Skip to content
Skill

pycse

by jkitchin

AI Summary

pycse is a Python library that assists with scientific computing tasks including nonlinear regression, uncertainty quantification, design of experiments, and neural network-based modeling. It's useful for researchers, engineers, and data scientists working on numerical optimization, experimental design, and uncertainty analysis.

Install

# Install skill into your project (87 files)
mkdir -p .cursor/skills/pycse
&& curl --retry 3 --retry-delay 2 --retry-all-errors -o .cursor/skills/pycse/SKILL.md "https://raw.githubusercontent.com/jkitchin/pycse/master/src/pycse/SKILL.md"
&& curl --retry 3 --retry-delay 2 --retry-all-errors -o .cursor/skills/pycse/PYCSE.py "https://raw.githubusercontent.com/jkitchin/pycse/master/src/pycse/PYCSE.py"

Run in your IDE terminal (bash). On Windows, use Git Bash, WSL, or your IDE's built-in terminal. If curl fails with an SSL error, your network may block raw.githubusercontent.com — try using a VPN or download the files directly from the source repo.

Description

Python computations in science and engineering (pycse) - helps with scientific computing tasks including nonlinear regression, uncertainty quantification, design of experiments (DOE), Latin hypercube sampling, surface response modeling, and neural network-based UQ with DPOSE. Use when working with numerical optimization, data fitting, experimental design, or uncertainty analysis.

pycse - Python Computations in Science and Engineering

pycse is a comprehensive library for scientific computing, data analysis, and uncertainty quantification in Python.

1. Nonlinear Regression and Curve Fitting

• nlinfit: Nonlinear least squares fitting with uncertainty quantification • regress: Linear regression with statistics • Supports parameter uncertainty estimation and confidence intervals

2. Design of Experiments (DOE)

• Latin Hypercube Sampling (LHC): Space-filling designs for efficient parameter exploration • Surface Response Modeling: Fit polynomial response surfaces to experimental data • Useful for optimizing experimental conditions with minimal trials

3. Uncertainty Quantification with DPOSE

• DPOSE (Direct Propagation of Shallow Ensembles): Neural network ensemble for UQ • Provides per-sample uncertainty estimates (heteroscedastic) • Handles gaps, extrapolation, and nonlinear relationships • Trained using CRPS or NLL loss for calibrated uncertainties

Quality Score

C

Acceptable

70/100

Standard Compliance35
Documentation Quality62
Usefulness78
Maintenance Signal100
Community Signal100
Scored Yesterday

GitHub Signals

Stars274
Forks74
Issues0
Updated8d ago
View on GitHub

Trust & Transparency

Open Source — GPL-2.0

Source code publicly auditable

Verified Open Source

Hosted on GitHub — publicly auditable

Actively Maintained

Last commit 8d ago

274 stars — Growing Community

74 forks

My Fox Den

Community Rating

Sign in to rate this booster

Works With

claude_desktop