junifer 0.0.7.dev332__py3-none-any.whl → 0.0.8__py3-none-any.whl

junifer/datagrabber/tests/test_pattern_datalad.py

@@ -7,64 +7,50 @@
 
 from pathlib import Path
 
+import datalad.api as dl
 import pytest
+from pydantic import AnyUrl
 
-from junifer.datagrabber import PatternDataladDataGrabber
+from junifer.datagrabber import DataType, PatternDataladDataGrabber
 
 
 _testing_dataset = {
     "example_bids": {
-        "uri": "https://gin.g-node.org/juaml/datalad-example-bids",
+        "uri": (
+            "https://cerebra.fz-juelich.de/junifer/datalad-example-bids.git"
+        ),
         "commit": "3f288c8725207ae0c9b3616e093e78cda192b570",
         "id": "8fddff30-6993-420a-9d1e-b5b028c59468",
     },
     "example_bids_ses": {
-        "uri": "https://gin.g-node.org/juaml/datalad-example-bids-ses",
+        "uri": (
+            "https://cerebra.fz-juelich.de/junifer/datalad-example-bids-ses.git"
+        ),
         "commit": "6b163aa98af76a9eac0272273c27e14127850181",
         "id": "715c17cf-a1b9-42d6-9af8-9f74c1a4a724",
     },
 }
 
 
-def test_bids_PatternDataladDataGrabber_missing_uri() -> None:
-    """Test check of missing URI in PatternDataladDataGrabber."""
-    with pytest.raises(ValueError, match=r"`uri` must be provided"):
-        PatternDataladDataGrabber(
-            datadir=None,
-            types=[],
-            patterns={},
-            replacements=[],
-        )
-
-
 def test_bids_PatternDataladDataGrabber() -> None:
     """Test subject-based BIDS PatternDataladDataGrabber."""
-    # Define types
-    types = ["T1w", "BOLD"]
-    # Define patterns
-    patterns = {
-        "T1w": {
-            "pattern": "{subject}/anat/{subject}_T1w.nii.gz",
-            "space": "MNI152NLin6Asym",
-        },
-        "BOLD": {
-            "pattern": "{subject}/func/{subject}_task-rest_bold.nii.gz",
-            "space": "MNI152NLin6Asym",
-        },
-    }
-    # Define replacements
-    replacements = ["subject"]
-
-    repo_uri = _testing_dataset["example_bids"]["uri"]
-    rootdir = "example_bids"
     repo_commit = _testing_dataset["example_bids"]["commit"]
-
+    repo_uri = _testing_dataset["example_bids"]["uri"]
     with PatternDataladDataGrabber(
-        rootdir=rootdir,
-        uri=repo_uri,
-        types=types,
-        patterns=patterns,
-        replacements=replacements,
+        uri=AnyUrl(repo_uri),
+        types=[DataType.T1w, DataType.BOLD],
+        patterns={
+            "T1w": {
+                "pattern": "{subject}/anat/{subject}_T1w.nii.gz",
+                "space": "MNI152NLin6Asym",
+            },
+            "BOLD": {
+                "pattern": "{subject}/func/{subject}_task-rest_bold.nii.gz",
+                "space": "MNI152NLin6Asym",
+            },
+        },
+        replacements=["subject"],
+        rootdir=Path("example_bids"),
     ) as dg:
         subs = list(dg)
         expected_subs = [f"sub-{i:02d}" for i in range(1, 10)]
@@ -74,11 +60,11 @@ def test_bids_PatternDataladDataGrabber() -> None:
             t_sub = dg[elem]
             assert "path" in t_sub["T1w"]
             assert t_sub["T1w"]["path"] == (
-                dg.datadir / f"{elem}/anat/{elem}_T1w.nii.gz"
+                dg.fulldir / f"{elem}/anat/{elem}_T1w.nii.gz"
             )
             assert "path" in t_sub["BOLD"]
             assert t_sub["BOLD"]["path"] == (
-                dg.datadir / f"{elem}/func/{elem}_task-rest_bold.nii.gz"
+                dg.fulldir / f"{elem}/func/{elem}_task-rest_bold.nii.gz"
             )
 
             assert "meta" in t_sub["BOLD"]
@@ -88,7 +74,7 @@ def test_bids_PatternDataladDataGrabber() -> None:
             assert "class" in dg_meta
             assert dg_meta["class"] == "PatternDataladDataGrabber"
             assert "uri" in dg_meta
-            assert dg_meta["uri"] == repo_uri
+            assert str(dg_meta["uri"]) == repo_uri
             assert "datalad_commit_id" in dg_meta
             assert dg_meta["datalad_commit_id"] == repo_commit
 
@@ -98,80 +84,67 @@ def test_bids_PatternDataladDataGrabber() -> None:
 
 def test_bids_PatternDataladDataGrabber_datadir() -> None:
     """Test PatternDataladDataGrabber with a datadir set to a relative path."""
-    # Define patterns
-    patterns = {
-        "T1w": {
-            "pattern": "{subject}/anat/{subject}_T*w.nii.gz",
-            "space": "MNI152NLin6Asym",
-        },
-        "BOLD": {
-            "pattern": "{subject}/func/{subject}_task-rest_*.nii.gz",
-            "space": "MNI152NLin6Asym",
-        },
-    }
-    # Define datadir
-    datadir = "dataset"  # use string and not absolute path
+    datadir = Path("dataset")  # use string and not absolute path
     with PatternDataladDataGrabber(
-        uri=_testing_dataset["example_bids"]["uri"],
-        types=["T1w", "BOLD"],
-        patterns=patterns,
-        datadir=datadir,
-        rootdir="example_bids",
+        uri=AnyUrl(_testing_dataset["example_bids"]["uri"]),
+        types=[DataType.T1w, DataType.BOLD],
+        patterns={
+            "T1w": {
+                "pattern": "{subject}/anat/{subject}_T*w.nii.gz",
+                "space": "MNI152NLin6Asym",
+            },
+            "BOLD": {
+                "pattern": "{subject}/func/{subject}_task-rest_*bold.nii.gz",
+                "space": "MNI152NLin6Asym",
+            },
+        },
         replacements=["subject"],
+        datadir=datadir,
+        rootdir=Path("example_bids"),
     ) as dg:
-        assert dg.datadir == Path(datadir) / "example_bids"
+        assert dg.fulldir == Path(datadir) / "example_bids"
+        assert len(dg.get_elements()) > 0
         for elem in dg:
             t_sub = dg[elem]
+            # The paths are absolute
             assert "path" in t_sub["T1w"]
             assert t_sub["T1w"]["path"] == (
-                dg.datadir / f"{elem}/anat/{elem}_T1w.nii.gz"
+                dg.fulldir.absolute() / f"{elem}/anat/{elem}_T1w.nii.gz"
             )
             assert "path" in t_sub["BOLD"]
             assert t_sub["BOLD"]["path"] == (
-                dg.datadir / f"{elem}/func/{elem}_task-rest_bold.nii.gz"
+                dg.fulldir.absolute()
+                / f"{elem}/func/{elem}_task-rest_bold.nii.gz"
             )
 
 
 def test_bids_PatternDataladDataGrabber_session():
     """Test a subject and session-based BIDS PatternDataladDataGrabber."""
-    types = ["T1w", "BOLD"]
-    patterns = {
-        "T1w": {
-            "pattern": (
-                "{subject}/{session}/anat/{subject}_{session}_T1w.nii.gz"
-            ),
-            "space": "MNI152NLin6Asym",
-        },
-        "BOLD": {
-            "pattern": (
-                "{subject}/{session}/func/"
-                "{subject}_{session}_task-rest_bold.nii.gz"
-            ),
-            "space": "MNI152NLin6Asym",
-        },
-    }
-    replacements = ["subject", "session"]
-
-    # Check error
-    with pytest.raises(ValueError, match=r"`uri` must be provided"):
-        PatternDataladDataGrabber(
-            datadir=None,
-            types=types,
-            patterns=patterns,
-            replacements=replacements,
-        )
-
     # Set parameters
-    repo_uri = _testing_dataset["example_bids_ses"]["uri"]
-    rootdir = "example_bids_ses"
-
+    repo_uri = AnyUrl(_testing_dataset["example_bids_ses"]["uri"])
+    rootdir = Path("example_bids_ses")
+    replacements = ["subject", "session"]
     # With T1W and bold, only 2 sessions are available
     with PatternDataladDataGrabber(
-        rootdir=rootdir,
         uri=repo_uri,
-        types=types,
-        patterns=patterns,
+        types=[DataType.T1w, DataType.BOLD],
+        patterns={
+            "T1w": {
+                "pattern": (
+                    "{subject}/{session}/anat/{subject}_{session}_T1w.nii.gz"
+                ),
+                "space": "MNI152NLin6Asym",
+            },
+            "BOLD": {
+                "pattern": (
+                    "{subject}/{session}/func/"
+                    "{subject}_{session}_task-rest_bold.nii.gz"
+                ),
+                "space": "MNI152NLin6Asym",
+            },
+        },
         replacements=replacements,
+        rootdir=rootdir,
     ) as dg:
         subs = list(dg.get_elements())
         expected_subs = [
@@ -182,21 +155,19 @@ def test_bids_PatternDataladDataGrabber_session():
         assert set(subs) == set(expected_subs)
 
     # Test with a different T1w only, it should have 3 sessions
-    types = ["T1w"]
-    patterns = {
-        "T1w": {
-            "pattern": (
-                "{subject}/{session}/anat/{subject}_{session}_T1w.nii.gz"
-            ),
-            "space": "MNI152NLin6Asym",
-        },
-    }
     with PatternDataladDataGrabber(
-        rootdir=rootdir,
         uri=repo_uri,
-        types=types,
-        patterns=patterns,
+        types=DataType.T1w,
+        patterns={
+            "T1w": {
+                "pattern": (
+                    "{subject}/{session}/anat/{subject}_{session}_T1w.nii.gz"
+                ),
+                "space": "MNI152NLin6Asym",
+            },
+        },
         replacements=replacements,
+        rootdir=rootdir,
     ) as dg:
         subs = list(dg)
         expected_subs = [
@@ -205,3 +176,102 @@ def test_bids_PatternDataladDataGrabber_session():
             for i in range(1, 10)
         ]
         assert set(subs) == set(expected_subs)
+
+
+@pytest.fixture
+def subdatasets_uri(tmp_path: Path) -> AnyUrl:
+    """Return the URI of a dataset with a sub-dataset for each subject.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+
+    """
+    dataset = dl.create(tmp_path / "origin", result_renderer="disabled")
+    for subject in ("sub-01", "sub-02"):
+        subdataset = dataset.create(subject, result_renderer="disabled")
+        (subdataset.pathobj / "T1w.nii").write_text(subject)
+        (dataset.pathobj / f"{subject}_T1w.nii").write_text(subject)
+    dataset.save(recursive=True, result_renderer="disabled")
+    return AnyUrl(f"file://{dataset.path}")
+
+
+@pytest.mark.parametrize(
+    "pattern",
+    ["{subject}/T1w.nii", "{subject}/T1*.nii"],
+)
+def test_PatternDataladDataGrabber_subdatasets_search(
+    tmp_path: Path, subdatasets_uri: AnyUrl, pattern: str
+) -> None:
+    """Test searching the files of the sub-datasets raises an error.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+    subdatasets_uri : pydantic.AnyUrl
+        The URI of the dataset with a sub-dataset for each subject.
+    pattern : str
+        The parametrized pattern, which searches the files of the
+        sub-datasets.
+
+    """
+    dg = PatternDataladDataGrabber(
+        uri=subdatasets_uri,
+        datadir=tmp_path / "clone",
+        types=["T1w"],
+        patterns={"T1w": {"pattern": pattern, "space": "native"}},
+        replacements=["subject"],
+    )
+    with pytest.raises(RuntimeError, match="searches the files of the"):
+        with dg:
+            pass
+    # The cloned dataset is removed
+    assert not (tmp_path / "clone").exists() or not any(
+        (tmp_path / "clone").iterdir()
+    )
+
+
+def test_PatternDataladDataGrabber_subdatasets_files(
+    tmp_path: Path, subdatasets_uri: AnyUrl
+) -> None:
+    """Test the patterns of a dataset with sub-datasets.
+
+    The files of the dataset can be searched, and the patterns without
+    wildcards can have files in the sub-datasets.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+    subdatasets_uri : pydantic.AnyUrl
+        The URI of the dataset with a sub-dataset for each subject.
+
+    """
+    dg = PatternDataladDataGrabber(
+        uri=subdatasets_uri,
+        datadir=tmp_path / "clone",
+        types=["T1w"],
+        patterns={"T1w": {"pattern": "{subject}_T1w.nii", "space": "native"}},
+        replacements=["subject"],
+    )
+    with dg:
+        assert dg.get_elements() == ["sub-01", "sub-02"]
+        assert dg["sub-02"]["T1w"]["path"].read_text() == "sub-02"
+    # A pattern without wildcards in a sub-dataset
+    dg = PatternDataladDataGrabber(
+        uri=subdatasets_uri,
+        datadir=tmp_path / "clone",
+        types=["T1w"],
+        patterns={
+            "T1w": {
+                "pattern": "{subject}_T1w.nii",
+                "space": "native",
+                "mask": {"pattern": "sub-01/T1w.nii", "space": "native"},
+            }
+        },
+        replacements=["subject"],
+    )
+    with dg:
+        assert dg.get_elements() == ["sub-01", "sub-02"]

junifer/datagrabber/tests/test_pattern_validation_mixin.py

@@ -5,11 +5,11 @@
 # License: AGPL
 
 from contextlib import AbstractContextManager, nullcontext
-from typing import Union
 
 import pytest
 
-from junifer.datagrabber.pattern_validation_mixin import (
+from junifer.datagrabber import (
+    DataType,
     DataTypeManager,
     DataTypeSchema,
     PatternValidationMixin,
@@ -80,7 +80,7 @@ def test_dtype_mgr(dtype: DataTypeSchema) -> None:
 
     Parameters
     ----------
-    dtype : DataTypeSchema
+    dtype : ``DataTypeSchema``
         The parametrized schema.
 
     """
@@ -111,33 +111,15 @@ def test_register_data_type() -> None:
     )
 
     assert "dtype" in DataTypeManager()
+    assert "dtype" in list(DataType)
     _ = DataTypeManager().pop("dtype")
-    assert "dumb" not in DataTypeManager()
+    assert "dtype" not in DataTypeManager()
+    assert "dtype" in list(DataType)
 
 
 @pytest.mark.parametrize(
     "types, replacements, patterns, expect",
     [
-        (
-            "wrong",
-            [],
-            {},
-            pytest.raises(TypeError, match="`types` must be a list"),
-        ),
-        (
-            [1],
-            [],
-            {},
-            pytest.raises(
-                TypeError, match="`types` must be a list of strings"
-            ),
-        ),
-        (
-            ["BOLD"],
-            [],
-            "wrong",
-            pytest.raises(TypeError, match="`patterns` must be a dict"),
-        ),
         (
             ["T1w", "BOLD"],
             "",
@@ -205,30 +187,6 @@ def test_register_data_type() -> None:
             },
             pytest.raises(ValueError, match="following a replacement"),
         ),
-        (
-            ["T1w"],
-            "wrong",
-            {
-                "T1w": {
-                    "pattern": "{subject}/anat/{subject}_T1w.nii",
-                    "space": "native",
-                },
-            },
-            pytest.raises(TypeError, match="`replacements` must be a list"),
-        ),
-        (
-            ["T1w"],
-            [1],
-            {
-                "T1w": {
-                    "pattern": "{subject}/anat/{subject}_T1w.nii",
-                    "space": "native",
-                },
-            },
-            pytest.raises(
-                TypeError, match="`replacements` must be a list of strings"
-            ),
-        ),
         (
             ["T1w", "BOLD"],
             ["subject", "session"],
@@ -289,9 +247,9 @@ def test_register_data_type() -> None:
     ],
 )
 def test_PatternValidationMixin(
-    types: Union[str, list[str], list[int]],
-    replacements: Union[str, list[str], list[int]],
-    patterns: Union[str, dict[str, dict[str, str]]],
+    types: str | list[str] | list[int],
+    replacements: str | list[str] | list[int],
+    patterns: str | dict[str, dict[str, str]],
     expect: AbstractContextManager,
 ) -> None:
     """Test validation.

junifer/datareader/default.py

@@ -5,18 +5,21 @@
 # License: AGPL
 
 from pathlib import Path
-from typing import Optional, Union
 
 import nibabel as nib
 import pandas as pd
+import structlog
+from pydantic import BaseModel
 
 from ..api.decorators import register_datareader
 from ..pipeline import PipelineStepMixin, UpdateMetaMixin
-from ..utils.logging import logger, warn_with_log
+from ..utils.logging import warn_with_log
 
 
 __all__ = ["DefaultDataReader"]
 
+_log = structlog.get_logger("junifer")
+logger = _log.bind(pkg="datareader", step="datareader")
 
 # Map each file extension to a type
 _extensions = {
@@ -34,7 +37,7 @@ _readers["TSV"] = {"func": pd.read_csv, "params": {"sep": "\t"}}
 
 
 @register_datareader
-class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
+class DefaultDataReader(BaseModel, PipelineStepMixin, UpdateMetaMixin):
     """Concrete implementation for common data reading."""
 
     def validate_input(self, input: list[str]) -> list[str]:
@@ -59,7 +62,7 @@ class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
     def _fit_transform(
         self,
         input: dict[str, dict],
-        params: Optional[dict] = None,
+        params: dict | None = None,
     ) -> dict:
         """Fit and transform.
 
@@ -149,7 +152,7 @@ class DefaultDataReader(PipelineStepMixin, UpdateMetaMixin):
 
 def _read_data(
     data_type: str, path: Path, read_params: dict
-) -> Union[nib.Nifti1Image, pd.DataFrame, None]:
+) -> nib.Nifti1Image | pd.DataFrame | None:
     """Read data for data type.
 
     Parameters

junifer/datareader/tests/test_default_reader.py

@@ -30,7 +30,7 @@ def test_DefaultDataReader_validation(type_) -> None:
     """
     reader = DefaultDataReader()
     assert reader.validate_input(type_) == type_
-    assert reader.validate(type_) == type_
+    assert reader.validate_component(type_) == type_
 
 
 def test_DefaultDataReader_meta() -> None:

junifer/external/BrainPrint/.codecov.yml

@@ -0,0 +1,2 @@
+github_checks:
+  annotations: false

junifer/external/BrainPrint/.codespellignore

@@ -0,0 +1,2 @@
+coo
+daty

junifer/external/BrainPrint/.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,45 @@
+---
+name: Bug Report
+about: Create a bug report to help us improve BrainPrint
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+## Description
+<!-- A clear and concise description of the observed bug and/or error -->
+....
+
+## Steps to Reproduce
+<!-- 
+Steps to reproduce the observed behaviour, in as much detail as possible:
+1. Go to '...'
+2. Checkout version '...'
+3. Run '....'
+4. See error
+-->
+
+<!-- If possible, provide error messages, stack traces, and any snippets useful in describing the bug here -->
+...
+
+## Expected Behavior
+<!-- A clear and concise description of what you expected to happen. -->
+...
+
+## Screenshots
+<!-- If applicable and desired, add screenshots to help illustrate your problem. -->
+...
+
+## Environment
+ - BrainPrint Version: ...
+ - OS: ...
+ - CPU: ...
+
+<!-- Add any other relevant information on the environment here -->
+
+<!-- If possible, include a snapshot of the python software package versions you have (for e.g., using pip freeze or conda list) here -->
+
+## Additional Context
+<!-- Add any other context and comments about the problem here. -->
+...

junifer/external/BrainPrint/.github/ISSUE_TEMPLATE/documentation.md

@@ -0,0 +1,12 @@
+---
+name: Documentation
+about: Report an issue or make a suggestion related to BrainPrint documentation
+title: ''
+labels: documentation
+assignees: ''
+
+---
+
+## Documentation
+<!-- A clear and concise description of an issue you observed in the documentation, or a suggestion you wish to make. -->
+...

junifer/external/BrainPrint/.github/ISSUE_TEMPLATE/feature-request.md

@@ -0,0 +1,24 @@
+---
+name: Feature Request
+about: Submit a proposal/request for a new BrainPrint feature
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+## Feature Description
+<!-- A clear and concise description of the feature you would like to propose -->
+...
+
+## Motivation
+<!-- A clear and concise description of the problem that the proposed feature would address. For e.g., I'm always frustrated when [...]. If this is related to a specific issue, refer to it here -->
+...
+
+## Alternatives
+<!-- A clear and concise description of any alternative solutions or features you've considered, if any. -->
+...
+
+## Additional Context
+<!-- Add any other context or screenshots about the feature request here. -->
+...

junifer/external/BrainPrint/.github/ISSUE_TEMPLATE/questions-help-support.md

@@ -0,0 +1,28 @@
+---
+name: Questions/Help/Support
+about: Submit a request for support or a question
+title: ''
+labels: question
+assignees: ''
+
+---
+
+## Question/Support Request
+<!-- A clear and concise description of a question you may have or a problem for which you would like to request support  -->
+...
+
+## Screenshots
+<!-- If possible, add screenshots to help illustrate your problem. -->
+...
+
+<!-- If applicable, provide error messages, stack traces, and any snippets useful in describing your problem here -->
+
+## Environment
+ - BrainPrint Version: ...
+ - OS: ...
+ - CPU: ...
+
+<!-- Add any other relevant information on the environment here -->
+
+<!-- If possible, include a snapshot of the python software package versions you have (for e.g., using pip freeze or conda list) here -->
+

junifer/external/BrainPrint/.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"