Skip to main content

limen.backtest

Evaluate aligned predictions as trading outcomes through a vectorized snapshot.

Canonical docs​

What this package owns​

Owns Limen's snapshot backtest and the assumptions it encodes. Does not own signal generation, experiment logging, or portfolio bookkeeping.

Key entry points​

Entry pointUse caseNotes
backtest_snapshotVectorized evaluation across roundsfrom limen.backtest import backtest_snapshot
long_flat_strategyDefault execution model, or a template for a new strategyReturns an ExecutionResult; from limen.backtest import long_flat_strategy

The package root re-exports all three entry points (backtest_snapshot, long_flat_strategy, ExecutionResult); module-path imports keep working.

Adjacent modules​

  • limen.log uses backtest_snapshot() to summarize experiment permutations.
  • limen.experiment and limen.sfd sit upstream by producing the predictions that backtests consume.

Quick orientation​

backtest/
├── backtest_snapshot.py     # Vectorized snapshot evaluator (price validation + ledger)
└── long_flat_strategy.py    # Default long-only execution model

Things to know​

  • The package root currently does not re-export the backtest helpers, so import from the module paths directly.
  • backtest_snapshot() is the standard analysis path for vectorized experiment-sweep evaluation.
  • Snapshot return and cost outputs are basis-point scaled (*_bps columns), matching the basis-point fee and slippage inputs.