ruv_swarm_ml/
lib.rs

1//! Machine learning integration for RUV Swarm
2//!
3//! This crate provides neural forecasting capabilities for agent-specific time series prediction,
4//! ensemble methods, and swarm-level forecasting coordination.
5
6#![cfg_attr(target_arch = "wasm32", no_std)]
7#![allow(unused_imports)] // TODO: Remove when implementation is complete
8
9extern crate alloc;
10
11#[cfg(target_arch = "wasm32")]
12use alloc::{
13    boxed::Box,
14    string::{String, ToString},
15    vec::Vec,
16    format,
17    vec,
18};
19
20#[cfg(target_arch = "wasm32")]
21use alloc::collections::BTreeMap as HashMap;
22
23#[cfg(not(target_arch = "wasm32"))]
24use std::collections::HashMap;
25
26#[cfg(not(target_arch = "wasm32"))]
27use std::format;
28
29#[cfg(not(target_arch = "wasm32"))]
30use std::vec;
31
32pub mod agent_forecasting;
33pub mod ensemble;
34pub mod models;
35pub mod time_series;
36
37#[cfg(target_arch = "wasm32")]
38pub mod wasm_bindings;
39
40// Re-export main types
41pub use agent_forecasting::{
42    AgentForecastingManager,
43    AgentForecastContext,
44    ModelSpecialization,
45    ForecastDomain,
46    ForecastRequirements,
47};
48
49pub use ensemble::{
50    EnsembleForecaster,
51    EnsembleConfig,
52    EnsembleStrategy,
53    OptimizationMetric,
54};
55
56pub use models::{
57    ModelFactory,
58    ModelType,
59    ForecastModel,
60};
61
62pub use time_series::{
63    TimeSeriesData,
64    TimeSeriesProcessor,
65    TransformationType,
66};
67
68#[cfg(target_arch = "wasm32")]
69pub use wasm_bindings::*;
ruv_swarm_ml/lib.rs

ruv_swarm_ml/
lib.rs
