Reproducibility Contract (RNG Handling)
  • Deprecation Policy