junifer 0.0.5.dev68__py3-none-any.whl → 0.0.5.dev93__py3-none-any.whl

junifer/datagrabber/aomic/tests/test_piop2.py

@@ -57,19 +57,19 @@ def test_DataladAOMICPIOP2(tasks: Optional[str]) -> None:
         assert out["BOLD"]["path"].exists()
         assert out["BOLD"]["path"].is_file()
 
-        # asserts type "BOLD_confounds"
-        assert "BOLD_confounds" in out
+        # asserts type BOLD.confounds
+        assert "confounds" in out["BOLD"]
 
         assert (
-            out["BOLD_confounds"]["path"].name == f"{sub}_task-{new_task}_"
+            out["BOLD"]["confounds"]["path"].name == f"{sub}_task-{new_task}_"
             "desc-confounds_regressors.tsv"
         )
 
-        assert out["BOLD_confounds"]["path"].exists()
-        assert out["BOLD_confounds"]["path"].is_file()
+        assert out["BOLD"]["confounds"]["path"].exists()
+        assert out["BOLD"]["confounds"]["path"].is_file()
 
-        # assert BOLD_mask
-        assert out["BOLD_mask"]["path"].exists()
+        # assert BOLD.mask
+        assert out["BOLD"]["mask"]["path"].exists()
 
         # asserts type "T1w"
         assert "T1w" in out
@@ -82,8 +82,8 @@ def test_DataladAOMICPIOP2(tasks: Optional[str]) -> None:
         assert out["T1w"]["path"].exists()
         assert out["T1w"]["path"].is_file()
 
-        # asserts T1w_mask
-        assert out["T1w_mask"]["path"].exists()
+        # asserts T1w.mask
+        assert out["T1w"]["mask"]["path"].exists()
 
         # asserts type "VBM_CSF"
         assert "VBM_CSF" in out
@@ -141,13 +141,12 @@ def test_DataladAOMICPIOP2(tasks: Optional[str]) -> None:
     "types",
     [
         "BOLD",
-        "BOLD_confounds",
         "T1w",
         "VBM_CSF",
         "VBM_GM",
         "VBM_WM",
         "DWI",
-        ["BOLD", "BOLD_confounds"],
+        ["BOLD", "VBM_CSF"],
         ["T1w", "VBM_CSF"],
         ["VBM_GM", "VBM_WM"],
         ["DWI", "BOLD"],

junifer/datagrabber/datalad_base.py

@@ -176,7 +176,16 @@ class DataladDataGrabber(BaseDataGrabber):
             The unmodified input dictionary.
 
         """
-        to_get = [v["path"] for v in out.values() if "path" in v]
+        to_get = []
+        for type_val in out.values():
+            # Iterate to check for nested "types" like mask
+            for k, v in type_val.items():
+                # Add base data type path
+                if k == "path":
+                    to_get.append(v)
+                # Add nested data type path
+                if isinstance(v, dict) and "path" in v:
+                    to_get.append(v["path"])
 
         if len(to_get) > 0:
             logger.debug(f"Getting {len(to_get)} files using datalad:")

junifer/datagrabber/dmcc13_benchmark.py

@@ -25,17 +25,16 @@ class DMCC13Benchmark(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "BOLD_confounds", "BOLD_mask", "T1w", "T1w_mask", \
-           "VBM_CSF", "VBM_GM", "VBM_WM", "Warp" (only if \
-           "native_t1w = True")} or a list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM"} or \
+           list of the options, optional
         DMCC data types. If None, all available data types are selected.
         (default None).
-    sessions: {"ses-wave1bas", "ses-wave1pro", "ses-wave1rea"} or list of \
-            the options, optional
+    sessions: {"ses-wave1bas", "ses-wave1pro", "ses-wave1rea"} or \
+              list of the options, optional
         DMCC sessions. If None, all available sessions are selected
         (default None).
     tasks: {"Rest", "Axcpt", "Cuedts", "Stern", "Stroop"} or \
-            list of the options, optional
+           list of the options, optional
         DMCC task sessions. If None, all available task sessions are selected
         (default None).
     phase_encodings : {"AP", "PA"} or list of the options, optional
@@ -148,24 +147,23 @@ class DMCC13Benchmark(PatternDataladDataGrabber):
                     "space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz"
                 ),
                 "space": "MNI152NLin2009cAsym",
-                "mask_item": "BOLD_mask",
-            },
-            "BOLD_confounds": {
-                "pattern": (
-                    "derivatives/fmriprep-1.3.2/{subject}/{session}/"
-                    "func/{subject}_{session}_task-{task}_acq-mb4"
-                    "{phase_encoding}_run-{run}_desc-confounds_regressors.tsv"
-                ),
-                "format": "fmriprep",
-            },
-            "BOLD_mask": {
-                "pattern": (
-                    "derivatives/fmriprep-1.3.2/{subject}/{session}/"
-                    "/func/{subject}_{session}_task-{task}_acq-mb4"
-                    "{phase_encoding}_run-{run}_"
-                    "space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
-                ),
-                "space": "MNI152NLin2009cAsym",
+                "mask": {
+                    "pattern": (
+                        "derivatives/fmriprep-1.3.2/{subject}/{session}/"
+                        "/func/{subject}_{session}_task-{task}_acq-mb4"
+                        "{phase_encoding}_run-{run}_"
+                        "space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
+                    ),
+                    "space": "MNI152NLin2009cAsym",
+                },
+                "confounds": {
+                    "pattern": (
+                        "derivatives/fmriprep-1.3.2/{subject}/{session}/"
+                        "func/{subject}_{session}_task-{task}_acq-mb4"
+                        "{phase_encoding}_run-{run}_desc-confounds_regressors.tsv"
+                    ),
+                    "format": "fmriprep",
+                },
             },
             "T1w": {
                 "pattern": (
@@ -173,14 +171,13 @@ class DMCC13Benchmark(PatternDataladDataGrabber):
                     "{subject}_space-MNI152NLin2009cAsym_desc-preproc_T1w.nii.gz"
                 ),
                 "space": "MNI152NLin2009cAsym",
-                "mask_item": "T1w_mask",
-            },
-            "T1w_mask": {
-                "pattern": (
-                    "derivatives/fmriprep-1.3.2/{subject}/anat/"
-                    "{subject}_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
-                ),
-                "space": "MNI152NLin2009cAsym",
+                "mask": {
+                    "pattern": (
+                        "derivatives/fmriprep-1.3.2/{subject}/anat/"
+                        "{subject}_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
+                    ),
+                    "space": "MNI152NLin2009cAsym",
+                },
             },
             "VBM_CSF": {
                 "pattern": (
@@ -216,14 +213,13 @@ class DMCC13Benchmark(PatternDataladDataGrabber):
                             "{subject}_desc-preproc_T1w.nii.gz"
                         ),
                         "space": "native",
-                        "mask_item": "T1w_mask",
-                    },
-                    "T1w_mask": {
-                        "pattern": (
-                            "derivatives/fmriprep-1.3.2/{subject}/anat/"
-                            "{subject}_desc-brain_mask.nii.gz"
-                        ),
-                        "space": "native",
+                        "mask": {
+                            "pattern": (
+                                "derivatives/fmriprep-1.3.2/{subject}/anat/"
+                                "{subject}_desc-brain_mask.nii.gz"
+                            ),
+                            "space": "native",
+                        },
                     },
                     "Warp": {
                         "pattern": (
@@ -298,20 +294,6 @@ class DMCC13Benchmark(PatternDataladDataGrabber):
             phase_encoding=phase_encoding,
             run=run,
         )
-        if out.get("BOLD"):
-            out["BOLD"]["mask_item"] = "BOLD_mask"
-            # Add space information
-            out["BOLD"].update({"space": "MNI152NLin2009cAsym"})
-        if out.get("T1w"):
-            out["T1w"]["mask_item"] = "T1w_mask"
-            # Add space information
-            if self.native_t1w:
-                out["T1w"].update({"space": "native"})
-            else:
-                out["T1w"].update({"space": "MNI152NLin2009cAsym"})
-        if out.get("Warp"):
-            # Add source space information
-            out["Warp"].update({"src": "MNI152NLin2009cAsym"})
         return out
 
     def get_elements(self) -> List:

junifer/datagrabber/pattern.py

@@ -40,7 +40,12 @@ class PatternDataGrabber(BaseDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": []
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"T2w"`` :
@@ -49,7 +54,12 @@ class PatternDataGrabber(BaseDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": []
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"BOLD"`` :
@@ -58,7 +68,16 @@ class PatternDataGrabber(BaseDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": ["mask_item"]
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+                  "confounds": {
+                      "mandatory": ["pattern", "format"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"Warp"`` :
@@ -70,15 +89,6 @@ class PatternDataGrabber(BaseDataGrabber):
               "optional": []
             }
 
-        * ``"BOLD_confounds"`` :
-
-          .. code-block:: none
-
-            {
-              "mandatory": ["pattern", "format"],
-              "optional": []
-            }
-
         * ``"VBM_GM"`` :
 
           .. code-block:: none
@@ -246,6 +256,64 @@ class PatternDataGrabber(BaseDataGrabber):
             )
         return pattern.format(**element)
 
+    def _get_path_from_patterns(
+        self, element: Dict, pattern: str, data_type: str
+    ) -> Path:
+        """Get path from resolved patterns.
+
+        Parameters
+        ----------
+        element : dict
+            The element to be used in the replacement.
+        pattern : str
+            The pattern to be replaced.
+        data_type : str
+            The data type of the pattern.
+
+        Returns
+        -------
+        pathlib.Path
+            The path for the resolved pattern.
+
+        Raises
+        ------
+        RuntimeError
+            If more than one file matches for a data type's pattern or
+            if no file matches for a data type's pattern or
+            if file cannot be accessed for an element.
+
+        """
+        # Replace element in the pattern for globbing
+        resolved_pattern = self._replace_patterns_glob(element, pattern)
+        # Resolve path for wildcard
+        if "*" in resolved_pattern:
+            t_matches = list(self.datadir.absolute().glob(resolved_pattern))
+            # Multiple matches
+            if len(t_matches) > 1:
+                raise_error(
+                    f"More than one file matches for {element} / {data_type}:"
+                    f" {t_matches}",
+                    klass=RuntimeError,
+                )
+            # No matches
+            elif len(t_matches) == 0:
+                raise_error(
+                    f"No file matches for {element} / {data_type}",
+                    klass=RuntimeError,
+                )
+            path = t_matches[0]
+        else:
+            path = self.datadir / resolved_pattern
+            if not self.skip_file_check:
+                if not path.exists() and not path.is_symlink():
+                    raise_error(
+                        f"Cannot access {data_type} for {element}: "
+                        f"File {path} does not exist",
+                        klass=RuntimeError,
+                    )
+
+        return path
+
     def get_element_keys(self) -> List[str]:
         """Get element keys.
 
@@ -279,47 +347,49 @@ class PatternDataGrabber(BaseDataGrabber):
             Dictionary of dictionaries for each type of data required for the
             specified element.
 
-        Raises
-        ------
-        RuntimeError
-            If more than one file matches for a data type's pattern or
-            if no file matches for a data type's pattern or
-            if file cannot be accessed for an element.
-
         """
         out = {}
         for t_type in self.types:
+            # Data type dictionary
             t_pattern = self.patterns[t_type]
-            t_replace = self._replace_patterns_glob(
-                element, t_pattern["pattern"]
-            )
-            if "*" in t_replace:
-                t_matches = list(self.datadir.absolute().glob(t_replace))
-                if len(t_matches) > 1:
-                    raise_error(
-                        f"More than one file matches for {element} / {t_type}:"
-                        f" {t_matches}",
-                        klass=RuntimeError,
+            # Copy data type dictionary in output
+            out[t_type] = t_pattern.copy()
+            # Iterate to check for nested "types" like mask
+            for k, v in t_pattern.items():
+                # Resolve pattern for base data type
+                if k == "pattern":
+                    logger.info(f"Resolving path from pattern for {t_type}")
+                    # Resolve pattern
+                    base_data_type_pattern_path = self._get_path_from_patterns(
+                        element=element,
+                        pattern=v,
+                        data_type=t_type,
                     )
-                elif len(t_matches) == 0:
-                    raise_error(
-                        f"No file matches for {element} / {t_type}",
-                        klass=RuntimeError,
+                    # Remove pattern key
+                    out[t_type].pop("pattern")
+                    # Add path key
+                    out[t_type].update({"path": base_data_type_pattern_path})
+                # Resolve pattern for nested data type
+                if isinstance(v, dict) and "pattern" in v:
+                    # Set nested type key for easier access
+                    t_nested_type = f"{t_type}.{k}"
+                    logger.info(
+                        f"Resolving path from pattern for {t_nested_type}"
                     )
-                t_out = t_matches[0]
-            else:
-                t_out = self.datadir / t_replace
-                if not self.skip_file_check:
-                    if not t_out.exists() and not t_out.is_symlink():
-                        raise_error(
-                            f"Cannot access {t_type} for {element}: "
-                            f"File {t_out} does not exist",
-                            klass=RuntimeError,
+                    # Resolve pattern
+                    nested_data_type_pattern_path = (
+                        self._get_path_from_patterns(
+                            element=element,
+                            pattern=v["pattern"],
+                            data_type=t_nested_type,
                         )
-            # Update path for the element
-            out[t_type] = t_pattern.copy()  # copy data type dictionary
-            out[t_type].pop("pattern")  # remove pattern key
-            out[t_type].update({"path": t_out})  # add path key
+                    )
+                    # Remove pattern key
+                    out[t_type][k].pop("pattern")
+                    # Add path key
+                    out[t_type][k].update(
+                        {"path": nested_data_type_pattern_path}
+                    )
 
         return out
 

junifer/datagrabber/pattern_datalad.py

@@ -32,7 +32,12 @@ class PatternDataladDataGrabber(DataladDataGrabber, PatternDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": []
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"T2w"`` :
@@ -41,7 +46,12 @@ class PatternDataladDataGrabber(DataladDataGrabber, PatternDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": []
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"BOLD"`` :
@@ -50,7 +60,16 @@ class PatternDataladDataGrabber(DataladDataGrabber, PatternDataGrabber):
 
             {
               "mandatory": ["pattern", "space"],
-              "optional": ["mask_item"]
+              "optional": {
+                  "mask": {
+                      "mandatory": ["pattern", "space"],
+                      "optional": []
+                  }
+                  "confounds": {
+                      "mandatory": ["pattern", "format"],
+                      "optional": []
+                  }
+              }
             }
 
         * ``"Warp"`` :
@@ -62,15 +81,6 @@ class PatternDataladDataGrabber(DataladDataGrabber, PatternDataGrabber):
               "optional": []
             }
 
-        * ``"BOLD_confounds"`` :
-
-          .. code-block:: none
-
-            {
-              "mandatory": ["pattern", "format"],
-              "optional": []
-            }
-
         * ``"VBM_GM"`` :
 
           .. code-block:: none

junifer/datagrabber/tests/test_datagrabber_utils.py

@@ -151,12 +151,18 @@ def test_validate_replacements(
             pytest.raises(KeyError, match="Mandatory key"),
         ),
         (
-            ["BOLD_confounds"],
+            ["BOLD"],
             {
-                "BOLD_confounds": {
-                    "pattern": "{subject}/func/{subject}_confounds.tsv",
-                    "format": "fmriprep",
+                "BOLD": {
+                    "pattern": (
+                        "{subject}/func/{subject}_task-rest_bold.nii.gz"
+                    ),
                     "space": "MNINLin6Asym",
+                    "confounds": {
+                        "pattern": "{subject}/func/{subject}_confounds.tsv",
+                        "format": "fmriprep",
+                    },
+                    "zip": "zap",
                 },
             },
             pytest.raises(RuntimeError, match="not accepted"),
@@ -172,7 +178,7 @@ def test_validate_replacements(
             pytest.raises(ValueError, match="following a replacement"),
         ),
         (
-            ["T1w", "T2w", "BOLD", "BOLD_confounds"],
+            ["T1w", "T2w", "BOLD"],
             {
                 "T1w": {
                     "pattern": "{subject}/anat/{subject}_T1w.nii.gz",
@@ -187,10 +193,10 @@ def test_validate_replacements(
                         "{subject}/func/{subject}_task-rest_bold.nii.gz"
                     ),
                     "space": "MNI152NLin6Asym",
-                },
-                "BOLD_confounds": {
-                    "pattern": "{subject}/func/{subject}_confounds.tsv",
-                    "format": "fmriprep",
+                    "confounds": {
+                        "pattern": "{subject}/func/{subject}_confounds.tsv",
+                        "format": "fmriprep",
+                    },
                 },
             },
             nullcontext(),

junifer/datagrabber/tests/test_dmcc13_benchmark.py

@@ -93,13 +93,10 @@ def test_DMCC13Benchmark(
         # Available data types
         data_types = [
             "BOLD",
-            "BOLD_confounds",
-            "BOLD_mask",
             "VBM_CSF",
             "VBM_GM",
             "VBM_WM",
             "T1w",
-            "T1w_mask",
         ]
         # Add Warp if native T1w is accessed
         if native_t1w:
@@ -111,14 +108,6 @@ def test_DMCC13Benchmark(
                 f"sub-01_{ses}_task-{task}_acq-mb4{phase}_run-{run}_"
                 "space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz"
             ),
-            (
-                f"sub-01_{ses}_task-{task}_acq-mb4{phase}_run-{run}_"
-                "desc-confounds_regressors.tsv"
-            ),
-            (
-                f"sub-01_{ses}_task-{task}_acq-mb4{phase}_run-{run}_"
-                "space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
-            ),
             "sub-01_space-MNI152NLin2009cAsym_label-CSF_probseg.nii.gz",
             "sub-01_space-MNI152NLin2009cAsym_label-GM_probseg.nii.gz",
             "sub-01_space-MNI152NLin2009cAsym_label-WM_probseg.nii.gz",
@@ -127,16 +116,12 @@ def test_DMCC13Benchmark(
             data_file_names.extend(
                 [
                     "sub-01_desc-preproc_T1w.nii.gz",
-                    "sub-01_desc-brain_mask.nii.gz",
                     "sub-01_from-MNI152NLin2009cAsym_to-T1w_mode-image_xfm.h5",
                 ]
             )
         else:
-            data_file_names.extend(
-                [
-                    "sub-01_space-MNI152NLin2009cAsym_desc-preproc_T1w.nii.gz",
-                    "sub-01_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz",
-                ]
+            data_file_names.append(
+                "sub-01_space-MNI152NLin2009cAsym_desc-preproc_T1w.nii.gz"
             )
 
         for data_type, data_file_name in zip(data_types, data_file_names):
@@ -151,6 +136,48 @@ def test_DMCC13Benchmark(
             # Assert metadata
             assert "meta" in out[data_type]
 
+        # Check BOLD nested data types
+        for type_, file_name in zip(
+            ("mask", "confounds"),
+            (
+                (
+                    f"sub-01_{ses}_task-{task}_acq-mb4{phase}_run-{run}_"
+                    "space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
+                ),
+                (
+                    f"sub-01_{ses}_task-{task}_acq-mb4{phase}_run-{run}_"
+                    "desc-confounds_regressors.tsv"
+                ),
+            ),
+        ):
+            # Assert data type
+            assert type_ in out["BOLD"]
+            # Assert data file path exists
+            assert out["BOLD"][type_]["path"].exists()
+            # Assert data file path is a file
+            assert out["BOLD"][type_]["path"].is_file()
+            # Assert data file name
+            assert out["BOLD"][type_]["path"].name == file_name
+
+        # Check T1w nested data types
+        # Assert data type
+        assert "mask" in out["T1w"]
+        # Assert data file path exists
+        assert out["T1w"]["mask"]["path"].exists()
+        # Assert data file path is a file
+        assert out["T1w"]["mask"]["path"].is_file()
+        # Assert data file name
+        if native_t1w:
+            assert (
+                out["T1w"]["mask"]["path"].name
+                == "sub-01_desc-brain_mask.nii.gz"
+            )
+        else:
+            assert (
+                out["T1w"]["mask"]["path"].name
+                == "sub-01_space-MNI152NLin2009cAsym_desc-brain_mask.nii.gz"
+            )
+
 
 @pytest.mark.parametrize(
     "types, native_t1w",
@@ -165,8 +192,8 @@ def test_DMCC13Benchmark(
         ("VBM_GM", False),
         ("VBM_WM", True),
         ("VBM_WM", False),
-        (["BOLD", "BOLD_confounds"], True),
-        (["BOLD", "BOLD_confounds"], False),
+        (["BOLD", "VBM_CSF"], True),
+        (["BOLD", "VBM_CSF"], False),
         (["T1w", "VBM_CSF"], True),
         (["T1w", "VBM_CSF"], False),
         (["VBM_GM", "VBM_WM"], True),