Skip to main content

limen.sfd

Package ready-to-run Single-File Decoders that plug directly into the Universal Experiment Loop.

Canonical docs​

What this package owns​

Owns packaged SFD modules and the reference architectures they rely on. Does not own experiment execution, data retrieval, or the lower-level indicator, feature, scaler, and transform libraries it composes.

Key entry points​

Entry pointUse caseNotes
logreg_binaryStandard manifest-driven binary-classification SFDExported at the package root
random_binaryBaseline classifier for comparisonExported at the package root
xgboost_regressorRegression-style SFDExported at the package root
foundational_rule_basedRule-based foundational SFDExported at the package root
foundational_sfdFull catalog of packaged SFDsSubpackage with production-oriented SFD modules
reference_architectureModel-function templates without the packaged data pipelineStarting point for custom SFD work

Adjacent modules​

  • limen.experiment runs SFDs and consumes params() plus either manifest() or custom prep/model functions.
  • limen.data, limen.indicators, limen.features, limen.transforms, and limen.scalers provide the building blocks that manifest-driven SFDs wire together.
  • limen.metrics is commonly used inside the reference architecture model functions.

Quick orientation​

sfd/
├── foundational_sfd/          # Packaged SFDs with params + manifest
│   ├── logreg_binary.py
│   ├── dlinear_regressor.py
│   ├── lightgbm_binary.py
│   ├── random_binary.py
│   ├── rule_based.py
│   ├── xgboost_regressor.py
│   └── tabpfn_binary.py       # Optional
└── reference_architecture/    # Model-function implementations and templates
    ├── logreg_binary.py
    ├── dlinear_regressor.py
    ├── lightgbm_binary.py
    ├── random_binary.py
    ├── rule_based.py
    ├── xgboost_regressor.py
    └── tabpfn_binary.py

Things to know​

  • A foundational SFD owns the experiment shape, while the matching reference architecture owns the model training logic.
  • The lazy tabpfn_binary module and symbols are importable without the extra; constructing or training the TabPFN model requires vaquum-limen[tabpfn].
  • The simplest path to a new SFD is to copy an existing foundational SFD, adjust params(), and modify the manifest chain.
  • SFD modules are expected to stay cheap and stateless at import and manifest-construction time.