junifer 0.0.3.dev188__py3-none-any.whl → 0.0.4__py3-none-any.whl

junifer/preprocess/warping/tests/test_space_warper.py

@@ -0,0 +1,198 @@
+"""Provide tests for SpaceWarper."""
+
+# Authors: Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+import socket
+from typing import TYPE_CHECKING, Tuple, Type
+
+import pytest
+from numpy.testing import assert_array_equal, assert_raises
+
+from junifer.datagrabber import DataladHCP1200, DMCC13Benchmark
+from junifer.datareader import DefaultDataReader
+from junifer.pipeline.utils import _check_ants, _check_fsl
+from junifer.preprocess import SpaceWarper
+from junifer.testing.datagrabbers import PartlyCloudyTestingDataGrabber
+
+
+if TYPE_CHECKING:
+    from junifer.datagrabber import BaseDataGrabber
+
+
+@pytest.mark.parametrize(
+    "using, reference, error_type, error_msg",
+    [
+        ("jam", "T1w", ValueError, "`using`"),
+        ("ants", "juice", ValueError, "reference"),
+        ("ants", "MNI152NLin2009cAsym", RuntimeError, "remove"),
+        ("fsl", "MNI152NLin2009cAsym", RuntimeError, "ANTs"),
+    ],
+)
+def test_SpaceWarper_errors(
+    using: str,
+    reference: str,
+    error_type: Type[Exception],
+    error_msg: str,
+) -> None:
+    """Test SpaceWarper errors.
+
+    Parameters
+    ----------
+    using : str
+        The parametrized implementation method.
+    reference : str
+        The parametrized reference to use.
+    error_type : Exception-like object
+        The parametrized exception to check.
+    error_msg : str
+        The parametrized exception message to check.
+
+    """
+    with PartlyCloudyTestingDataGrabber() as dg:
+        # Read data
+        element_data = DefaultDataReader().fit_transform(dg["sub-01"])
+        # Preprocess data
+        with pytest.raises(error_type, match=error_msg):
+            SpaceWarper(
+                using=using,
+                reference=reference,
+                on="BOLD",
+            ).preprocess(
+                input=element_data["BOLD"],
+                extra_input=element_data,
+            )
+
+
+@pytest.mark.parametrize(
+    "datagrabber, element, using",
+    [
+        [
+            DMCC13Benchmark(
+                types=["BOLD", "T1w", "Warp"],
+                sessions=["ses-wave1bas"],
+                tasks=["Rest"],
+                phase_encodings=["AP"],
+                runs=["1"],
+                native_t1w=True,
+            ),
+            ("sub-f9057kp", "ses-wave1bas", "Rest", "AP", "1"),
+            "ants",
+        ],
+        [
+            DataladHCP1200(
+                tasks=["REST1"],
+                phase_encodings=["LR"],
+                ica_fix=True,
+            ),
+            ("100206", "REST1", "LR"),
+            "fsl",
+        ],
+    ],
+)
+@pytest.mark.skipif(_check_fsl() is False, reason="requires FSL to be in PATH")
+@pytest.mark.skipif(
+    _check_ants() is False, reason="requires ANTs to be in PATH"
+)
+@pytest.mark.skipif(
+    socket.gethostname() != "juseless",
+    reason="only for juseless",
+)
+def test_SpaceWarper_native(
+    datagrabber: "BaseDataGrabber", element: Tuple[str, ...], using: str
+) -> None:
+    """Test SpaceWarper for native space warping.
+
+    Parameters
+    ----------
+    datagrabber : DataGrabber-like object
+        The parametrized DataGrabber objects.
+    element : tuple of str
+        The parametrized elements.
+    using : str
+        The parametrized implementation method.
+
+    """
+    with datagrabber as dg:
+        # Read data
+        element_data = DefaultDataReader().fit_transform(dg[element])
+        # Preprocess data
+        output, _ = SpaceWarper(
+            using=using,
+            reference="T1w",
+            on="BOLD",
+        ).preprocess(
+            input=element_data["BOLD"],
+            extra_input=element_data,
+        )
+        # Check
+        assert isinstance(output, dict)
+
+
+@pytest.mark.parametrize(
+    "datagrabber, element, space",
+    [
+        [
+            DMCC13Benchmark(
+                types=["T1w"],
+                sessions=["ses-wave1bas"],
+                tasks=["Rest"],
+                phase_encodings=["AP"],
+                runs=["1"],
+                native_t1w=False,
+            ),
+            ("sub-f9057kp", "ses-wave1bas", "Rest", "AP", "1"),
+            "MNI152NLin2009aAsym",
+        ],
+        [
+            DMCC13Benchmark(
+                types=["T1w"],
+                sessions=["ses-wave1bas"],
+                tasks=["Rest"],
+                phase_encodings=["AP"],
+                runs=["1"],
+                native_t1w=False,
+            ),
+            ("sub-f9057kp", "ses-wave1bas", "Rest", "AP", "1"),
+            "MNI152NLin6Asym",
+        ],
+    ],
+)
+@pytest.mark.skipif(
+    _check_ants() is False, reason="requires ANTs to be in PATH"
+)
+def test_SpaceWarper_multi_mni(
+    datagrabber: "BaseDataGrabber",
+    element: Tuple[str, ...],
+    space: str,
+) -> None:
+    """Test SpaceWarper for MNI space warping.
+
+    Parameters
+    ----------
+    datagrabber : DataGrabber-like object
+        The parametrized DataGrabber objects.
+    element : tuple of str
+        The parametrized elements.
+    space : str
+        The parametrized template space to transform to.
+
+    """
+    with datagrabber as dg:
+        # Read data
+        element_data = DefaultDataReader().fit_transform(dg[element])
+        pre_xfm_data = element_data["T1w"]["data"].get_fdata().copy()
+        # Preprocess data
+        output, _ = SpaceWarper(
+            using="ants",
+            reference=space,
+            on=["T1w"],
+        ).preprocess(
+            input=element_data["T1w"],
+            extra_input=element_data,
+        )
+        # Checks
+        assert isinstance(output, dict)
+        assert output["space"] == space
+        with assert_raises(AssertionError):
+            assert_array_equal(pre_xfm_data, output["data"])

junifer/stats.py

@@ -7,7 +7,7 @@
 from typing import Any, Callable, Dict, List, Optional
 
 import numpy as np
-from scipy.stats import trim_mean
+from scipy.stats import mode, trim_mean
 from scipy.stats.mstats import winsorize
 
 from .utils import logger, raise_error
@@ -24,10 +24,11 @@ def get_aggfunc_by_name(
         Name to identify the function. Currently supported names and
         corresponding functions are:
 
-        * ``winsorized_mean`` -> :func:`scipy.stats.mstats.winsorize`
         * ``mean`` -> :func:`numpy.mean`
-        * ``std`` -> :func:`numpy.std`
+        * ``winsorized_mean`` -> :func:`scipy.stats.mstats.winsorize`
         * ``trim_mean`` -> :func:`scipy.stats.trim_mean`
+        * ``mode`` -> :func:`scipy.stats.mode`
+        * ``std`` -> :func:`numpy.std`
         * ``count`` -> :func:`.count`
         * ``select`` -> :func:`.select`
 
@@ -40,6 +41,7 @@ def get_aggfunc_by_name(
     -------
     function
         Respective function with ``func_params`` parameter set.
+
     """
     from functools import partial  # local import to avoid sphinx error
 
@@ -51,6 +53,7 @@ def get_aggfunc_by_name(
         "trim_mean",
         "count",
         "select",
+        "mode",
     }
     if func_params is None:
         func_params = {}
@@ -93,6 +96,8 @@ def get_aggfunc_by_name(
         elif pick is not None and drop is not None:
             raise_error("Either pick or drop must be specified, not both.")
         func = partial(select, **func_params)
+    elif name == "mode":
+        func = partial(mode, **func_params)
     else:
         raise_error(
             f"Function {name} unknown. Please provide any of "
@@ -115,6 +120,7 @@ def count(data: np.ndarray, axis: int = 0) -> np.ndarray:
     -------
     numpy.ndarray
         Number of elements along the given axis.
+
     """
     ax_size = data.shape[axis]
     if axis < 0:
@@ -137,7 +143,7 @@ def winsorized_mean(
         The axis to calculate winsorized mean on (default None).
     **win_params : dict
         Dictionary containing the keyword arguments for the winsorize function.
-        E.g. ``{'limits': [0.1, 0.1]}``.
+        E.g., ``{'limits': [0.1, 0.1]}``.
 
     Returns
     -------
@@ -149,6 +155,7 @@ def winsorized_mean(
     --------
     scipy.stats.mstats.winsorize :
         The winsorize function used in this function.
+
     """
     win_dat = winsorize(data, axis=axis, **win_params)
     win_mean = win_dat.mean(axis=axis)
@@ -180,6 +187,13 @@ def select(
     numpy.ndarray
         Subset of the inputted data with the select settings
         applied as specified in ``select_params``.
+
+    Raises
+    ------
+    ValueError
+        If both ``pick`` and ``drop`` are None or
+        if both ``pick`` and ``drop`` are not None.
+
     """
 
     if pick is None and drop is None:

junifer/storage/base.py

@@ -30,6 +30,11 @@ class BaseFeatureStorage(ABC):
     single_output : bool, optional
         Whether to have single output (default True).
 
+    Raises
+    ------
+    ValueError
+        If required storage type(s) is(are) missing from ``storage_types``.
+
     """
 
     def __init__(
@@ -39,13 +44,15 @@ class BaseFeatureStorage(ABC):
         single_output: bool = True,
     ) -> None:
         self.uri = uri
+        # Convert storage_types to list
         if not isinstance(storage_types, list):
             storage_types = [storage_types]
+        # Check if required inputs are found
         if any(x not in self.get_valid_inputs() for x in storage_types):
             wrong_storage_types = [
                 x for x in storage_types if x not in self.get_valid_inputs()
             ]
-            raise ValueError(
+            raise_error(
                 f"{self.__class__.__name__} cannot store {wrong_storage_types}"
             )
         self._valid_inputs = storage_types
@@ -170,6 +177,7 @@ class BaseFeatureStorage(ABC):
             The element as a dictionary.
         meta : dict
             The metadata as a dictionary.
+
         """
         raise_error(
             msg="Concrete classes need to implement store_metadata().",

junifer/storage/hdf5.py

@@ -57,6 +57,7 @@ def _create_chunk(
     ------
     ValueError
         If `kind` is not one of ['vector', 'matrix', 'timeseries'].
+
     """
     if kind in ["vector", "matrix"]:
         features_data = np.concatenate(chunk_data, axis=-1)
@@ -678,9 +679,13 @@ class HDF5FeatureStorage(BaseFeatureStorage):
         elif isinstance(data, list):
             if self.force_float32:
                 data = [
-                    x.astype(dtype=np.dtype("float32"), casting="same_kind")
-                    if x.dtype == np.dtype("float64")
-                    else x
+                    (
+                        x.astype(
+                            dtype=np.dtype("float32"), casting="same_kind"
+                        )
+                        if x.dtype == np.dtype("float64")
+                        else x
+                    )
                     for x in data
                 ]
         # Handle cases for existing and new entry

junifer/storage/pandas_base.py

@@ -114,7 +114,8 @@ class PandasBaseFeatureStorage(BaseFeatureStorage):
         if len(elem_idx) == 1:
             # Create normal index for vector
             index = pd.Index(
-                data=list(elem_idx.values())[0], name=list(elem_idx.keys())[0]
+                data=next(iter(elem_idx.values())),
+                name=next(iter(elem_idx.keys())),
             )
         else:
             # Create multiindex for timeseries

junifer/storage/sqlite.py

@@ -366,6 +366,7 @@ class SQLiteFeatureStorage(PandasBaseFeatureStorage):
             The element as a dictionary.
         meta : dict
             The metadata as a dictionary.
+
         """
         # Get sqlalchemy engine
         engine = self.get_engine(element=element)

junifer/storage/tests/test_hdf5.py

@@ -175,7 +175,7 @@ def test_store_metadata_and_list_features(tmp_path: Path) -> None:
     # List the stored features
     features = storage.list_features()
     # Get the first MD5
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     # Check the MD5
     assert meta_md5 == feature_md5
 
@@ -838,6 +838,7 @@ def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
         The meta md5.
     dict
         The data to store.
+
     """
     all_data = []
     t_md5 = None

junifer/storage/tests/test_sqlite.py

@@ -335,7 +335,7 @@ def test_store_df_and_read_df(tmp_path: Path) -> None:
     with pytest.raises(ValueError, match="Only one"):
         storage.read_df(feature_name="wrong_name", feature_md5="wrong_md5")
     # Get MD5 hash of features
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "feature_md5" == feature_md5
     # Check for key
     assert "BOLD_markername" == features[feature_md5]["name"]
@@ -373,7 +373,7 @@ def test_store_metadata(tmp_path: Path) -> None:
         meta_md5=meta_md5, element=element_to_store, meta=meta_to_store
     )
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert meta_md5 == feature_md5
 
 
@@ -474,7 +474,7 @@ def test_store_matrix(tmp_path: Path) -> None:
     stored_names = [f"{i}~{j}" for i in row_names for j in col_names]
 
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
 
     read_df = storage.read_df(feature_md5=feature_md5)
@@ -498,7 +498,7 @@ def test_store_matrix(tmp_path: Path) -> None:
         for j in range(data.shape[1])
     ]
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
     read_df = storage.read_df(feature_md5=feature_md5)
     assert list(read_df.columns) == stored_names
@@ -563,7 +563,7 @@ def test_store_matrix(tmp_path: Path) -> None:
     ]
 
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
     read_df = storage.read_df(feature_md5=feature_md5)
     assert list(read_df.columns) == stored_names
@@ -595,7 +595,7 @@ def test_store_matrix(tmp_path: Path) -> None:
     ]
 
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
     read_df = storage.read_df(feature_md5=feature_md5)
     assert list(read_df.columns) == stored_names
@@ -632,7 +632,7 @@ def test_store_matrix(tmp_path: Path) -> None:
     ]
 
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
     read_df = storage.read_df(feature_md5=feature_md5)
     assert list(read_df.columns) == stored_names
@@ -663,7 +663,7 @@ def test_store_matrix(tmp_path: Path) -> None:
     ]
 
     features = storage.list_features()
-    feature_md5 = list(features.keys())[0]
+    feature_md5 = next(iter(features.keys()))
     assert "BOLD_fc" == features[feature_md5]["name"]
     read_df = storage.read_df(feature_md5=feature_md5)
     assert list(read_df.columns) == stored_names

junifer/storage/tests/test_utils.py

@@ -23,12 +23,12 @@ from junifer.storage.utils import (
     "dependency, max_version",
     [
         ("click", "8.2"),
-        ("numpy", "1.26"),
-        ("datalad", "0.19"),
-        ("pandas", "1.6"),
-        ("nibabel", "4.1"),
-        ("nilearn", "0.10.0"),
-        ("sqlalchemy", "1.5.0"),
+        ("numpy", "1.27"),
+        ("datalad", "0.20"),
+        ("pandas", "2.2"),
+        ("nibabel", "5.11"),
+        ("nilearn", "0.11.0"),
+        ("sqlalchemy", "2.1.0"),
         ("ruamel.yaml", "0.18.0"),
     ],
 )

junifer/storage/utils.py

@@ -131,6 +131,7 @@ def element_to_prefix(element: Dict) -> str:
     -------
     str
         The element converted to prefix.
+
     """
     logger.debug(f"Converting element {element} to prefix.")
     prefix = "element"

junifer/testing/datagrabbers.py

@@ -55,7 +55,10 @@ class OasisVBMTestingDataGrabber(BaseDataGrabber):
         """
         out = {}
         i_sub = int(subject.split("-")[1]) - 1
-        out["VBM_GM"] = {"path": Path(self._dataset.gray_matter_maps[i_sub])}
+        out["VBM_GM"] = {
+            "path": Path(self._dataset.gray_matter_maps[i_sub]),
+            "space": "MNI152Lin",
+        }
 
         return out
 
@@ -141,8 +144,8 @@ class SPMAuditoryTestingDataGrabber(BaseDataGrabber):
         anat_fname = self.datadir / f"{subject}_T1w.nii.gz"
         nib.save(fmri_img, fmri_fname)
         nib.save(anat_img, anat_fname)
-        out["BOLD"] = {"path": fmri_fname}
-        out["T1w"] = {"path": anat_fname}
+        out["BOLD"] = {"path": fmri_fname, "space": "MNI152Lin"}
+        out["T1w"] = {"path": anat_fname, "space": "native"}
         return out
 
 
@@ -236,12 +239,13 @@ class PartlyCloudyTestingDataGrabber(BaseDataGrabber):
         """
         out = {}
         i_sub = int(subject.split("-")[1]) - 1
-        out["BOLD"] = {"path": Path(self._dataset["func"][i_sub])}
-        conf_format = "fmriprep"
-
+        out["BOLD"] = {
+            "path": Path(self._dataset["func"][i_sub]),
+            "space": "MNI152NLin2009cAsym",
+        }
         out["BOLD_confounds"] = {
             "path": Path(self._dataset["confounds"][i_sub]),
-            "format": conf_format,
+            "format": "fmriprep",
         }
 
         return out

junifer/testing/utils.py

@@ -18,6 +18,7 @@ def get_testing_data(fname: str) -> Path:
     -------
     pathlib.Path
         The absolute path to the file.
+
     """
     t_path = Path(__file__).parent / "data" / fname
     if not t_path.exists():

junifer/tests/test_stats.py

@@ -21,6 +21,8 @@ from junifer.stats import count, get_aggfunc_by_name, select, winsorized_mean
         ("count", None),
         ("trim_mean", None),
         ("trim_mean", {"proportiontocut": 0.1}),
+        ("mode", None),
+        ("mode", {"keepdims": True}),
     ],
 )
 def test_get_aggfunc_by_name(name: str, params: Optional[Dict]) -> None:

junifer/utils/__init__.py

@@ -6,3 +6,4 @@
 
 from .fs import make_executable
 from .logging import configure_logging, logger, raise_error, warn_with_log
+from .helpers import run_ext_cmd

junifer/utils/helpers.py

@@ -0,0 +1,53 @@
+"""Provide helper functions for the package."""
+
+# Authors: Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+import subprocess
+from typing import List
+
+from .logging import logger, raise_error
+
+
+def run_ext_cmd(name: str, cmd: List[str]) -> None:
+    """Run external command via subprocess.
+
+    Parameters
+    ----------
+    name : str
+        The name of the command.
+    cmd : list of str
+        The command to run as list of string.
+
+    Raises
+    ------
+    RuntimeError
+        If command fails.
+
+    """
+    # Convert list to str
+    cmd_str = " ".join(cmd)
+    logger.info(f"{name} command to be executed:\n{cmd_str}")
+    # Run command via subprocess
+    process = subprocess.run(
+        cmd_str,  # string needed with shell=True
+        stdin=subprocess.DEVNULL,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        shell=True,  # needed for respecting $PATH
+        check=False,
+    )
+    # Check for success or failure
+    if process.returncode == 0:
+        logger.info(
+            f"{name} command succeeded with the following output:\n"
+            f"{process.stdout}"
+        )
+    else:
+        raise_error(
+            msg=(
+                f"{name} command failed with the following error:\n"
+                f"{process.stdout}"
+            ),
+            klass=RuntimeError,
+        )

junifer/utils/logging.py

@@ -4,9 +4,13 @@
 #          Synchon Mandal <s.mandal@fz-juelich.de>
 # License: AGPL
 
+try:
+    from distutils.version import LooseVersion
+except ImportError:  # pragma: no cover
+    from looseversion import LooseVersion
+
 import logging
 import sys
-from distutils.version import LooseVersion
 from pathlib import Path
 from subprocess import PIPE, Popen, TimeoutExpired
 from typing import Dict, NoReturn, Optional, Type, Union
@@ -60,9 +64,16 @@ def _get_git_head(path: Path) -> str:
         Empty string if timeout expired for subprocess command execution else
         git HEAD information.
 
+    Raises
+    ------
+    FileNotFoundError
+        If ``path`` is invalid.
+
     """
     if not path.exists():
-        raise ValueError(f"This path does not exist: {path}")
+        raise_error(
+            msg=f"This path does not exist: {path}", klass=FileNotFoundError
+        )
     command = f"cd {path}; git rev-parse --verify HEAD"
     process = Popen(
         args=command,
@@ -88,7 +99,7 @@ def get_versions() -> Dict:
 
     """
     module_versions = {}
-    for name, module in sys.modules.items():
+    for name, module in sys.modules.copy().items():
         # Bypassing sub-modules of packages and
         # allowing ruamel.yaml
         if "." in name and name != "ruamel.yaml":

junifer/utils/tests/test_helpers.py

@@ -0,0 +1,35 @@
+"""Provide tests for helper functions."""
+
+# Authors: Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+import logging
+
+import pytest
+
+from junifer.utils.helpers import run_ext_cmd
+
+
+def test_run_ext_cmd_success(caplog: pytest.LogCaptureFixture) -> None:
+    """Test external command run success.
+
+    Parameters
+    ----------
+    caplog : pytest.LogCaptureFixture
+        The pytest.LogCaptureFixture object.
+
+    """
+    # Set log capturing at INFO
+    with caplog.at_level(logging.INFO):
+        # Run external command
+        run_ext_cmd(name="pwd", cmd=["pwd"])
+        # Check logging message
+        assert "executed" in caplog.text
+        assert "succeeded" in caplog.text
+
+
+def test_run_ext_cmd_failure() -> None:
+    """Test external command run failure."""
+    with pytest.raises(RuntimeError, match="failed"):
+        # Run external command
+        run_ext_cmd(name="flymetothemoon", cmd=["flymetothemoon"])