9.2.7. Testing

Testing DataGrabbers.

pydantic model junifer.testing.datagrabbers.ADHDTestingDataGrabber

DataGrabber for ADHD dataset.

Wrapper for nilearn.datasets.fetch_adhd(). The BOLD images are truncated to the first n_timepoints, resampled to the requested resolution on the MNI152NLin6Asym (FSL) grid and cached (uncompressed) next to the original files in the nilearn data directory.

Parameters:
resolutionfloat, optional

The resolution (in mm) of the BOLD images. The original data is in 3mm, so other resolutions are resampled (default 3.0).

n_timepointsint or None, optional

The number of timepoints to keep. If None, all the 176 timepoints are kept (default 50).

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Show JSON schema
{
   "title": "ADHDTestingDataGrabber",
   "description": "DataGrabber for ADHD dataset.\n\nWrapper for :func:`nilearn.datasets.fetch_adhd`. The BOLD images are\ntruncated to the first ``n_timepoints``, resampled to the requested\nresolution on the MNI152NLin6Asym (FSL) grid and cached (uncompressed)\nnext to the original files in the nilearn data directory.\n\nParameters\n----------\nresolution : float, optional\n    The resolution (in mm) of the BOLD images. The original data is in\n    3mm, so other resolutions are resampled (default 3.0).\nn_timepoints : int or None, optional\n    The number of timepoints to keep. If None, all the 176 timepoints\n    are kept (default 50).",
   "type": "object",
   "properties": {
      "types": {
         "default": [
            "BOLD"
         ],
         "items": {
            "$ref": "#/$defs/DataType"
         },
         "title": "Types",
         "type": "array"
      },
      "datadir": {
         "default": "/tmp/tmp5u84on0q",
         "format": "path",
         "title": "Datadir",
         "type": "string"
      },
      "resolution": {
         "default": 3.0,
         "title": "Resolution",
         "type": "number"
      },
      "n_timepoints": {
         "anyOf": [
            {
               "type": "integer"
            },
            {
               "type": "null"
            }
         ],
         "default": 50,
         "title": "N Timepoints"
      }
   },
   "$defs": {
      "DataType": {
         "description": "Accepted data type.",
         "enum": [
            "T1w",
            "T2w",
            "BOLD",
            "Warp",
            "VBM_GM",
            "VBM_WM",
            "VBM_CSF",
            "fALFF",
            "GCOR",
            "LCOR",
            "DWI",
            "FreeSurfer"
         ],
         "title": "DataType",
         "type": "string"
      }
   },
   "additionalProperties": false
}

Config:

  • extra: str = forbid

  • use_enum_values: bool = True

Fields:
field datadir: Path = PosixPath('/tmp/tmp5u84on0q')
field n_timepoints: int | None = 50
field resolution: float = 3.0
field types: list[DataType] = [<DataType.BOLD: 'BOLD'>]
get_element_keys()

Get element keys.

Returns:
list of str

The element keys.

get_elements()

Get elements.

Returns:
list of str

List of elements that can be grabbed.

get_item(subject)

Implement indexing support.

Parameters:
subjectstr

The subject to retrieve.

Returns:
dict

The data along with the metadata.

pydantic model junifer.testing.datagrabbers.OasisVBMTestingDataGrabber

DataGrabber for Oasis VBM testing data.

Wrapper for nilearn.datasets.fetch_oasis_vbm().

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Show JSON schema
{
   "title": "OasisVBMTestingDataGrabber",
   "description": "DataGrabber for Oasis VBM testing data.\n\nWrapper for :func:`nilearn.datasets.fetch_oasis_vbm`.",
   "type": "object",
   "properties": {
      "types": {
         "default": [
            "VBM_GM"
         ],
         "items": {
            "$ref": "#/$defs/DataType"
         },
         "title": "Types",
         "type": "array"
      },
      "datadir": {
         "default": "/tmp/tmpbogz3olo",
         "format": "path",
         "title": "Datadir",
         "type": "string"
      }
   },
   "$defs": {
      "DataType": {
         "description": "Accepted data type.",
         "enum": [
            "T1w",
            "T2w",
            "BOLD",
            "Warp",
            "VBM_GM",
            "VBM_WM",
            "VBM_CSF",
            "fALFF",
            "GCOR",
            "LCOR",
            "DWI",
            "FreeSurfer"
         ],
         "title": "DataType",
         "type": "string"
      }
   },
   "additionalProperties": false
}

Config:

  • extra: str = forbid

  • use_enum_values: bool = True

Fields:
field datadir: Path = PosixPath('/tmp/tmpbogz3olo')
field types: list[DataType] = [<DataType.VBM_GM: 'VBM_GM'>]
get_element_keys()

Get element keys.

Returns:
list of str

The element keys.

get_elements()

Get elements.

Returns:
list of str

List of elements that can be grabbed.

get_item(subject)

Implement indexing support.

Parameters:
subjectstr

The subject to retrieve.

Returns:
dict

The data along with the metadata.

model_post_init(context)

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

enum junifer.testing.datagrabbers.PartlyCloudyAgeGroup(value)

Age group to fetch.

  • Adult : fetch adults only (n=33, ages 18-39)

  • Child : fetch children only (n=122, ages 3-12)

  • Both : fetch full sample (n=155)

Member Type:

str

Valid values are as follows:

Adult = <PartlyCloudyAgeGroup.Adult: 'adult'>
Child = <PartlyCloudyAgeGroup.Child: 'child'>
Both = <PartlyCloudyAgeGroup.Both: 'both'>
pydantic model junifer.testing.datagrabbers.PartlyCloudyTestingDataGrabber

DataGrabber for Partly Cloudy dataset.

Wrapper for nilearn.datasets.fetch_development_fmri().

Parameters:
reduce_confoundsbool, optional

If True, the returned confounds only include 6 motion parameters, mean framewise displacement, signal from white matter, csf, and 6 anatomical compcor parameters. This selection only serves the purpose of having realistic examples. Depending on your research question, other confounds might be more appropriate. If False, returns all fMRIPrep confounds (default True).

age_group{“adult”, “child”, “both”}, optional

Age group to fetch (default PartlyCloudyAgeGroup.Both).

n_subjectsint, optional

The number of subjects to use (default 10).

n_timepointsint or None, optional

The number of timepoints to keep. The truncated BOLD images and confounds are cached next to the original files in the nilearn data directory. If None, all the 168 timepoints are kept (default None).

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Show JSON schema
{
   "title": "PartlyCloudyTestingDataGrabber",
   "description": "DataGrabber for Partly Cloudy dataset.\n\nWrapper for :func:`nilearn.datasets.fetch_development_fmri`.\n\nParameters\n----------\nreduce_confounds : bool, optional\n    If True, the returned confounds only include 6 motion parameters,\n    mean framewise displacement, signal from white matter, csf, and\n    6 anatomical compcor parameters. This selection only serves the\n    purpose of having realistic examples. Depending on your research\n    question, other confounds might be more appropriate.\n    If False, returns all :term:`fMRIPrep` confounds (default True).\nage_group : {\"adult\", \"child\", \"both\"}, optional\n   Age group to fetch (default ``PartlyCloudyAgeGroup.Both``).\nn_subjects : int, optional\n    The number of subjects to use (default 10).\nn_timepoints : int or None, optional\n    The number of timepoints to keep. The truncated BOLD images and\n    confounds are cached next to the original files in the nilearn data\n    directory. If None, all the 168 timepoints are kept (default None).",
   "type": "object",
   "properties": {
      "types": {
         "default": [
            "BOLD"
         ],
         "items": {
            "$ref": "#/$defs/DataType"
         },
         "title": "Types",
         "type": "array"
      },
      "datadir": {
         "default": "/tmp/tmp5l7xuyal",
         "format": "path",
         "title": "Datadir",
         "type": "string"
      },
      "reduce_confounds": {
         "default": true,
         "title": "Reduce Confounds",
         "type": "boolean"
      },
      "age_group": {
         "$ref": "#/$defs/PartlyCloudyAgeGroup",
         "default": "both"
      },
      "n_subjects": {
         "default": 10,
         "title": "N Subjects",
         "type": "integer"
      },
      "n_timepoints": {
         "anyOf": [
            {
               "type": "integer"
            },
            {
               "type": "null"
            }
         ],
         "default": null,
         "title": "N Timepoints"
      }
   },
   "$defs": {
      "DataType": {
         "description": "Accepted data type.",
         "enum": [
            "T1w",
            "T2w",
            "BOLD",
            "Warp",
            "VBM_GM",
            "VBM_WM",
            "VBM_CSF",
            "fALFF",
            "GCOR",
            "LCOR",
            "DWI",
            "FreeSurfer"
         ],
         "title": "DataType",
         "type": "string"
      },
      "PartlyCloudyAgeGroup": {
         "description": "Age group to fetch.\n\n* ``Adult`` : fetch adults only (n=33, ages 18-39)\n* ``Child`` : fetch children only (n=122, ages 3-12)\n* ``Both`` : fetch full sample (n=155)",
         "enum": [
            "adult",
            "child",
            "both"
         ],
         "title": "PartlyCloudyAgeGroup",
         "type": "string"
      }
   },
   "additionalProperties": false
}

Config:

  • extra: str = forbid

  • use_enum_values: bool = True

Fields:
field age_group: PartlyCloudyAgeGroup = PartlyCloudyAgeGroup.Both
field datadir: Path = PosixPath('/tmp/tmp5l7xuyal')
field n_subjects: int = 10
field n_timepoints: int | None = None
field reduce_confounds: bool = True
field types: list[DataType] = [<DataType.BOLD: 'BOLD'>]
get_element_keys()

Get element keys.

Returns:
list of str

The element keys.

get_elements()

Get elements.

Returns:
list of str

List of elements that can be grabbed.

get_item(subject)

Implement indexing support.

Parameters:
subjectstr

The subject to retrieve.

Returns:
dict

The data along with the metadata.

pydantic model junifer.testing.datagrabbers.SPMAuditoryTestingDataGrabber

DataGrabber for SPM Auditory dataset.

Wrapper for nilearn.datasets.fetch_spm_auditory(). The dataset has a single subject, which is provided for each of the elements.

Parameters:
n_timepointsint or None, optional

The number of BOLD timepoints to keep. If None, all the 84 timepoints are kept (default None).

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Show JSON schema
{
   "title": "SPMAuditoryTestingDataGrabber",
   "description": "DataGrabber for SPM Auditory dataset.\n\nWrapper for :func:`nilearn.datasets.fetch_spm_auditory`. The dataset has\na single subject, which is provided for each of the elements.\n\nParameters\n----------\nn_timepoints : int or None, optional\n    The number of BOLD timepoints to keep. If None, all the 84\n    timepoints are kept (default None).",
   "type": "object",
   "properties": {
      "types": {
         "default": [
            "BOLD",
            "T1w"
         ],
         "items": {
            "$ref": "#/$defs/DataType"
         },
         "title": "Types",
         "type": "array"
      },
      "datadir": {
         "default": "/tmp/tmpal3h61cf",
         "format": "path",
         "title": "Datadir",
         "type": "string"
      },
      "n_timepoints": {
         "anyOf": [
            {
               "type": "integer"
            },
            {
               "type": "null"
            }
         ],
         "default": null,
         "title": "N Timepoints"
      }
   },
   "$defs": {
      "DataType": {
         "description": "Accepted data type.",
         "enum": [
            "T1w",
            "T2w",
            "BOLD",
            "Warp",
            "VBM_GM",
            "VBM_WM",
            "VBM_CSF",
            "fALFF",
            "GCOR",
            "LCOR",
            "DWI",
            "FreeSurfer"
         ],
         "title": "DataType",
         "type": "string"
      }
   },
   "additionalProperties": false
}

Config:

  • extra: str = forbid

  • use_enum_values: bool = True

Fields:
field datadir: Path = PosixPath('/tmp/tmpal3h61cf')
field n_timepoints: int | None = None
field types: list[DataType] = [<DataType.BOLD: 'BOLD'>, <DataType.T1w: 'T1w'>]
get_element_keys()

Get element keys.

Returns:
list of str

The element keys.

get_elements()

Get elements.

Returns:
list of str

List of elements that can be grabbed.

get_item(subject)

Implement indexing support.

Parameters:
subjectstr

The subject to retrieve.

Returns:
dict

The data along with the metadata.

pydantic model junifer.testing.datagrabbers.UCLACNPVBMTestingDataGrabber

DataGrabber for UCLA CNP VBM testing data.

Grey matter probability maps (computed with fMRIPrep) of 10 control subjects of the UCLA Consortium for Neuropsychiatric Phenomics LA5c study (OpenNeuro ds000030, release R1.0.4), downloaded with nilearn.datasets.fetch_openneuro_dataset().

The maps are in MNI152NLin2009cAsym at 1mm. Other resolutions are resampled (linear interpolation) to the corresponding templateflow grid, so templates and masks at that resolution do not need resampling. They are cached (uncompressed) next to the original files in the nilearn data directory.

Parameters:
resolutionfloat, optional

The resolution (in mm) of the maps (default 2.0).

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Show JSON schema
{
   "title": "UCLACNPVBMTestingDataGrabber",
   "description": "DataGrabber for UCLA CNP VBM testing data.\n\nGrey matter probability maps (computed with fMRIPrep) of 10 control\nsubjects of the UCLA Consortium for Neuropsychiatric Phenomics LA5c\nstudy (OpenNeuro ds000030, release R1.0.4), downloaded with\n:func:`nilearn.datasets.fetch_openneuro_dataset`.\n\nThe maps are in MNI152NLin2009cAsym at 1mm. Other resolutions are\nresampled (linear interpolation) to the corresponding templateflow grid,\nso templates and masks at that resolution do not need resampling. They\nare cached (uncompressed) next to the original files in the nilearn data\ndirectory.\n\nParameters\n----------\nresolution : float, optional\n    The resolution (in mm) of the maps (default 2.0).",
   "type": "object",
   "properties": {
      "types": {
         "default": [
            "VBM_GM"
         ],
         "items": {
            "$ref": "#/$defs/DataType"
         },
         "title": "Types",
         "type": "array"
      },
      "datadir": {
         "default": "/tmp/tmpmc101b16",
         "format": "path",
         "title": "Datadir",
         "type": "string"
      },
      "resolution": {
         "default": 2.0,
         "title": "Resolution",
         "type": "number"
      }
   },
   "$defs": {
      "DataType": {
         "description": "Accepted data type.",
         "enum": [
            "T1w",
            "T2w",
            "BOLD",
            "Warp",
            "VBM_GM",
            "VBM_WM",
            "VBM_CSF",
            "fALFF",
            "GCOR",
            "LCOR",
            "DWI",
            "FreeSurfer"
         ],
         "title": "DataType",
         "type": "string"
      }
   },
   "additionalProperties": false
}

Config:

  • extra: str = forbid

  • use_enum_values: bool = True

Fields:
field datadir: Path = PosixPath('/tmp/tmpmc101b16')
field resolution: float = 2.0
field types: list[DataType] = [<DataType.VBM_GM: 'VBM_GM'>]
get_element_keys()

Get element keys.

Returns:
list of str

The element keys.

get_elements()

Get elements.

Returns:
list of str

List of elements that can be grabbed.

get_item(subject)

Implement indexing support.

Parameters:
subjectstr

The subject to retrieve.

Returns:
dict

The data along with the metadata.

get_participants()

Get the participants information.

Returns:
pandas.DataFrame

The participants information (e.g. age and gender), indexed by subject.