Skip to content

Repository Map

This page gives a quick path through the repository for contributors and power users.

Top-level areas

PathPurpose
README.mdGitHub landing page
docs/.vitepress/config.jsNavigation and site structure for the /docs/ site
web/Static landing page assets for the published site root
docs/VitePress source for the versioned documentation site
examples/Notebooks and runnable examples
foreblocks/Main forecasting library
foretools/Companion tooling

foreblocks/

PathPurpose
foreblocks/__init__.pyTop-level public exports
foreblocks/config.pyPublic configuration dataclasses (ModelConfig, TrainingConfig)
foreblocks/models/Model-level composition APIs (ForecastingModel, GraphForecastingModel)
foreblocks/layers/Reusable layer families, including graph convolutions and graph construction
foreblocks/core/Core forecasting internals and heads
foreblocks/training/Trainer and training support
foreblocks/evaluation/Evaluation and metrics
foreblocks/data/Dataset and dataloader helpers
foreblocks/ts_handler/Preprocessing and sequence construction
foreblocks/tf/Transformer stack and advanced attention
foreblocks/darts/Neural architecture search
foreblocks/mltracker/Experiment tracking
foreblocks/hybrid_mamba/Hybrid Mamba SSM blocks (HybridMambaBlock, HybridMamba2Block, SSD)
foreblocks/mamba/Original Mamba backbone with MoE, positional encoding, and eval tools
foreblocks/kan/Kolmogorov-Arnold Network backbone

foretools/

PathPurpose
foretools/tsgen/Synthetic time-series generation
foretools/bohb/BOHB, TPE configuration, pruning, and optimization plots
foretools/foreminer/Exploratory analysis and diagnostics
foretools/fengineer/Feature engineering utilities
foretools/emd_like/Decomposition tools
foretools/tsaug/AutoDA-Timeseries: automated data augmentation with adaptive policy

Recommended entry points by task

TaskEntry point
Training a baseline modelREADME.md, Getting Started
Understanding architecture compositionforeblocks/models/
Working with graph forecastingforeblocks/models/graph_forecasting.py, foreblocks/layers/graph/
Configuring runsforeblocks/config.py
Building dataloadersforeblocks/data/dataset.py
Adding preprocessing logicforeblocks/ts_handler/preprocessing.py
Exploring transformer internalsforeblocks/tf/transformer.py
Working on architecture searchforeblocks/darts/
Using SSM / Mamba-style blocksforeblocks/hybrid_mamba/layers.py
Generating synthetic dataforetools/tsgen/
Running hyperparameter searchforetools/bohb/
Augmenting training data adaptivelyforetools/tsaug/

MIT License