From fe6253404543821a7d1c67417866dd07116837e5 Mon Sep 17 00:00:00 2001
From: Cody Baker <cbaker9@nd.edu>
Date: Sun, 17 Sep 2023 19:06:12 -0400
Subject: [PATCH 01/13] add backends and their tests

---
 src/neuroconv/tools/nwb_helpers/__init__.py   |  6 +-
 ...base_dataset_models.py => _base_models.py} | 30 ++++++++-
 ...hdf5_dataset_models.py => _hdf5_models.py} | 20 +++++-
 ...zarr_dataset_models.py => _zarr_models.py} | 29 ++++++++-
 src/neuroconv/tools/testing/__init__.py       |  8 ++-
 .../testing/_mock/_mock_dataset_models.py     | 63 +++++++++++++++++--
 .../test_dataset_configuration_model.py       |  4 +-
 .../test_dataset_configuration_models.py      | 50 ---------------
 .../test_hdf5_backend_configuration_model.py  | 38 +++++++++++
 .../test_zarr_backend_configuration_model.py  | 40 ++++++++++++
 10 files changed, 221 insertions(+), 67 deletions(-)
 rename src/neuroconv/tools/nwb_helpers/_models/{_base_dataset_models.py => _base_models.py} (80%)
 rename src/neuroconv/tools/nwb_helpers/_models/{_hdf5_dataset_models.py => _hdf5_models.py} (80%)
 rename src/neuroconv/tools/nwb_helpers/_models/{_zarr_dataset_models.py => _zarr_models.py} (82%)
 delete mode 100644 tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_models.py
 create mode 100644 tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
 create mode 100644 tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py

diff --git a/src/neuroconv/tools/nwb_helpers/__init__.py b/src/neuroconv/tools/nwb_helpers/__init__.py
index 07dd54ffc..d5f7c0b0a 100644
--- a/src/neuroconv/tools/nwb_helpers/__init__.py
+++ b/src/neuroconv/tools/nwb_helpers/__init__.py
@@ -5,8 +5,8 @@
     make_nwbfile_from_metadata,
     make_or_load_nwbfile,
 )
-from ._models._base_dataset_models import DatasetConfiguration, DatasetInfo
-from ._models._hdf5_dataset_models import HDF5DatasetConfiguration, AVAILABLE_HDF5_COMPRESSION_METHODS
-from ._models._zarr_dataset_models import ZarrDatasetConfiguration, AVAILABLE_ZARR_COMPRESSION_METHODS
+from ._models._base_models import DatasetConfiguration, DatasetInfo
+from ._models._hdf5_models import HDF5BackendConfiguration, HDF5DatasetConfiguration, AVAILABLE_HDF5_COMPRESSION_METHODS
+from ._models._zarr_models import ZarrBackendConfiguration, ZarrDatasetConfiguration, AVAILABLE_ZARR_COMPRESSION_METHODS
 
 BACKEND_TO_DATASET_CONFIGURATION = dict(hdf5=HDF5DatasetConfiguration, zarr=ZarrDatasetConfiguration)
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_base_dataset_models.py b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
similarity index 80%
rename from src/neuroconv/tools/nwb_helpers/_models/_base_dataset_models.py
rename to src/neuroconv/tools/nwb_helpers/_models/_base_models.py
index 624896466..eb0408c2e 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_base_dataset_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
@@ -1,10 +1,11 @@
 """Base Pydantic models for DatasetInfo and DatasetConfiguration."""
-from typing import Any, Dict, Tuple, Union
+from typing import Any, Dict, Tuple, Union, Literal, Type
 
 import h5py
 import numcodecs
 import numpy as np
-from pydantic import BaseModel, Field, root_validator, validator
+from hdmf.container import DataIO
+from pydantic import BaseModel, Field, root_validator
 
 
 class DatasetInfo(BaseModel):
@@ -113,3 +114,28 @@ def get_data_io_keyword_arguments(self):
         Fetch the properly structured dictionary of input arguments to be passed directly into a H5DataIO or ZarrDataIO.
         """
         raise NotImplementedError
+
+
+class BackendConfiguration(BaseModel):
+    """A model for matching collections of DatasetConfigurations to a specific backend."""
+
+    backend: Literal["hdf5", "zarr"] = Field(description="The name of the backend used to configure the NWBFile.")
+    data_io_class: Type[DataIO] = Field(description="The DataIO class that is specific to this backend.")
+    dataset_configurations: Dict[str, DatasetConfiguration] = Field(
+        description=(
+            "A mapping from object locations to their DatasetConfiguration specification that contains all information "
+            "for writing the datasets to disk using the specific backend."
+        )
+    )
+
+    def __str__(self) -> str:
+        """Not overriding __repr__ as this is intended to render only when wrapped in print()."""
+        string = (
+            f"\nConfigurable datasets identified using the {self.backend} backend"
+            f"\n{'-' * (43 + len(self.backend) + 8)}"
+        )
+
+        for dataset_configuration in self.dataset_configurations.values():
+            string += f"\n{dataset_configuration}"
+
+        return string
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_dataset_models.py b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
similarity index 80%
rename from src/neuroconv/tools/nwb_helpers/_models/_hdf5_dataset_models.py
rename to src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
index df9e98c9c..e21015f89 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_dataset_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
@@ -1,11 +1,12 @@
 """Base Pydantic models for the HDF5DatasetConfiguration."""
-from typing import Any, Dict, Literal, Union
+from typing import Any, Dict, Literal, Union, Type
 
 import h5py
+from pynwb import H5DataIO
 from nwbinspector.utils import is_module_installed
 from pydantic import Field
 
-from ._base_dataset_models import DatasetConfiguration
+from ._base_models import DatasetConfiguration, BackendConfiguration
 
 _base_hdf5_filters = set(h5py.filters.decode) - set(
     (
@@ -74,3 +75,18 @@ def get_data_io_keyword_arguments(self) -> Dict[str, Any]:
             compression_bundle = dict(compression=self.compression_method, compression_opts=self.compression_options)
 
         return dict(chunks=self.chunk_shape, **compression_bundle)
+
+
+class HDF5BackendConfiguration(BackendConfiguration):
+    """A model for matching collections of DatasetConfigurations specific to the HDF5 backend."""
+
+    backend: Literal["hdf5"] = Field(
+        default="hdf5", description="The name of the backend used to configure the NWBFile."
+    )
+    data_io_class: Type[H5DataIO] = Field(default=H5DataIO, description="The DataIO class that is specific to HDF5.")
+    dataset_configurations: Dict[str, HDF5DatasetConfiguration] = Field(
+        description=(
+            "A mapping from object locations to their HDF5DatasetConfiguration specification that contains all "
+            "information for writing the datasets to disk using the HDF5 backend."
+        )
+    )
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_dataset_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
similarity index 82%
rename from src/neuroconv/tools/nwb_helpers/_models/_zarr_dataset_models.py
rename to src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index d8691c677..0e83d58e5 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_dataset_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -1,11 +1,13 @@
 """Base Pydantic models for the ZarrDatasetConfiguration."""
-from typing import Any, Dict, Literal, Union, List
+from typing import Any, Dict, Literal, Union, List, Type
 
 import numcodecs
 import zarr
+import psutil
+from hdmf_zarr import ZarrDataIO
 from pydantic import Field, root_validator
 
-from ._base_dataset_models import DatasetConfiguration
+from ._base_models import DatasetConfiguration, BackendConfiguration
 
 _available_zarr_filters = (
     set(zarr.codec_registry.keys())
@@ -120,3 +122,26 @@ def get_data_io_keyword_arguments(self) -> Dict[str, Any]:
             compressor = False
 
         return dict(chunks=self.chunk_shape, filters=filters, compressor=compressor)
+
+
+class ZarrBackendConfiguration(BackendConfiguration):
+    """A model for matching collections of DatasetConfigurations specific to the Zarr backend."""
+
+    backend: Literal["zarr"] = Field(
+        default="zarr", description="The name of the backend used to configure the NWBFile."
+    )
+    data_io_class: Type[ZarrDataIO] = Field(
+        default=ZarrDataIO, description="The DataIO class that is specific to Zarr."
+    )
+    dataset_configurations: Dict[str, ZarrDatasetConfiguration] = Field(
+        description=(
+            "A mapping from object locations to their ZarrDatasetConfiguration specification that contains all "
+            "information for writing the datasets to disk using the Zarr backend."
+        )
+    )
+    number_of_jobs: int = Field(
+        description="Number of jobs to use in parallel during write.",
+        ge=-psutil.cpu_count(),  # TODO: should we specify logical=False in cpu_count?
+        le=psutil.cpu_count(),
+        default=-2,  # -2 translates to 'all CPU except for one'
+    )
diff --git a/src/neuroconv/tools/testing/__init__.py b/src/neuroconv/tools/testing/__init__.py
index 731c19dbe..3c987fdd0 100644
--- a/src/neuroconv/tools/testing/__init__.py
+++ b/src/neuroconv/tools/testing/__init__.py
@@ -1,4 +1,10 @@
 from .mock_files import generate_path_expander_demo_ibl
 from .mock_interfaces import MockBehaviorEventInterface, MockSpikeGLXNIDQInterface
 from .mock_ttl_signals import generate_mock_ttl_signal, regenerate_test_cases
-from ._mock._mock_dataset_models import mock_DatasetInfo, mock_HDF5DatasetConfiguration, mock_ZarrDatasetConfiguration
+from ._mock._mock_dataset_models import (
+    mock_DatasetInfo,
+    mock_HDF5BackendConfiguration,
+    mock_ZarrBackendConfiguration,
+    mock_HDF5DatasetConfiguration,
+    mock_ZarrDatasetConfiguration,
+)
diff --git a/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py b/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
index e1d6a4e19..024ad9d3c 100644
--- a/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
+++ b/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
@@ -6,20 +6,27 @@
 
 from ...nwb_helpers import (
     DatasetInfo,
+    HDF5BackendConfiguration,
     HDF5DatasetConfiguration,
+    ZarrBackendConfiguration,
     ZarrDatasetConfiguration,
     AVAILABLE_HDF5_COMPRESSION_METHODS,
     AVAILABLE_ZARR_COMPRESSION_METHODS,
 )
 
 
-def mock_DatasetInfo() -> DatasetInfo:
+def mock_DatasetInfo(
+    object_id: str = "481a0860-3a0c-40ec-b931-df4a3e9b101f",
+    location: str = "acquisition/TestElectricalSeries/data",
+    full_shape: Tuple[int, ...] = (60 * 30_000, 384),  # ~1 minute of v1 NeuroPixels probe
+    dtype=np.dtype("int16"),
+) -> DatasetInfo:
     """Mock instance of a DatasetInfo with NeuroPixel-like values to showcase chunk/buffer recommendations."""
     return DatasetInfo(
-        object_id="481a0860-3a0c-40ec-b931-df4a3e9b101f",
-        location="acquisition/TestElectricalSeries/data",
-        full_shape=(60 * 30_000, 384),  # ~1 minute of v1 NeuroPixels probe
-        dtype=np.dtype("int16"),
+        object_id=object_id,
+        location=location,
+        full_shape=full_shape,
+        dtype=dtype,
     )
 
 
@@ -55,3 +62,49 @@ def mock_ZarrDatasetConfiguration(
         filter_methods=filter_methods,
         filter_options=filter_options,
     )
+
+
+def mock_HDF5BackendConfiguration() -> HDF5BackendConfiguration:
+    """Mock instance of a HDF5BackendConfiguration with several NeuroPixel-like datasets."""
+    dataset_configurations = {
+        "acquisition/TestElectricalSeriesAP/data": HDF5DatasetConfiguration(
+            dataset_info=mock_DatasetInfo(location="acquisition/TestElectricalSeriesAP/data"),
+            chunk_shape=(78_125, 64),  # ~10 MB
+            buffer_shape=(1_250_000, 384),  # ~1 GB
+        ),
+        "acquisition/TestElectricalSeriesLF/data": HDF5DatasetConfiguration(
+            dataset_info=mock_DatasetInfo(
+                object_id="bc37e164-519f-4b65-a976-206440f1d325",
+                location="acquisition/TestElectricalSeriesLF/data",
+                full_shape=(75_000, 384),
+            ),
+            chunk_shape=(37_500, 128),  # ~10 MB
+            buffer_shape=(75_000, 384),
+        ),
+    }
+
+    return HDF5BackendConfiguration(dataset_configurations=dataset_configurations)
+
+
+def mock_ZarrBackendConfiguration() -> ZarrBackendConfiguration:
+    """Mock instance of a HDF5BackendConfiguration with several NeuroPixel-like datasets."""
+    dataset_configurations = {
+        "acquisition/TestElectricalSeriesAP/data": ZarrDatasetConfiguration(
+            dataset_info=mock_DatasetInfo(location="acquisition/TestElectricalSeriesAP/data"),
+            chunk_shape=(78_125, 64),
+            buffer_shape=(1_250_000, 384),  # ~1 GB
+            filter_methods=["delta"],
+        ),
+        "acquisition/TestElectricalSeriesLF/data": ZarrDatasetConfiguration(
+            dataset_info=mock_DatasetInfo(
+                object_id="bc37e164-519f-4b65-a976-206440f1d325",
+                location="acquisition/TestElectricalSeriesLF/data",
+                full_shape=(75_000, 384),
+            ),
+            chunk_shape=(37_500, 128),  # ~10 MB
+            buffer_shape=(75_000, 384),
+            filter_methods=["delta"],
+        ),
+    }
+
+    return ZarrBackendConfiguration(dataset_configurations=dataset_configurations)
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_model.py
index 614fd92e3..b0f5a5e76 100644
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_model.py
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_model.py
@@ -1,7 +1,7 @@
 """Unit tests for the DatasetConfiguration Pydantic model."""
 import pytest
 
-from neuroconv.tools.nwb_helpers._models._base_dataset_models import DatasetConfiguration
+from neuroconv.tools.nwb_helpers._models._base_models import DatasetConfiguration
 from neuroconv.tools.testing import mock_DatasetInfo
 
 
@@ -11,6 +11,6 @@ def test_get_data_io_keyword_arguments_not_implemented():
         chunk_shape=(78_125, 64),
         buffer_shape=(1_250_000, 384),
     )
-    
+
     with pytest.raises(NotImplementedError):
         dataset_configuration.get_data_io_keyword_arguments()
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_models.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_models.py
deleted file mode 100644
index 273610fe4..000000000
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_dataset_configuration_models.py
+++ /dev/null
@@ -1,50 +0,0 @@
-"""Unit tests for the DatasetInfo Pydantic model."""
-from io import StringIO
-from unittest.mock import patch
-
-import numpy as np
-
-from neuroconv.tools.nwb_helpers import 
-
-
-def MockHDF5DatasetConfig() -> DatasetInfo:
-    return DatasetInfo(
-        object_id="abc123",
-        location="TestParent/data",
-        full_shape=(2, 4),
-        dtype=np.dtype("int16"),
-    )
-
-
-def test_dataset_info_print():
-    """Test the printout display of a Dataset modellooks nice."""
-    dataset_info = MockDatasetInfo()
-
-    with patch("sys.stdout", new=StringIO()) as out:
-        print(dataset_info)
-
-    expected_print = """
-TestParent/data
----------------
-  maxshape: (2, 4)
-  dtype: int16
-"""
-    assert out.getvalue() == expected_print
-
-
-def test_dataset_info_repr():
-    """Test the programmatic repr of a Dataset model is more dataclass-like."""
-    dataset_info = MockDatasetInfo()
-
-    # Important to keep the `repr` unmodified for appearance inside iterables of DatasetInfo objects
-    expected_repr = (
-        "DatasetInfo(object_id='abc123', location='TestParent/data', full_shape=(2, 4), dtype=dtype('int16'))"
-    )
-    assert repr(dataset_info) == expected_repr
-
-
-def test_dataset_info_hashability():
-    dataset_info = MockDatasetInfo()
-
-    test_dict = {dataset_info: True}  # Technically this alone would raise an error if it didn't work...
-    assert test_dict[dataset_info] is True  # ... but asserting this for good measure.
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
new file mode 100644
index 000000000..e77694d08
--- /dev/null
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
@@ -0,0 +1,38 @@
+"""Unit tests for the DatasetInfo Pydantic model."""
+from io import StringIO
+from unittest.mock import patch
+
+
+from neuroconv.tools.testing import mock_HDF5BackendConfiguration
+
+
+def test_hdf5_backend_configuration_print():
+    """Test the printout display of a HDF5DatasetConfiguration model looks nice."""
+    hdf5_backend_configuration = mock_HDF5BackendConfiguration()
+
+    with patch("sys.stdout", new=StringIO()) as out:
+        print(hdf5_backend_configuration)
+
+    expected_print = """
+Configurable datasets identified using the hdf5 backend
+-------------------------------------------------------
+
+acquisition/TestElectricalSeriesAP/data
+---------------------------------------
+  maxshape: (1800000, 384)
+  dtype: int16
+
+  chunk_shape: (78125, 64)
+  buffer_shape: (1250000, 384)
+  compression_method: gzip
+
+acquisition/TestElectricalSeriesLF/data
+---------------------------------------
+  maxshape: (75000, 384)
+  dtype: int16
+
+  chunk_shape: (37500, 128)
+  buffer_shape: (75000, 384)
+  compression_method: gzip
+"""
+    assert out.getvalue() == expected_print
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
new file mode 100644
index 000000000..66d7dbc03
--- /dev/null
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
@@ -0,0 +1,40 @@
+"""Unit tests for the DatasetInfo Pydantic model."""
+from io import StringIO
+from unittest.mock import patch
+
+
+from neuroconv.tools.testing import mock_ZarrBackendConfiguration
+
+
+def test_zarr_backend_configuration_print():
+    """Test the printout display of a HDF5DatasetConfiguration model looks nice."""
+    zarr_backend_configuration = mock_ZarrBackendConfiguration()
+
+    with patch("sys.stdout", new=StringIO()) as out:
+        print(zarr_backend_configuration)
+
+    expected_print = """
+Configurable datasets identified using the zarr backend
+-------------------------------------------------------
+
+acquisition/TestElectricalSeriesAP/data
+---------------------------------------
+  maxshape: (1800000, 384)
+  dtype: int16
+
+  chunk_shape: (78125, 64)
+  buffer_shape: (1250000, 384)
+  compression_method: gzip
+  filter_methods: ['delta']
+
+acquisition/TestElectricalSeriesLF/data
+---------------------------------------
+  maxshape: (75000, 384)
+  dtype: int16
+
+  chunk_shape: (37500, 128)
+  buffer_shape: (75000, 384)
+  compression_method: gzip
+  filter_methods: ['delta']
+"""
+    assert out.getvalue() == expected_print

From 81261d167139100f872cb8ef7b8313c0a237b3f5 Mon Sep 17 00:00:00 2001
From: Cody Baker <cbaker9@nd.edu>
Date: Sun, 17 Sep 2023 19:07:31 -0400
Subject: [PATCH 02/13] include global mapper

---
 src/neuroconv/tools/nwb_helpers/__init__.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/neuroconv/tools/nwb_helpers/__init__.py b/src/neuroconv/tools/nwb_helpers/__init__.py
index d5f7c0b0a..89c738d51 100644
--- a/src/neuroconv/tools/nwb_helpers/__init__.py
+++ b/src/neuroconv/tools/nwb_helpers/__init__.py
@@ -10,3 +10,4 @@
 from ._models._zarr_models import ZarrBackendConfiguration, ZarrDatasetConfiguration, AVAILABLE_ZARR_COMPRESSION_METHODS
 
 BACKEND_TO_DATASET_CONFIGURATION = dict(hdf5=HDF5DatasetConfiguration, zarr=ZarrDatasetConfiguration)
+BACKEND_TO_CONFIGURATION = dict(hdf5=HDF5BackendConfiguration, zarr=ZarrBackendConfiguration)

From fa15d6aa6e70b50d8771486b6b9f566812560024 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 18 Sep 2023 02:50:30 +0000
Subject: [PATCH 03/13] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/neuroconv/tools/nwb_helpers/__init__.py          | 12 ++++++++++--
 .../tools/nwb_helpers/_models/_base_models.py        |  2 +-
 .../tools/nwb_helpers/_models/_hdf5_models.py        |  6 +++---
 .../tools/nwb_helpers/_models/_zarr_models.py        |  6 +++---
 src/neuroconv/tools/testing/__init__.py              |  9 ++-------
 .../test_hdf5_backend_configuration_model.py         |  1 -
 .../test_zarr_backend_configuration_model.py         |  1 -
 7 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/src/neuroconv/tools/nwb_helpers/__init__.py b/src/neuroconv/tools/nwb_helpers/__init__.py
index 89c738d51..0982439bb 100644
--- a/src/neuroconv/tools/nwb_helpers/__init__.py
+++ b/src/neuroconv/tools/nwb_helpers/__init__.py
@@ -6,8 +6,16 @@
     make_or_load_nwbfile,
 )
 from ._models._base_models import DatasetConfiguration, DatasetInfo
-from ._models._hdf5_models import HDF5BackendConfiguration, HDF5DatasetConfiguration, AVAILABLE_HDF5_COMPRESSION_METHODS
-from ._models._zarr_models import ZarrBackendConfiguration, ZarrDatasetConfiguration, AVAILABLE_ZARR_COMPRESSION_METHODS
+from ._models._hdf5_models import (
+    AVAILABLE_HDF5_COMPRESSION_METHODS,
+    HDF5BackendConfiguration,
+    HDF5DatasetConfiguration,
+)
+from ._models._zarr_models import (
+    AVAILABLE_ZARR_COMPRESSION_METHODS,
+    ZarrBackendConfiguration,
+    ZarrDatasetConfiguration,
+)
 
 BACKEND_TO_DATASET_CONFIGURATION = dict(hdf5=HDF5DatasetConfiguration, zarr=ZarrDatasetConfiguration)
 BACKEND_TO_CONFIGURATION = dict(hdf5=HDF5BackendConfiguration, zarr=ZarrBackendConfiguration)
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
index eb0408c2e..ad940fb6f 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
@@ -1,5 +1,5 @@
 """Base Pydantic models for DatasetInfo and DatasetConfiguration."""
-from typing import Any, Dict, Tuple, Union, Literal, Type
+from typing import Any, Dict, Literal, Tuple, Type, Union
 
 import h5py
 import numcodecs
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
index e21015f89..6e1108432 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
@@ -1,12 +1,12 @@
 """Base Pydantic models for the HDF5DatasetConfiguration."""
-from typing import Any, Dict, Literal, Union, Type
+from typing import Any, Dict, Literal, Type, Union
 
 import h5py
-from pynwb import H5DataIO
 from nwbinspector.utils import is_module_installed
 from pydantic import Field
+from pynwb import H5DataIO
 
-from ._base_models import DatasetConfiguration, BackendConfiguration
+from ._base_models import BackendConfiguration, DatasetConfiguration
 
 _base_hdf5_filters = set(h5py.filters.decode) - set(
     (
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 0e83d58e5..7b7b2dcbc 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -1,13 +1,13 @@
 """Base Pydantic models for the ZarrDatasetConfiguration."""
-from typing import Any, Dict, Literal, Union, List, Type
+from typing import Any, Dict, List, Literal, Type, Union
 
 import numcodecs
-import zarr
 import psutil
+import zarr
 from hdmf_zarr import ZarrDataIO
 from pydantic import Field, root_validator
 
-from ._base_models import DatasetConfiguration, BackendConfiguration
+from ._base_models import BackendConfiguration, DatasetConfiguration
 
 _available_zarr_filters = (
     set(zarr.codec_registry.keys())
diff --git a/src/neuroconv/tools/testing/__init__.py b/src/neuroconv/tools/testing/__init__.py
index 1afc05495..502634466 100644
--- a/src/neuroconv/tools/testing/__init__.py
+++ b/src/neuroconv/tools/testing/__init__.py
@@ -1,15 +1,10 @@
 from ._mock._mock_dataset_models import (
     mock_DatasetInfo,
+    mock_HDF5BackendConfiguration,
     mock_HDF5DatasetConfiguration,
+    mock_ZarrBackendConfiguration,
     mock_ZarrDatasetConfiguration,
 )
 from .mock_files import generate_path_expander_demo_ibl
 from .mock_interfaces import MockBehaviorEventInterface, MockSpikeGLXNIDQInterface
 from .mock_ttl_signals import generate_mock_ttl_signal, regenerate_test_cases
-from ._mock._mock_dataset_models import (
-    mock_DatasetInfo,
-    mock_HDF5BackendConfiguration,
-    mock_ZarrBackendConfiguration,
-    mock_HDF5DatasetConfiguration,
-    mock_ZarrDatasetConfiguration,
-)
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
index e77694d08..290ca6a1b 100644
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
@@ -2,7 +2,6 @@
 from io import StringIO
 from unittest.mock import patch
 
-
 from neuroconv.tools.testing import mock_HDF5BackendConfiguration
 
 
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
index 66d7dbc03..9e235df77 100644
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
@@ -2,7 +2,6 @@
 from io import StringIO
 from unittest.mock import patch
 
-
 from neuroconv.tools.testing import mock_ZarrBackendConfiguration
 
 

From fd7c5e4e1da0c278778c9d4359dd580de4196545 Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Sun, 17 Sep 2023 22:53:46 -0400
Subject: [PATCH 04/13] Update CHANGELOG.md

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4f1375b46..7ee7c7c08 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,6 +3,7 @@
 ### Features
 
 * Added Pydantic data models of `DatasetInfo` (immutable summary of core dataset values such as maximum shape and dtype) and `DatasetConfiguration` for both HDF5 and Zarr datasets (the optional layer that specifies chunk/buffering/compression). [PR #567](https://github.com/catalystneuro/neuroconv/pull/567)
+* Added Pydantic data models of `BackendConfiguration` for both HDF5 and Zarr datasets (container/mapper of all the `DatasetConfiguration`s for a particular file). [PR #568](https://github.com/catalystneuro/neuroconv/pull/568)
 
 
 

From eb705b4bc7ce3b24269092a4fcae542bb454749d Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Sun, 17 Sep 2023 23:55:11 -0400
Subject: [PATCH 05/13] Update requirements-minimal.txt

---
 requirements-minimal.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/requirements-minimal.txt b/requirements-minimal.txt
index 7ba056107..26545b661 100644
--- a/requirements-minimal.txt
+++ b/requirements-minimal.txt
@@ -3,6 +3,7 @@ jsonschema>=3.2.0
 PyYAML>=5.4
 scipy>=1.4.1
 h5py>=2.10.0
+hdmf_zarr>=3.0.0
 hdmf>=3.4.7
 pynwb>=2.3.2;python_version>='3.8'
 psutil>=5.8.0

From 9bb6c0434ccb520e0647dfbe97255a99ab5a7726 Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Wed, 4 Oct 2023 03:36:55 -0400
Subject: [PATCH 06/13] Update
 src/neuroconv/tools/testing/_mock/_mock_dataset_models.py

Co-authored-by: Heberto Mayorquin <h.mayorquin@gmail.com>
---
 src/neuroconv/tools/testing/_mock/_mock_dataset_models.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py b/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
index 67b82c1bb..c1cbb0f3a 100644
--- a/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
+++ b/src/neuroconv/tools/testing/_mock/_mock_dataset_models.py
@@ -65,7 +65,7 @@ def mock_ZarrDatasetConfiguration(
 
 
 def mock_HDF5BackendConfiguration() -> HDF5BackendConfiguration:
-    """Mock instance of a HDF5BackendConfiguration with several NeuroPixel-like datasets."""
+    """Mock instance of a HDF5BackendConfiguration with two NeuroPixel-like datasets."""
     dataset_configurations = {
         "acquisition/TestElectricalSeriesAP/data": HDF5DatasetConfiguration(
             dataset_info=mock_DatasetInfo(location="acquisition/TestElectricalSeriesAP/data"),

From 5a8b139620a59cd1c1b2d6b87ebd5b9f49d344c0 Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Wed, 4 Oct 2023 03:40:01 -0400
Subject: [PATCH 07/13] Update
 src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py

---
 src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 7b7b2dcbc..9156e233e 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -140,7 +140,7 @@ class ZarrBackendConfiguration(BackendConfiguration):
         )
     )
     number_of_jobs: int = Field(
-        description="Number of jobs to use in parallel during write.",
+        description="Number of jobs to use in parallel during write. Negative slicing conforms with the pattern of indexing `list(range(total_number_of_cpu))[number_of_jobs]`; for example, `-1` uses all available CPU, `-2` uses all except one, etc.",
         ge=-psutil.cpu_count(),  # TODO: should we specify logical=False in cpu_count?
         le=psutil.cpu_count(),
         default=-2,  # -2 translates to 'all CPU except for one'

From 56fd1bb16328d9558692bc9098e9f76c20c66b1d Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 6 Nov 2023 14:54:25 +0000
Subject: [PATCH 08/13] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/neuroconv/tools/nwb_helpers/_models/_base_models.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
index 88fd837cc..313454678 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
@@ -1,7 +1,7 @@
 """Base Pydantic models for DatasetInfo and DatasetConfiguration."""
 import math
 from abc import ABC, abstractmethod
-from typing import Any, Dict, Literal, Tuple, Union, Type
+from typing import Any, Dict, Literal, Tuple, Type, Union
 
 import h5py
 import numcodecs

From d0fd8b8c0fcf9da43fb833918e18cc45551cd6a9 Mon Sep 17 00:00:00 2001
From: Cody Baker <cbaker9@nd.edu>
Date: Mon, 6 Nov 2023 10:33:55 -0500
Subject: [PATCH 09/13] fix tests

---
 .../tools/nwb_helpers/_models/_hdf5_models.py |  6 ++-
 .../tools/nwb_helpers/_models/_zarr_models.py |  6 ++-
 .../test_hdf5_backend_configuration_model.py  | 32 +++++++++++-----
 .../test_zarr_backend_configuration_model.py  | 38 +++++++++++++------
 4 files changed, 57 insertions(+), 25 deletions(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
index 6a97f1b50..daf772688 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_hdf5_models.py
@@ -84,10 +84,12 @@ def get_data_io_kwargs(self) -> Dict[str, Any]:
 class HDF5BackendConfiguration(BackendConfiguration):
     """A model for matching collections of DatasetConfigurations specific to the HDF5 backend."""
 
-    backend: Literal["hdf5"] = Field(
+    backend: Literal["hdf5"] = Field(  # TODO: in pydantic v2 use property instead of class attribute
         default="hdf5", description="The name of the backend used to configure the NWBFile."
     )
-    data_io_class: Type[H5DataIO] = Field(default=H5DataIO, description="The DataIO class that is specific to HDF5.")
+    data_io_class: Type[H5DataIO] = Field(  # TODO: in pydantic v2 use property instead of class attribute
+        default=H5DataIO, description="The DataIO class that is specific to HDF5."
+    )
     dataset_configurations: Dict[str, HDF5DatasetConfiguration] = Field(
         description=(
             "A mapping from object locations to their HDF5DatasetConfiguration specification that contains all "
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 55c434536..8874e212b 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -154,7 +154,11 @@ class ZarrBackendConfiguration(BackendConfiguration):
         )
     )
     number_of_jobs: int = Field(
-        description="Number of jobs to use in parallel during write. Negative slicing conforms with the pattern of indexing `list(range(total_number_of_cpu))[number_of_jobs]`; for example, `-1` uses all available CPU, `-2` uses all except one, etc.",
+        description=(
+            "Number of jobs to use in parallel during write. Negative slicing conforms with the pattern of indexing "
+            " `list(range(total_number_of_cpu))[number_of_jobs]`; for example, `-1` uses all available CPU, `-2` "
+            "uses all except one, etc."
+        ),
         ge=-psutil.cpu_count(),  # TODO: should we specify logical=False in cpu_count?
         le=psutil.cpu_count(),
         default=-2,  # -2 translates to 'all CPU except for one'
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
index 290ca6a1b..2d6242ad1 100644
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_hdf5_backend_configuration_model.py
@@ -18,20 +18,32 @@ def test_hdf5_backend_configuration_print():
 
 acquisition/TestElectricalSeriesAP/data
 ---------------------------------------
-  maxshape: (1800000, 384)
-  dtype: int16
+  dtype : int16
+  full shape of source array : (1800000, 384)
+  full size of source array : 1.38 GB
+
+  buffer shape : (1250000, 384)
+  maximum RAM usage per iteration : 0.96 GB
+
+  chunk shape : (78125, 64)
+  disk space usage per chunk : 10.00 MB
+
+  compression method : gzip
 
-  chunk_shape: (78125, 64)
-  buffer_shape: (1250000, 384)
-  compression_method: gzip
 
 acquisition/TestElectricalSeriesLF/data
 ---------------------------------------
-  maxshape: (75000, 384)
-  dtype: int16
+  dtype : int16
+  full shape of source array : (75000, 384)
+  full size of source array : 0.06 GB
+
+  buffer shape : (75000, 384)
+  maximum RAM usage per iteration : 0.06 GB
+
+  chunk shape : (37500, 128)
+  disk space usage per chunk : 9.60 MB
+
+  compression method : gzip
 
-  chunk_shape: (37500, 128)
-  buffer_shape: (75000, 384)
-  compression_method: gzip
 """
     assert out.getvalue() == expected_print
diff --git a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
index 9e235df77..e8017c719 100644
--- a/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
+++ b/tests/test_minimal/test_tools/test_backend_and_dataset_configuration/test_zarr_backend_configuration_model.py
@@ -18,22 +18,36 @@ def test_zarr_backend_configuration_print():
 
 acquisition/TestElectricalSeriesAP/data
 ---------------------------------------
-  maxshape: (1800000, 384)
-  dtype: int16
+  dtype : int16
+  full shape of source array : (1800000, 384)
+  full size of source array : 1.38 GB
+
+  buffer shape : (1250000, 384)
+  maximum RAM usage per iteration : 0.96 GB
+
+  chunk shape : (78125, 64)
+  disk space usage per chunk : 10.00 MB
+
+  compression method : gzip
+
+  filter methods : ['delta']
 
-  chunk_shape: (78125, 64)
-  buffer_shape: (1250000, 384)
-  compression_method: gzip
-  filter_methods: ['delta']
 
 acquisition/TestElectricalSeriesLF/data
 ---------------------------------------
-  maxshape: (75000, 384)
-  dtype: int16
+  dtype : int16
+  full shape of source array : (75000, 384)
+  full size of source array : 0.06 GB
+
+  buffer shape : (75000, 384)
+  maximum RAM usage per iteration : 0.06 GB
+
+  chunk shape : (37500, 128)
+  disk space usage per chunk : 9.60 MB
+
+  compression method : gzip
+
+  filter methods : ['delta']
 
-  chunk_shape: (37500, 128)
-  buffer_shape: (75000, 384)
-  compression_method: gzip
-  filter_methods: ['delta']
 """
     assert out.getvalue() == expected_print

From b014351f4b15aefe7f88b8ade6af663c14b348ec Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Tue, 7 Nov 2023 10:33:17 -0500
Subject: [PATCH 10/13] Apply suggestions from code review

Co-authored-by: Heberto Mayorquin <h.mayorquin@gmail.com>
---
 src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 8874e212b..353dd2a0d 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -155,11 +155,11 @@ class ZarrBackendConfiguration(BackendConfiguration):
     )
     number_of_jobs: int = Field(
         description=(
-            "Number of jobs to use in parallel during write. Negative slicing conforms with the pattern of indexing "
+            "Number of jobs to use in parallel during write. Negative values, starting from -1, will use all the available CPUs (including logical), -2 is all except one, etc. This is equivalent to the pattern of indexing of "
             " `list(range(total_number_of_cpu))[number_of_jobs]`; for example, `-1` uses all available CPU, `-2` "
             "uses all except one, etc."
         ),
         ge=-psutil.cpu_count(),  # TODO: should we specify logical=False in cpu_count?
         le=psutil.cpu_count(),
-        default=-2,  # -2 translates to 'all CPU except for one'
+        default=psutil.cpu_count() -1 
     )

From bdb6fd0f030ada801333a8b90a0f2300dbb01048 Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Tue, 7 Nov 2023 10:33:30 -0500
Subject: [PATCH 11/13] Update
 src/neuroconv/tools/nwb_helpers/_models/_base_models.py

Co-authored-by: Heberto Mayorquin <h.mayorquin@gmail.com>
---
 src/neuroconv/tools/nwb_helpers/_models/_base_models.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
index 313454678..ceba9781e 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
@@ -190,7 +190,8 @@ class BackendConfiguration(BaseModel):
     data_io_class: Type[DataIO] = Field(description="The DataIO class that is specific to this backend.")
     dataset_configurations: Dict[str, DatasetConfiguration] = Field(
         description=(
-            "A mapping from object locations to their DatasetConfiguration specification that contains all information "
+            "A mapping from object locations (e.g. `
+acquisition/TestElectricalSeriesAP/data`)  to their DatasetConfiguration specification that contains all information "
             "for writing the datasets to disk using the specific backend."
         )
     )

From 8c1d8561f5b4cfc8b88e3a44bb2cda7ffd9ec127 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 7 Nov 2023 15:35:22 +0000
Subject: [PATCH 12/13] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 353dd2a0d..4d96bcc43 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -161,5 +161,5 @@ class ZarrBackendConfiguration(BackendConfiguration):
         ),
         ge=-psutil.cpu_count(),  # TODO: should we specify logical=False in cpu_count?
         le=psutil.cpu_count(),
-        default=psutil.cpu_count() -1 
+        default=psutil.cpu_count() - 1,
     )

From 435053a2e212b8ce10d086dd04e9dc1cd1c09616 Mon Sep 17 00:00:00 2001
From: Cody Baker <51133164+CodyCBakerPhD@users.noreply.github.com>
Date: Tue, 7 Nov 2023 10:41:48 -0500
Subject: [PATCH 13/13] Apply suggestions from code review

---
 src/neuroconv/tools/nwb_helpers/_models/_base_models.py | 4 ++--
 src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py | 4 +++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
index ceba9781e..72b364dea 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_base_models.py
@@ -190,8 +190,8 @@ class BackendConfiguration(BaseModel):
     data_io_class: Type[DataIO] = Field(description="The DataIO class that is specific to this backend.")
     dataset_configurations: Dict[str, DatasetConfiguration] = Field(
         description=(
-            "A mapping from object locations (e.g. `
-acquisition/TestElectricalSeriesAP/data`)  to their DatasetConfiguration specification that contains all information "
+            "A mapping from object locations (e.g. `acquisition/TestElectricalSeriesAP/data`) "
+            "to their DatasetConfiguration specification that contains all information "
             "for writing the datasets to disk using the specific backend."
         )
     )
diff --git a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
index 4d96bcc43..760c7c2a9 100644
--- a/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
+++ b/src/neuroconv/tools/nwb_helpers/_models/_zarr_models.py
@@ -155,7 +155,9 @@ class ZarrBackendConfiguration(BackendConfiguration):
     )
     number_of_jobs: int = Field(
         description=(
-            "Number of jobs to use in parallel during write. Negative values, starting from -1, will use all the available CPUs (including logical), -2 is all except one, etc. This is equivalent to the pattern of indexing of "
+            "Number of jobs to use in parallel during write. Negative values, starting from -1, "
+            "will use all the available CPUs (including logical), -2 is all except one, etc. "
+            "This is equivalent to the pattern of indexing of "
             " `list(range(total_number_of_cpu))[number_of_jobs]`; for example, `-1` uses all available CPU, `-2` "
             "uses all except one, etc."
         ),