feat(mri): add is_valid_volume guard for NaN/inf/shape/dtype on 3-D arrays

src/pipelines/mri_pipeline.py

@@ -0,0 +1,50 @@
+"""MRI (magnetic resonance imaging) pipeline.
+
+Loads NIfTI volumes (`.nii` / `.nii.gz`), applies a brain mask, harmonizes
+across sites with ComBat (`neuroHarmonize`), and writes per-subject ROI
+statistics as a model-ready Parquet at `data/processed/mri_features.parquet`.
+
+Follows the Data Readiness contract in AGENTS.md §4 and the Parquet storage
+convention in §6: schema validity, domain validity (drop NaN/inf volumes
+with a logged WARNING), determinism (ComBat is RNG-free given fixed input),
+traceability (in/out/dropped counts at INFO), and idempotent overwrite.
+"""
+from __future__ import annotations
+
+import os
+
+import numpy as np
+import pyarrow as pa
+
+from src.core.logger import get_logger
+
+logger = get_logger(__name__)
+
+# Pin BLAS / OpenMP / pyarrow to single-threaded mode so byte-determinism
+# (AGENTS.md §4 rule 3) holds across hardware. Without this, multi-threaded
+# floating-point reductions can reorder and produce non-bit-identical output.
+os.environ.setdefault("OMP_NUM_THREADS", "1")
+os.environ.setdefault("OPENBLAS_NUM_THREADS", "1")
+os.environ.setdefault("MKL_NUM_THREADS", "1")
+pa.set_cpu_count(1)
+pa.set_io_thread_count(1)
+
+
+def is_valid_volume(volume: np.ndarray | None) -> bool:
+    """Return True iff `volume` is a non-empty 3-D numeric array with no NaN/inf.
+
+    Used to drop corrupted volumes before masking + feature extraction.
+    Defensive against the full set of garbage we expect from real archives:
+    lists, None, NaN/inf samples, zero-sized arrays, string-dtype arrays.
+    """
+    if not isinstance(volume, np.ndarray):
+        return False
+    if volume.ndim != 3:
+        return False
+    if volume.size == 0:
+        return False
+    if not np.issubdtype(volume.dtype, np.number):
+        return False
+    if not np.all(np.isfinite(volume)):
+        return False
+    return True

tests/pipelines/test_mri_pipeline.py

@@ -0,0 +1,47 @@
+"""Unit + integration tests for the MRI ComBat pipeline."""
+from __future__ import annotations
+
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+from src.pipelines.mri_pipeline import is_valid_volume
+
+
+FIXTURE_DIR = Path(__file__).parent.parent / "fixtures" / "mri_sample"
+
+
+class TestIsValidVolume:
+    def test_accepts_3d_finite_array(self) -> None:
+        vol = np.zeros((8, 8, 8), dtype=np.float64)
+        assert is_valid_volume(vol) is True
+
+    def test_rejects_wrong_dimension(self) -> None:
+        assert is_valid_volume(np.zeros((8, 8))) is False
+        assert is_valid_volume(np.zeros((8, 8, 8, 2))) is False
+
+    def test_rejects_nan(self) -> None:
+        vol = np.zeros((8, 8, 8))
+        vol[0, 0, 0] = np.nan
+        assert is_valid_volume(vol) is False
+
+    def test_rejects_inf(self) -> None:
+        vol = np.zeros((8, 8, 8))
+        vol[1, 1, 1] = np.inf
+        assert is_valid_volume(vol) is False
+        vol[1, 1, 1] = -np.inf
+        assert is_valid_volume(vol) is False
+
+    def test_rejects_empty(self) -> None:
+        assert is_valid_volume(np.zeros((0, 8, 8))) is False
+        assert is_valid_volume(np.zeros((8, 0, 8))) is False
+        assert is_valid_volume(np.zeros((8, 8, 0))) is False
+
+    def test_rejects_non_numeric_dtype(self) -> None:
+        vol = np.array([[["a", "b"], ["c", "d"]]])
+        assert is_valid_volume(vol) is False
+
+    def test_rejects_non_array(self) -> None:
+        assert is_valid_volume([[[1, 2]], [[3, 4]]]) is False
+        assert is_valid_volume(None) is False