gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: test_data_dir returns base dir for fxcache key match

Browse Source 
test_data_dir() was returning the symbol-specific path
(test_data/futures-baseline/ES.FUT) causing fxcache key mismatch —
the cache was created with the base dir. Now returns the parent
directory so trainer.train(data_dir, "ES.FUT", ...) can discover
the fxcache via matching cache key.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
jgrusewski
2026-04-05 13:49:01 +02:00
parent c9191e7c58
commit 24bae7d101
1 changed files with 21 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
crates/ml/src/trainers/dqn/smoke_tests/helpers.rs
View File

@@ -125,37 +125,45 @@ pub(super) fn load_smoke_data() -> anyhow::Result<(
Ok((train, val))
}
/// Resolve single-symbol test data directory.
/// Resolve base data directory containing symbol subdirectories.
///
/// Returns the PARENT of the symbol directory (e.g. `test_data/futures-baseline`),
/// not the symbol-specific path. Callers pass the symbol separately to
/// `trainer.train(data_dir, "ES.FUT", ...)` which enables fxcache key matching
/// (the cache key hashes all files at data_dir, not just one symbol).
///
/// Uses `FOXHUNT_TEST_DATA` env var if set, otherwise auto-detects
/// `test_data/ES.FUT` relative to the workspace root.
/// Returns `None` if the directory doesn't exist.
/// relative to the workspace root. Returns `None` if no data found.
pub(super) fn test_data_dir() -> Option<String> {
// Check env vars: FOXHUNT_TEST_DATA (explicit), TEST_DATA_DIR (CI PVC root)
for var in &["FOXHUNT_TEST_DATA", "TEST_DATA_DIR"] {
if let Ok(dir) = std::env::var(var) {
let path = std::path::Path::new(&dir);
// Search for ES.FUT in common layouts:
// 1. $DIR/ES.FUT (direct)
// 2. $DIR/ohlcv/ES.FUT (CI PVC layout)
// If the env var points directly at a symbol dir, return its parent
if path.file_name().and_then(|n| n.to_str()) == Some("ES.FUT") {
if let Some(parent) = path.parent() {
return Some(parent.to_string_lossy().into_owned());
}
}
// Check if ES.FUT exists as a subdirectory
for sub in &["ES.FUT", "ohlcv/ES.FUT"] {
let candidate = path.join(sub);
if candidate.exists() {
return Some(candidate.to_string_lossy().into_owned());
if path.join(sub).exists() {
return Some(path.to_string_lossy().into_owned());
}
}
}
}
// Auto-detect from workspace root: test_data/ES.FUT or test_data/ohlcv/ES.FUT
// Auto-detect from workspace root
let manifest = std::env::var("CARGO_MANIFEST_DIR").unwrap_or_default();
let workspace = std::path::Path::new(&manifest)
.parent() // crates/
.and_then(|p| p.parent()) // repo root
.unwrap_or(std::path::Path::new("../.."));
let test_data = workspace.join("test_data");
for sub in &["futures-baseline/ES.FUT", "ES.FUT", "ohlcv/ES.FUT"] {
let candidate = test_data.join(sub);
if candidate.exists() {
// Return the base dir that contains ES.FUT as a subdirectory
for base in &["futures-baseline", ".", "ohlcv"] {
let candidate = test_data.join(base);
if candidate.join("ES.FUT").exists() {
return Some(candidate.to_string_lossy().into_owned());
}
}