(reference_guide)=
# Reference Guide

Welcome to the `delaynet` Reference Guide.
This guide provides comprehensive documentation for the `delaynet` package, a Python library for **reconstructing delay functional networks** from time series data.
Reconstruction can be performed using various building blocks and connectivities,
e.g. by detecting causality relationships with granger causality tests or transfer entropy,
among others.
The package offers a suite of tools for analyzing time series data and reconstructing delay networks, designed to be flexible and extensible, allowing users to apply various methods for preprocessing, detrending, and connectivity analysis.

## What You'll Find in This Guide

- **[Preparation](00_preparation)**: Learn what data format to prepare, or how to generate synthetic data for testing and experimentation, including random data and fMRI time series.

- **[Detrending](10_detrending/index)**: Explore various detrending techniques to standardize time series data, remove trends, and make different time series comparable for connectivities.

- **[Connectivity Measures](20_connectivity/index)**: Learn about the different connectivity measures available in `delaynet`, including Granger Causality, Linear Correlation, Mutual Information, and more.

- **[Network Reconstruction](30_network_reconstruction)**: Understand how to infer the structure of a network from time series data (work in progress).

- **[Network Analysis](40_network_analysis)**: Learn about network pruning methods for simplifying complex networks and topological analysis techniques for analyzing structural properties of networks (work in progress).


```{toctree}
:maxdepth: 2

00_preparation
10_detrending/index
20_connectivity/index
30_network_reconstruction
40_network_analysis
```