junifer 0.0.4.dev829__py3-none-any.whl → 0.0.5__py3-none-any.whl

junifer/storage/tests/test_hdf5.py

@@ -25,7 +25,12 @@ from junifer.storage.utils import (
 def test_get_valid_inputs() -> None:
     """Test valid inputs."""
     storage = HDF5FeatureStorage(uri="/tmp")
-    assert storage.get_valid_inputs() == ["matrix", "vector", "timeseries"]
+    assert storage.get_valid_inputs() == [
+        "matrix",
+        "vector",
+        "timeseries",
+        "scalar_table",
+    ]
 
 
 def test_single_output(tmp_path: Path) -> None:
@@ -808,7 +813,7 @@ def test_store_timeseries(tmp_path: Path) -> None:
     data = np.array([[10], [20], [30], [40], [50]])
     col_names = ["signal"]
 
-    # Store vector
+    # Store timeseries
     storage.store_timeseries(
         meta_md5=meta_md5,
         element=element_to_store,
@@ -822,6 +827,53 @@ def test_store_timeseries(tmp_path: Path) -> None:
     assert_array_equal(read_df.values, data)
 
 
+def test_store_scalar_table(tmp_path: Path) -> None:
+    """Test scalar table store.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+
+    """
+    uri = tmp_path / "test_store_scalar_table.hdf5"
+    storage = HDF5FeatureStorage(uri=uri)
+    # Metadata to store
+    element = {"subject": "test"}
+    meta = {
+        "element": element,
+        "dependencies": ["numpy"],
+        "marker": {"name": "brainprint"},
+        "type": "FreeSurfer",
+    }
+    # Process the metadata
+    meta_md5, meta_to_store, element_to_store = process_meta(meta)
+    # Store metadata
+    storage.store_metadata(
+        meta_md5=meta_md5, element=element_to_store, meta=meta_to_store
+    )
+
+    # Data to store
+    data = np.array([[10, 20], [30, 40], [50, 60]])
+    col_names = ["roi1", "roi2"]
+    row_names = ["ev1", "ev2", "ev3"]
+
+    # Store timeseries
+    storage.store_scalar_table(
+        meta_md5=meta_md5,
+        element=element_to_store,
+        data=data,
+        col_names=col_names,
+        row_names=row_names,
+        row_header_col_name="eigenvalue",
+    )
+
+    # Read into dataframe
+    read_df = storage.read_df(feature_md5=meta_md5)
+    # Check if data are equal
+    assert_array_equal(read_df.values, data)
+
+
 def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
     """Create data to store.
 
@@ -854,13 +906,19 @@ def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
             "col_names": [f"col-{i}" for i in range(10)],
             "matrix_kind": "full",
         }
-    elif kind == "timeseries":
+    elif kind in "timeseries":
         data_to_store = {
             "data": np.arange(20).reshape(2, 10),
             "col_names": [f"col-{i}" for i in range(10)],
         }
-    else:
-        raise ValueError(f"Unknown kind {kind}.")
+    elif kind in "scalar_table":
+        data_to_store = {
+            "data": np.arange(50).reshape(5, 10),
+            "row_names": [f"row-{i}" for i in range(5)],
+            "col_names": [f"col-{i}" for i in range(10)],
+            "row_header_col_name": "row",
+        }
+
     for i in range(n_elements):
         element = {"subject": f"sub-{i // 2}", "session": f"ses-{i % 2}"}
         meta = {
@@ -903,6 +961,7 @@ def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
         (10, 3, "matrix"),
         (10, 5, "matrix"),
         (10, 5, "timeseries"),
+        (10, 5, "scalar_table"),
     ],
 )
 def test_multi_output_store_and_collect(
@@ -930,21 +989,20 @@ def test_multi_output_store_and_collect(
     meta_md5, all_data = _create_data_to_store(n_elements, kind)
 
     for t_data in all_data:
-        # Store metadata for tables
+        # Store metadata
         storage.store_metadata(
             meta_md5=meta_md5,
             element=t_data["element"],
             meta=t_data["meta"],
         )
+        # Store data
         if kind == "vector":
-            # Store tables
             storage.store_vector(
                 meta_md5=meta_md5,
                 element=t_data["element"],
                 **t_data["data"],
             )
         elif kind == "matrix":
-            # Store tables
             storage.store_matrix(
                 meta_md5=meta_md5,
                 element=t_data["element"],
@@ -956,11 +1014,17 @@ def test_multi_output_store_and_collect(
                 element=t_data["element"],
                 **t_data["data"],
             )
+        elif kind == "scalar_table":
+            storage.store_scalar_table(
+                meta_md5=meta_md5,
+                element=t_data["element"],
+                **t_data["data"],
+            )
     # Check that base URI does not exist yet
     assert not uri.exists()
 
     for t_data in all_data:
-        # Convert element to preifx
+        # Convert element to prefix
         prefix = element_to_prefix(t_data["element"])
         # URIs for data storage
         elem_uri = uri.parent / f"{prefix}{uri.name}"
@@ -977,7 +1041,7 @@ def test_multi_output_store_and_collect(
     # Check that base URI exists now
     assert uri.exists()
 
-    # # Read unified metadata
+    # Read unified metadata
     read_unified_meta = storage.list_features()
     assert meta_md5 in read_unified_meta
 
@@ -989,6 +1053,10 @@ def test_multi_output_store_and_collect(
         data_size = np.sum([x["data"]["data"].shape[0] for x in all_data])
         assert len(all_df) == data_size
         idx_names = [x for x in all_df.index.names if x != "timepoint"]
+    elif kind == "scalar_table":
+        data_size = np.sum([x["data"]["data"].shape[0] for x in all_data])
+        assert len(all_df) == data_size
+        idx_names = [x for x in all_df.index.names if x != "row"]
     else:
         assert len(all_df) == len(all_data)
         idx_names = all_df.index.names
@@ -1013,6 +1081,10 @@ def test_multi_output_store_and_collect(
             assert_array_equal(t_series.values, t_data["data"]["data"])
             series_names = t_series.columns.values.tolist()
             assert series_names == t_data["data"]["col_names"]
+        elif kind == "scalar_table":
+            assert_array_equal(t_series.values, t_data["data"]["data"])
+            series_names = t_series.columns.values.tolist()
+            assert series_names == t_data["data"]["col_names"]
 
 
 def test_collect_error_single_output() -> None:

junifer/storage/utils.py

@@ -14,6 +14,15 @@ import numpy as np
 from ..utils.logging import logger, raise_error
 
 
+__all__ = [
+    "get_dependency_version",
+    "process_meta",
+    "element_to_prefix",
+    "store_matrix_checks",
+    "matrix_to_vector",
+]
+
+
 def get_dependency_version(dependency: str) -> str:
     """Get dependency version.
 

junifer/testing/__init__.py

@@ -1,4 +1,4 @@
-"""Provide imports for testing sub-package."""
+"""Testing components."""
 
 # Authors: Federico Raimondo <f.raimondo@fz-juelich.de>
 #          Synchon Mandal <s.mandal@fz-juelich.de>
@@ -6,3 +6,6 @@
 
 from . import datagrabbers
 from .utils import get_testing_data
+
+
+__all__ = ["datagrabbers", "get_testing_data"]

junifer/testing/datagrabbers.py

@@ -1,4 +1,4 @@
-"""Provide testing DataGrabbers."""
+"""Testing DataGrabbers."""
 
 # Authors: Federico Raimondo <f.raimondo@fz-juelich.de>
 #          Synchon Mandal <s.mandal@fz-juelich.de>
@@ -14,6 +14,13 @@ from nilearn import datasets, image
 from ..datagrabber.base import BaseDataGrabber
 
 
+__all__ = [
+    "OasisVBMTestingDataGrabber",
+    "SPMAuditoryTestingDataGrabber",
+    "PartlyCloudyTestingDataGrabber",
+]
+
+
 class OasisVBMTestingDataGrabber(BaseDataGrabber):
     """DataGrabber for Oasis VBM testing data.
 
@@ -181,7 +188,7 @@ class PartlyCloudyTestingDataGrabber(BaseDataGrabber):
         """Initialize the class."""
         datadir = tempfile.mkdtemp()
         # Define types
-        types = ["BOLD", "BOLD_confounds"]
+        types = ["BOLD"]
         self.reduce_confounds = reduce_confounds
         self.age_group = age_group
         super().__init__(types=types, datadir=datadir)
@@ -242,10 +249,10 @@ class PartlyCloudyTestingDataGrabber(BaseDataGrabber):
         out["BOLD"] = {
             "path": Path(self._dataset["func"][i_sub]),
             "space": "MNI152NLin2009cAsym",
-        }
-        out["BOLD_confounds"] = {
-            "path": Path(self._dataset["confounds"][i_sub]),
-            "format": "fmriprep",
+            "confounds": {
+                "path": Path(self._dataset["confounds"][i_sub]),
+                "format": "fmriprep",
+            },
         }
 
         return out

junifer/testing/tests/test_partlycloudytesting_datagrabber.py

@@ -28,13 +28,13 @@ def test_PartlyCloudyTestingDataGrabber() -> None:
         assert out["BOLD"]["path"].exists()
         assert out["BOLD"]["path"].is_file()
 
-        assert "BOLD_confounds" in out
-        assert out["BOLD_confounds"]["path"].exists()
-        assert out["BOLD_confounds"]["path"].is_file()
-        assert "format" in out["BOLD_confounds"]
-        assert "fmriprep" == out["BOLD_confounds"]["format"]
+        assert "confounds" in out["BOLD"]
+        assert out["BOLD"]["confounds"]["path"].exists()
+        assert out["BOLD"]["confounds"]["path"].is_file()
+        assert "format" in out["BOLD"]["confounds"]
+        assert "fmriprep" == out["BOLD"]["confounds"]["format"]
 
     with PartlyCloudyTestingDataGrabber(reduce_confounds=False) as dg:
         out = dg["sub-01"]
-        assert "format" in out["BOLD_confounds"]
-        assert "fmriprep" == out["BOLD_confounds"]["format"]
+        assert "format" in out["BOLD"]["confounds"]
+        assert "fmriprep" == out["BOLD"]["confounds"]["format"]

junifer/testing/utils.py

@@ -6,6 +6,9 @@
 from pathlib import Path
 
 
+__all__ = ["get_testing_data"]
+
+
 def get_testing_data(fname: str) -> Path:
     """Get the path to a testing data file.
 

junifer/utils/__init__.py

@@ -1,4 +1,4 @@
-"""Provide imports for utils sub-package."""
+"""General utilities and helpers."""
 
 # Authors: Federico Raimondo <f.raimondo@fz-juelich.de>
 #          Synchon Mandal <s.mandal@fz-juelich.de>
@@ -6,4 +6,15 @@
 
 from .fs import make_executable
 from .logging import configure_logging, logger, raise_error, warn_with_log
-from .helpers import run_ext_cmd
+from .helpers import run_ext_cmd, deep_update
+
+
+__all__ = [
+    "make_executable",
+    "configure_logging",
+    "logger",
+    "raise_error",
+    "warn_with_log",
+    "run_ext_cmd",
+    "deep_update",
+]

junifer/utils/fs.py

@@ -8,6 +8,9 @@ import stat
 from pathlib import Path
 
 
+__all__ = ["make_executable"]
+
+
 def make_executable(path: Path) -> None:
     """Make ``path`` executable.
 

junifer/utils/helpers.py

@@ -3,12 +3,16 @@
 # Authors: Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
+import collections.abc
 import subprocess
-from typing import List
+from typing import Dict, List
 
 from .logging import logger, raise_error
 
 
+__all__ = ["run_ext_cmd", "deep_update"]
+
+
 def run_ext_cmd(name: str, cmd: List[str]) -> None:
     """Run external command via subprocess.
 
@@ -51,3 +55,30 @@ def run_ext_cmd(name: str, cmd: List[str]) -> None:
             ),
             klass=RuntimeError,
         )
+
+
+def deep_update(d: Dict, u: Dict) -> Dict:
+    """Deep update `d` with `u`.
+
+    From: "https://stackoverflow.com/questions/3232943/update-value-of-a-nested
+    -dictionary-of-varying-depth"
+
+    Parameters
+    ----------
+    d : dict
+        The dictionary to deep-update.
+    u : dict
+        The dictionary to deep-update `d` with.
+
+    Returns
+    -------
+    dict
+        The updated dictionary.
+
+    """
+    for k, v in u.items():
+        if isinstance(v, collections.abc.Mapping):
+            d[k] = deep_update(d.get(k, {}), v)
+        else:
+            d[k] = v
+    return d

junifer/utils/logging.py

@@ -4,13 +4,16 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
-try:
+import sys
+
+
+if sys.version_info < (3, 12):
     from distutils.version import LooseVersion
-except ImportError:  # pragma: no cover
+else:  # pragma: no cover
     from looseversion import LooseVersion
 
 import logging
-import sys
+import warnings
 from pathlib import Path
 from subprocess import PIPE, Popen, TimeoutExpired
 from typing import Dict, NoReturn, Optional, Type, Union
@@ -19,6 +22,16 @@ from warnings import warn
 import datalad
 
 
+__all__ = [
+    "WrapStdOut",
+    "get_versions",
+    "log_versions",
+    "configure_logging",
+    "raise_error",
+    "warn_with_log",
+]
+
+
 logger = logging.getLogger("JUNIFER")
 
 # Set up datalad logger level to warning by default
@@ -32,6 +45,23 @@ _logging_types = {
 }
 
 
+# Copied over from stdlib and tweaked to our use-case.
+def _showwarning(message, category, filename, lineno, file=None, line=None):
+    s = warnings.formatwarning(message, category, filename, lineno, line)
+    logger.warning(str(s))
+
+
+# Overwrite warnings display to integrate with logging
+
+
+def capture_warnings():
+    """Capture warnings and log them."""
+    warnings.showwarning = _showwarning
+
+
+capture_warnings()
+
+
 class WrapStdOut(logging.StreamHandler):
     """Dynamically wrap to sys.stdout.
 
@@ -313,5 +343,4 @@ def warn_with_log(
         The warning subclass (default RuntimeWarning).
 
     """
-    logger.warning(msg)
     warn(msg, category=category, stacklevel=2)

junifer/utils/tests/test_logging.py

@@ -145,8 +145,16 @@ def test_log_file(tmp_path: Path) -> None:
         assert any("Warn3 message" in line for line in lines)
         assert any("Error3 message" in line for line in lines)
 
+    # This should raise a warning (test that it was raised)
     with pytest.warns(RuntimeWarning, match=r"Warn raised"):
         warn_with_log("Warn raised")
+
+    # This should log the warning (workaround for pytest messing with logging)
+    from junifer.utils.logging import capture_warnings
+
+    capture_warnings()
+
+    warn_with_log("Warn raised 2")
     with pytest.raises(ValueError, match=r"Error raised"):
         raise_error("Error raised")
     with open(tmp_path / "test4.log") as f:

{junifer-0.0.4.dev829.dist-info → junifer-0.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.4.dev829
+Version: 0.0.5
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
@@ -29,19 +29,20 @@ Description-Content-Type: text/markdown
 License-File: LICENSE.md
 License-File: AUTHORS.rst
 Requires-Dist: click <8.2,>=8.1.3
-Requires-Dist: numpy <1.27,>=1.24
-Requires-Dist: scipy <=1.11.4,>=1.9.0
-Requires-Dist: datalad <0.20,>=0.15.4
-Requires-Dist: pandas <2.2,>=1.4.0
-Requires-Dist: nibabel <5.11,>=3.2.0
-Requires-Dist: nilearn <=0.10.2,>=0.9.0
-Requires-Dist: sqlalchemy <=2.1.0,>=1.4.27
+Requires-Dist: numpy <2.0.0,>=1.24.0
+Requires-Dist: scipy <=1.14.0,>=1.10.0
+Requires-Dist: datalad <1.2.0,>=1.0.0
+Requires-Dist: pandas <2.3.0,>=2.0.0
+Requires-Dist: nibabel <5.3.0,>=5.2.0
+Requires-Dist: nilearn <=0.10.4,>=0.10.3
+Requires-Dist: sqlalchemy <=2.1.0,>=2.0.25
 Requires-Dist: ruamel.yaml <0.18,>=0.17
 Requires-Dist: h5py >=3.10
 Requires-Dist: httpx[http2] ==0.26.0
 Requires-Dist: tqdm ==4.66.1
 Requires-Dist: templateflow >=23.0.0
-Requires-Dist: importlib-metadata ; python_version < "3.10"
+Requires-Dist: lapy <2.0.0,>=1.0.0
+Requires-Dist: importlib-metadata ; python_version < "3.9"
 Requires-Dist: looseversion ==1.3.0 ; python_version >= "3.12"
 Provides-Extra: all
 Requires-Dist: bctpy ==0.6.0 ; extra == 'all'
@@ -52,14 +53,14 @@ Provides-Extra: dev
 Requires-Dist: tox ; extra == 'dev'
 Requires-Dist: pre-commit ; extra == 'dev'
 Provides-Extra: docs
-Requires-Dist: seaborn <0.13,>=0.11.2 ; extra == 'docs'
-Requires-Dist: sphinx <7.3,>=5.3.0 ; extra == 'docs'
-Requires-Dist: sphinx-gallery <0.15.0,>=0.11.0 ; extra == 'docs'
-Requires-Dist: furo <2023.10.0,>=2022.9.29 ; extra == 'docs'
-Requires-Dist: numpydoc <1.6,>=1.5.0 ; extra == 'docs'
-Requires-Dist: julearn <0.4,>=0.3.0 ; extra == 'docs'
+Requires-Dist: seaborn <0.14.0,>=0.13.0 ; extra == 'docs'
+Requires-Dist: sphinx <7.4.0,>=7.3.0 ; extra == 'docs'
+Requires-Dist: sphinx-gallery <0.17.0,>=0.15.0 ; extra == 'docs'
+Requires-Dist: furo <2024.6.0,>=2024.4.27 ; extra == 'docs'
+Requires-Dist: numpydoc <1.8.0,>=1.6.0 ; extra == 'docs'
+Requires-Dist: julearn ==0.3.3 ; extra == 'docs'
 Requires-Dist: sphinx-copybutton <0.5.3,>=0.5.1 ; extra == 'docs'
-Requires-Dist: towncrier <23.7,>=22.12.0 ; extra == 'docs'
+Requires-Dist: towncrier <23.12.0,>=23.10.0 ; extra == 'docs'
 Requires-Dist: sphinxcontrib-mermaid <0.10,>=0.8.1 ; extra == 'docs'
 Provides-Extra: neurokit2
 Requires-Dist: neurokit2 >=0.1.7 ; extra == 'neurokit2'