Packages | Limen

📄️Data

Fetch raw market data, form optional bars, and hand experiment-ready splits to the rest of Limen.

Define manifests and run basic or adaptive parameter search.

Replay selected experiment rounds into validated models and run them bar-by-bar at inference time.

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

Provide the lower-level technical indicator library that manifests and custom prep functions build on.

Build higher-level model inputs and target helpers on top of raw bars and indicator columns.

Hold stateless transform helpers for target construction and data cleanup.

Fit train-only feature scaling and apply it consistently across validation and test data.

Score classifier and regressor outputs so experiments can compare permutations on consistent metrics.

Turn finished experiment runs into analyzable tables for prediction quality, confusion behavior, backtests, and parameter diagnostics.

Inference-time cohort surfaces for aggregating decoder outputs from completed Limen experiments.

Evaluate aligned predictions as trading outcomes through a vectorized snapshot.

Hold the smaller cross-cutting helpers that support experiments without belonging to one primary domain package.

Calibrate model probabilities and choose decision thresholds inside manifest-driven experiments.

Provide the limen shell command for YAML validation, profiling, execution, manifest storage, and project scaffolding.

Build supervised target columns from market data for manifest-driven and custom experiments.

Parse, validate, compile, store, and profile declarative YAML experiment manifests.

9 items