Files
rustytorch/crates/training/rtx-automeasure/src/lib.rs
T
2026-03-04 00:08:42 +00:00

344 lines
9.7 KiB
Rust

//! AutoML system for automatic model selection and hyperparameter optimization
//!
//! This crate provides a complete AutoML system that automatically:
//! - Selects appropriate models based on data characteristics
//! - Optimizes hyperparameters using various strategies
//! - Engineers features automatically
//! - Builds ensemble models
//! - Monitors resources and performance
//!
//! The system integrates with GPU acceleration and follows strict TDD methodology.
pub mod agents;
pub mod error;
pub mod monitoring;
mod simple_test;
pub mod strategies;
pub mod tensor_utils;
// Re-export core types for convenience
pub use error::{AutoMLError, AutoMLResult};
// Re-export rtx-validation components for AutoML integration
pub use rtx_validation::{
// Estimator trait for search compatibility
Estimator as ValidationEstimator,
// Validation error type
ValidationError,
// Cross-validation strategies
cv::{CrossValidator, GroupKFold, KFold, SplitIndices, TimeSeriesSplit},
// Metrics for model evaluation
metrics::{accuracy_score, f1_score, precision_score, recall_score, roc_auc_score},
// Hyperparameter search
search::{BayesSearchCV, GridSearchCV, ParamGrid, RandomizedSearchCV, SearchResult},
};
use rtx_tensor::Tensor;
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use std::time::Instant;
use uuid::Uuid;
/// Task type for machine learning problems
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
pub enum TaskType {
/// Classification task (predict discrete labels)
Classification,
/// Regression task (predict continuous values)
Regression,
}
/// Optimization objective for AutoML
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
pub enum OptimizationObjective {
/// Accuracy for classification
Accuracy,
/// Precision for classification
Precision,
/// Recall for classification
Recall,
/// F1 score for classification
F1Score,
/// Area under ROC curve
AUC,
/// Mean absolute error for regression
MAE,
/// Mean squared error for regression
MSE,
/// Root mean squared error for regression
RMSE,
}
/// Configuration for AutoML agent
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct AutoMLConfig {
pub task_type: TaskType,
pub time_budget_seconds: u64,
pub memory_budget_bytes: u64,
pub cv_folds: u32,
pub objective: OptimizationObjective,
}
impl AutoMLConfig {
pub fn new() -> Self {
Self::default()
}
pub fn with_task_type(mut self, task_type: TaskType) -> Self {
self.task_type = task_type;
self
}
pub fn with_time_budget(mut self, seconds: u64) -> Self {
self.time_budget_seconds = seconds;
self
}
pub fn with_memory_budget(mut self, bytes: u64) -> Self {
self.memory_budget_bytes = bytes;
self
}
pub fn with_objective(mut self, objective: OptimizationObjective) -> Self {
self.objective = objective;
self
}
pub fn with_cv_folds(mut self, folds: u32) -> Self {
self.cv_folds = folds;
self
}
}
impl Default for AutoMLConfig {
fn default() -> Self {
Self {
task_type: TaskType::Classification,
time_budget_seconds: 3600,
memory_budget_bytes: 4 * 1024 * 1024 * 1024, // 4GB
cv_folds: 5,
objective: OptimizationObjective::Accuracy,
}
}
}
/// Progress information for AutoML training
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ProgressInfo {
pub elapsed_time_seconds: f64,
pub completion_percentage: f64,
}
/// Leaderboard entry for model performance
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct LeaderboardEntry {
pub score: f64,
pub model_name: String,
pub hyperparameters: HashMap<String, String>,
pub training_time_seconds: f64,
}
/// Trained AutoML pipeline
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct AutoMLPipeline {
models: Vec<String>,
best_model: String,
hyperparameters: HashMap<String, String>,
feature_transformations: Vec<String>,
validation_score: f64,
}
impl AutoMLPipeline {
pub fn new(
models: Vec<String>,
best_model: String,
hyperparameters: HashMap<String, String>,
feature_transformations: Vec<String>,
validation_score: f64,
) -> Self {
Self {
models,
best_model,
hyperparameters,
feature_transformations,
validation_score,
}
}
pub fn get_models(&self) -> &[String] {
&self.models
}
pub fn get_best_model(&self) -> &str {
&self.best_model
}
pub fn get_hyperparameters(&self) -> &HashMap<String, String> {
&self.hyperparameters
}
pub fn get_validation_score(&self) -> f64 {
self.validation_score
}
pub fn to_json(&self) -> AutoMLResult<String> {
serde_json::to_string(self).map_err(|e| AutoMLError::SerializationError(e.to_string()))
}
pub fn from_json(json: &str) -> AutoMLResult<Self> {
serde_json::from_str(json).map_err(|e| AutoMLError::SerializationError(e.to_string()))
}
}
/// Main AutoML agent
pub struct AutoMLAgent {
config: AutoMLConfig,
id: String,
start_time: Option<Instant>,
leaderboard: Vec<LeaderboardEntry>,
}
impl AutoMLAgent {
pub fn new(config: AutoMLConfig) -> AutoMLResult<Self> {
// Validate configuration
if config.time_budget_seconds == 0 {
return Err(AutoMLError::ConfigurationError(
"Time budget must be greater than 0".to_string(),
));
}
if config.cv_folds == 0 {
return Err(AutoMLError::ConfigurationError(
"CV folds must be greater than 0".to_string(),
));
}
Ok(Self {
config,
id: Uuid::new_v4().to_string(),
start_time: None,
leaderboard: Vec::new(),
})
}
pub fn get_id(&self) -> &str {
&self.id
}
pub async fn fit(&mut self, x: &Tensor, y: &Tensor) -> AutoMLResult<AutoMLPipeline> {
self.start_time = Some(Instant::now());
// Basic validation
if x.shape()[0] != y.shape()[0] {
return Err(AutoMLError::ValidationError(
"X and y must have same number of samples".to_string(),
));
}
// Simple implementation for demonstration
// In a real implementation, this would:
// 1. Analyze data characteristics
// 2. Select candidate models
// 3. Optimize hyperparameters
// 4. Build ensembles
// 5. Validate performance
let models = vec![
"LogisticRegression".to_string(),
"RandomForest".to_string(),
"GradientBoosting".to_string(),
];
let best_model = "RandomForest".to_string();
let mut hyperparameters = HashMap::new();
hyperparameters.insert("n_estimators".to_string(), "100".to_string());
hyperparameters.insert("max_depth".to_string(), "10".to_string());
let feature_transformations = vec![
"StandardScaler".to_string(),
"PolynomialFeatures".to_string(),
];
// Simulate training with some basic score
let validation_score = match self.config.task_type {
TaskType::Classification => 0.85, // 85% accuracy
TaskType::Regression => 0.12, // Low MSE
};
// Add to leaderboard
self.leaderboard.push(LeaderboardEntry {
score: validation_score,
model_name: best_model.clone(),
hyperparameters: hyperparameters.clone(),
training_time_seconds: 10.0,
});
Ok(AutoMLPipeline::new(
models,
best_model,
hyperparameters,
feature_transformations,
validation_score,
))
}
pub async fn predict(&self, _pipeline: &AutoMLPipeline, x: &Tensor) -> AutoMLResult<Tensor> {
// Simple prediction simulation
let n_samples = x.shape()[0];
let device = x.device();
let predictions = match self.config.task_type {
TaskType::Classification => {
// Return class predictions (0 or 1)
Tensor::zeros_typed([n_samples], rtx_tensor::DType::I64, device)?
}
TaskType::Regression => {
// Return continuous predictions
Tensor::zeros_typed([n_samples], rtx_tensor::DType::F32, device)?
}
};
Ok(predictions)
}
pub fn get_leaderboard(&self) -> Vec<LeaderboardEntry> {
let mut sorted = self.leaderboard.clone();
sorted.sort_by(|a, b| b.score.total_cmp(&a.score));
sorted
}
pub fn get_feature_importance(
&self,
_pipeline: &AutoMLPipeline,
) -> AutoMLResult<HashMap<String, f64>> {
let mut importance = HashMap::new();
// Simulate feature importance scores
let n_features = 8; // Assume 8 features for demo
for i in 0..n_features {
importance.insert(format!("feature_{i}"), rand::random::<f64>());
}
Ok(importance)
}
pub fn get_progress(&self) -> ProgressInfo {
let elapsed_time = if let Some(start) = self.start_time {
start.elapsed().as_secs_f64()
} else {
0.0
};
let completion_percentage = if self.config.time_budget_seconds > 0 {
(elapsed_time / self.config.time_budget_seconds as f64 * 100.0).min(100.0)
} else {
0.0
};
ProgressInfo {
elapsed_time_seconds: elapsed_time,
completion_percentage,
}
}
}