$$
% Define your custom commands here
\newcommand{\bmat}[1]{\begin{bmatrix}#1\end{bmatrix}}
\newcommand{\E}{\mathbb{E}}
\newcommand{\P}{\mathbb{P}}
\newcommand{\S}{\mathbb{S}}
\newcommand{\R}{\mathbb{R}}
\newcommand{\S}{\mathbb{S}}
\newcommand{\norm}[2]{\|{#1}\|_{{}_{#2}}}
\newcommand{\pd}[2]{\frac{\partial #1}{\partial #2}}
\newcommand{\pdd}[2]{\frac{\partial^2 #1}{\partial #2^2}}
\newcommand{\vectornorm}[1]{\left|\left|#1\right|\right|}
\newcommand{\abs}[1]{\left|{#1}\right|}
\newcommand{\mbf}[1]{\mathbf{#1}}
\newcommand{\mc}[1]{\mathcal{#1}}
\newcommand{\bm}[1]{\boldsymbol{#1}}
\newcommand{\nicefrac}[2]{{}^{#1}\!/_{\!#2}}
\newcommand{\argmin}{\operatorname*{arg\,min}}
\newcommand{\argmax}{\operatorname*{arg\,max}}
\newcommand{\dd}{\operatorname{d}\!}
$$
API reference
Configuration and data
The subject file, the observations CSV and its validation, and the daily bookkeeping.
| config |
Subject metadata, goals, and safety limits. |
| schema |
CSV column definitions and validation. |
| io |
Loading observations from CSV into episode arrays. |
| daily |
The morning routine’s bookkeeping: record today’s readings, keep a plan log. |
| constants |
Physiological and unit constants, with provenance. |
The model
State and parameter types, the physiology, the step map, the observations.
| models.types |
Core datatypes: model state, parameters, and daily inputs. |
| models.energetics |
Energy expenditure: resting metabolism, the thermic effect of food, and |
| models.partition |
Body-composition partitioning: how much of a mass change is fat. |
| models.glycogen |
Fast water compartments: glycogen-bound and sodium-associated water. |
| models.dynamics |
The continuous-time model, its one-day step map, and the process-noise model. |
| models.observation |
The observation model: what a bathroom scale actually reports. |
Filters
Model-agnostic Kalman, unscented and extended filters and smoothers.
| filters.common |
Shared filter types and numerical helpers. |
| filters.linear |
Linear Kalman filter, RTS smoother, and the local-linear-trend model. |
| filters.ukf |
Unscented (sigma-point) Kalman filter and smoother. |
| filters.ekf |
Extended Kalman filter using JAX automatic differentiation. |
Estimation
Phase 1 noise identification, phase 2 joint estimation, reparameterization, the backtest.
Control
Cost terms and the receding-horizon controller.
Exercise energy
MET estimates from a routine CSV or a dated workout spreadsheet.
| routine |
A minimal, current-state definition of a lifting routine. |
| exercise |
Estimating exercise energy expenditure from a logged lifting session. |
| tracker_write |
Appending a repeated session to the workout tracker spreadsheet. |