"""Opt-in numeric feature cache. Keys include actual signals and fitted block state.""" from contextlib import contextmanager from contextvars import ContextVar from functools import lru_cache import hashlib import os from pathlib import Path import platform import tempfile import joblib import numpy as np import scipy _SEARCH = ContextVar("wisp_search_memory", default=None) _ACTIVE = ContextVar("wisp_feature_store", default=None) @lru_cache(maxsize=1) def _backend(): from wisp.cpu import features as original from . import features as fast digest = hashlib.sha256() from importlib.util import find_spec native = [find_spec("wisp_fast."+key) for key in ("_kernels","_cis_conv","_cis_intervals","_family_kernels")] for path in [original.__file__, fast.__file__, __file__]+[s.origin for s in native if s is not None]: if path: digest.update(Path(path).read_bytes()) digest.update(repr((np.__version__,scipy.__version__,joblib.__version__, platform.machine(), platform.processor())).encode()) return digest.hexdigest() @contextmanager def feature_cache(directory, *, max_entry_mb=512): """Reuse exact NPY feature matrices. Use a private, same-host cache directory. Caller controls the directory lifetime. Bound any single entry with max_entry_mb. Atomic replacement supports racing workers. There is no cross-filesystem lock. """ if directory is None: yield return if max_entry_mb <= 0: raise ValueError("max_entry_mb must be positive") path = Path(directory) / _backend() path.mkdir(parents=True, exist_ok=True) token = _ACTIVE.set((path, max_entry_mb*1024**2)) try: yield finally: _ACTIVE.reset(token) def transform_blocks(blocks, X): config = _ACTIVE.get() shared_search = _SEARCH.get() if shared_search is not None and config is None: return shared_search.transform(blocks,X) if config is None: shared = (len(blocks) >= 2 and X.flags.c_contiguous and all(getattr(b,"zscore",False) and hasattr(b,"transform_normalized") for b in blocks)) if shared: from wisp.cpu.features import _as_3d from .features import _normalize z = _normalize(_as_3d(X)) return [b.transform_normalized(z) for b in blocks] return [block.transform(X) for block in blocks] directory, limit = config signal = hashlib.sha256(np.ascontiguousarray(X).view(np.uint8)).digest() features = [] for block in blocks: # feature_names_ is display metadata produced during transform. Every # fit-dependent quantity, including shapelet values, remains in the key. state = {k:v for k,v in vars(block).items() if k not in ("feature_names_","_conv_plan","_quant_plan")} key = joblib.hash((type(block).__module__, type(block).__qualname__, state, X.dtype.str,X.shape,X.strides,signal),hash_name="sha1") path = directory / (key+".npy") try: arr = np.load(path, allow_pickle=False, mmap_mode="r") except FileNotFoundError: arr = block.transform(X) if arr.nbytes <= limit: tmp = None try: with tempfile.NamedTemporaryFile(dir=directory, delete=False) as stream: tmp = stream.name np.save(stream, arr, allow_pickle=False) os.replace(tmp,path) finally: if tmp and os.path.exists(tmp): os.unlink(tmp) else: if hasattr(block, "feature_names_") and not block.feature_names_: block.transform(X[:1]) features.append(arr) return features