bw-processing 0.8.5__tar.gz → 0.9.1__tar.gz

{bw-processing-0.8.5/bw_processing.egg-info → bw_processing-0.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bw-processing
-Version: 0.8.5
+Version: 0.9.1
 Summary: Tools to create structured arrays in a common format
 Home-page: https://github.com/brightway-lca/bw_processing
 Author: Chris Mutel
@@ -22,10 +22,22 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown; charset=UTF-8
+License-File: LICENSE
+Requires-Dist: fs
+Requires-Dist: numpy
+Requires-Dist: pandas
 Provides-Extra: testing
+Requires-Dist: setuptools; extra == "testing"
+Requires-Dist: pytest; extra == "testing"
+Requires-Dist: pytest-cov; extra == "testing"
+Requires-Dist: pyarrow; extra == "testing"
 Provides-Extra: dev
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pylint; extra == "dev"
 Provides-Extra: docs
-License-File: LICENSE
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: myst_parser; extra == "docs"
+Requires-Dist: furo; extra == "docs"
 
 # bw-processing
 
@@ -34,10 +46,10 @@ Library for storing numeric data for use in matrix-based calculations. Designed
 [![PyPI](https://img.shields.io/pypi/v/bw-processing.svg)][pypi status]
 [![Status](https://img.shields.io/pypi/status/bw-processing.svg)][pypi status]
 [![Python Version](https://img.shields.io/pypi/pyversions/bw-processing)][pypi status]
-[![License](https://img.shields.io/pypi/l/bw-processing)][license]
+[![License](https://img.shields.io/pypi/l/bw_processing)][license]
 
 [![Read the documentation at https://bw-processing.readthedocs.io/](https://img.shields.io/readthedocs/bw-processing/latest.svg?label=Read%20the%20Docs)][read the docs]
-[![Tests](https://github.com/brightway-lca/bw-processing/actions/workflows/python-test.yml/badge.svg)][tests]
+[![Testing](https://github.com/brightway-lca/bw_processing/actions/workflows/python-test.yml/badge.svg)][tests]
 [![Codecov](https://codecov.io/gh/brightway-lca/bw-processing/branch/main/graph/badge.svg)][codecov]
 
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)][pre-commit]
@@ -45,7 +57,7 @@ Library for storing numeric data for use in matrix-based calculations. Designed
 
 [pypi status]: https://pypi.org/project/bw-processing/
 [read the docs]: https://bw-processing.readthedocs.io/
-[tests]: https://github.com/brightway-lca/bw-processing/actions?workflow=Tests
+[tests]: https://github.com/brightway-lca/bw_processing/actions/workflows/python-test.yml
 [codecov]: https://app.codecov.io/gh/brightway-lca/bw-processing
 [pre-commit]: https://github.com/pre-commit/pre-commit
 [black]: https://github.com/psf/black

{bw-processing-0.8.5 → bw_processing-0.9.1}/README.md

@@ -5,10 +5,10 @@ Library for storing numeric data for use in matrix-based calculations. Designed
 [![PyPI](https://img.shields.io/pypi/v/bw-processing.svg)][pypi status]
 [![Status](https://img.shields.io/pypi/status/bw-processing.svg)][pypi status]
 [![Python Version](https://img.shields.io/pypi/pyversions/bw-processing)][pypi status]
-[![License](https://img.shields.io/pypi/l/bw-processing)][license]
+[![License](https://img.shields.io/pypi/l/bw_processing)][license]
 
 [![Read the documentation at https://bw-processing.readthedocs.io/](https://img.shields.io/readthedocs/bw-processing/latest.svg?label=Read%20the%20Docs)][read the docs]
-[![Tests](https://github.com/brightway-lca/bw-processing/actions/workflows/python-test.yml/badge.svg)][tests]
+[![Testing](https://github.com/brightway-lca/bw_processing/actions/workflows/python-test.yml/badge.svg)][tests]
 [![Codecov](https://codecov.io/gh/brightway-lca/bw-processing/branch/main/graph/badge.svg)][codecov]
 
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)][pre-commit]
@@ -16,7 +16,7 @@ Library for storing numeric data for use in matrix-based calculations. Designed
 
 [pypi status]: https://pypi.org/project/bw-processing/
 [read the docs]: https://bw-processing.readthedocs.io/
-[tests]: https://github.com/brightway-lca/bw-processing/actions?workflow=Tests
+[tests]: https://github.com/brightway-lca/bw_processing/actions/workflows/python-test.yml
 [codecov]: https://app.codecov.io/gh/brightway-lca/bw-processing
 [pre-commit]: https://github.com/pre-commit/pre-commit
 [black]: https://github.com/psf/black

{bw-processing-0.8.5 → bw_processing-0.9.1}/bw_processing/__init__.py

@@ -15,6 +15,7 @@ __all__ = (
     "generic_zipfile_filesystem",
     "INDICES_DTYPE",
     "load_datapackage",
+    "MatrixSerializeFormat",
     "md5",
     "merge_datapackages_with_mask",
     "reindex",
@@ -25,11 +26,16 @@ __all__ = (
     "UndefinedInterface",
 )
 
-__version__ = "0.8.5"
+__version__ = "0.9.1"
 
 
 from .array_creation import create_array, create_structured_array
-from .constants import DEFAULT_LICENSES, INDICES_DTYPE, UNCERTAINTY_DTYPE
+from .constants import (
+    DEFAULT_LICENSES,
+    INDICES_DTYPE,
+    UNCERTAINTY_DTYPE,
+    MatrixSerializeFormat,
+)
 from .datapackage import (
     Datapackage,
     DatapackageBase,

{bw-processing-0.8.5 → bw_processing-0.9.1}/bw_processing/constants.py

@@ -1,4 +1,5 @@
 import re
+from enum import Enum
 
 import numpy as np
 
@@ -30,3 +31,19 @@ DEFAULT_LICENSES = [
         "title": "Open Data Commons Public Domain Dedication and License v1.0",
     }
 ]
+
+
+class MatrixSerializeFormat(str, Enum):
+    """
+    Enum with the serializing formats for the vectors and matrices.
+    """
+
+    NUMPY = "numpy"  # numpy .npy format
+    PARQUET = "parquet"  # Apache .parquet format
+
+
+# FILE EXTENSIONS
+NUMPY_SERIALIZE_FORMAT_EXTENSION = ".npy"
+NUMPY_SERIALIZE_FORMAT_NAME = "npy"
+PARQUET_SERIALIZE_FORMAT_EXTENSION = ".parquet"
+PARQUET_SERIALIZE_FORMAT_NAME = "pqt"

{bw-processing-0.8.5 → bw_processing-0.9.1}/bw_processing/datapackage.py

@@ -1,5 +1,6 @@
 import datetime
 import uuid
+from abc import ABC
 from functools import partial
 from typing import Any, Dict, List, Optional, Union
 
@@ -9,7 +10,15 @@ from fs.base import FS
 from fs.errors import ResourceNotFound
 from fs.memoryfs import MemoryFS
 
-from .constants import DEFAULT_LICENSES, INDICES_DTYPE
+from .constants import (
+    DEFAULT_LICENSES,
+    INDICES_DTYPE,
+    NUMPY_SERIALIZE_FORMAT_EXTENSION,
+    NUMPY_SERIALIZE_FORMAT_NAME,
+    PARQUET_SERIALIZE_FORMAT_EXTENSION,
+    PARQUET_SERIALIZE_FORMAT_NAME,
+    MatrixSerializeFormat,
+)
 from .errors import (
     Closed,
     InvalidMimetype,
@@ -25,10 +34,13 @@ from .proxies import Proxy, UndefinedInterface
 from .utils import check_name, check_suffix, load_bytes, resolve_dict_iterator
 
 
-class DatapackageBase:
+class DatapackageBase(ABC):
     """Base class for datapackages. Not for normal use - you should use either `Datapackage` or `FilteredDatapackage`."""
 
     def __init__(self):
+        # This is the global serialization format used for numpy.ndarray for the whole object.
+        # It can be overwritten locally for each numpy.ndarray introduced.
+        self._matrix_serialize_format_type = MatrixSerializeFormat.NUMPY
         self._finalized = False
         self._modified = set()
 
@@ -333,6 +345,7 @@ class Datapackage(DatapackageBase):
         seed: Optional[int] = None,
         sum_intra_duplicates: bool = True,
         sum_inter_duplicates: bool = False,
+        matrix_serialize_format_type: MatrixSerializeFormat = MatrixSerializeFormat.NUMPY,
     ) -> None:
         """Start a new data package.
 
@@ -344,6 +357,11 @@ class Datapackage(DatapackageBase):
         check_name(name)
 
         self.fs = fs or MemoryFS()
+        if not isinstance(matrix_serialize_format_type, MatrixSerializeFormat):
+            raise TypeError(
+                f"Matrix serialize format type ({matrix_serialize_format_type}) not recognized!"
+            )
+        self._matrix_serialize_format_type = matrix_serialize_format_type
 
         self.metadata = {
             "profile": "data-package",
@@ -351,12 +369,13 @@ class Datapackage(DatapackageBase):
             "id": id_ or uuid.uuid4().hex,
             "licenses": (metadata or {}).get("licenses", DEFAULT_LICENSES),
             "resources": [],
-            "created": datetime.datetime.utcnow().isoformat("T") + "Z",
+            "created": datetime.datetime.now(datetime.UTC).isoformat("T") + "Z",
             "combinatorial": combinatorial,
             "sequential": sequential,
             "seed": seed,
             "sum_intra_duplicates": sum_intra_duplicates,
             "sum_inter_duplicates": sum_inter_duplicates,
+            "matrix_serialize_format_type": matrix_serialize_format_type.value,
         }
         for k, v in (metadata or {}).items():
             if k not in self.metadata:
@@ -380,6 +399,7 @@ class Datapackage(DatapackageBase):
             mimetype="application/json",
         )
         self.fs.close()
+        self._finalized = True
 
     def _prepare_modifications(self) -> None:
         self._check_length_consistency()
@@ -406,6 +426,7 @@ class Datapackage(DatapackageBase):
         name: Optional[str] = None,
         dict_iterator: Any = None,
         nrows: Optional[int] = None,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
         **kwargs,
     ) -> None:
         """Create a persistant vector from an iterator. Uses the utility function ``resolve_dict_iterator``.
@@ -426,6 +447,7 @@ class Datapackage(DatapackageBase):
             indices_array=indices_array,
             flip_array=flip_array,
             distributions_array=distributions_array,
+            matrix_serialize_format_type=matrix_serialize_format_type,
             **kwargs,
         )
 
@@ -439,6 +461,7 @@ class Datapackage(DatapackageBase):
         flip_array: Optional[np.ndarray] = None,
         distributions_array: Optional[np.ndarray] = None,
         keep_proxy: bool = False,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
         **kwargs,
     ) -> None:
         """ """
@@ -458,6 +481,9 @@ class Datapackage(DatapackageBase):
             group=name,
             kind="indices",
             keep_proxy=keep_proxy,
+            matrix_serialize_format_type=matrix_serialize_format_type,
+            meta_object="vector",
+            meta_type="indices",
             **kwargs,
         )
         if data_array is not None:
@@ -480,6 +506,9 @@ class Datapackage(DatapackageBase):
                 name=name + ".data",
                 kind="data",
                 keep_proxy=keep_proxy,
+                matrix_serialize_format_type=matrix_serialize_format_type,
+                meta_object="vector",
+                meta_type="generic",
                 **kwargs,
             )
         if distributions_array is not None:
@@ -500,6 +529,9 @@ class Datapackage(DatapackageBase):
                     group=name,
                     kind="distributions",
                     keep_proxy=keep_proxy,
+                    matrix_serialize_format_type=matrix_serialize_format_type,
+                    meta_object="vector",
+                    meta_type="distributions",
                     **kwargs,
                 )
         if flip_array is not None:
@@ -524,6 +556,9 @@ class Datapackage(DatapackageBase):
                     name=name + ".flip",
                     kind="flip",
                     keep_proxy=keep_proxy,
+                    matrix_serialize_format_type=matrix_serialize_format_type,
+                    meta_object="vector",
+                    meta_type="generic",
                     **kwargs,
                 )
 
@@ -536,6 +571,7 @@ class Datapackage(DatapackageBase):
         name: Optional[str] = None,
         flip_array: Optional[np.ndarray] = None,
         keep_proxy: bool = False,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
         **kwargs,
     ) -> None:
         """ """
@@ -553,6 +589,9 @@ class Datapackage(DatapackageBase):
             kind="indices",
             group=name,
             keep_proxy=keep_proxy,
+            matrix_serialize_format_type=matrix_serialize_format_type,
+            meta_object="vector",
+            meta_type="indices",
             **kwargs,
         )
 
@@ -575,6 +614,9 @@ class Datapackage(DatapackageBase):
             group=name,
             kind="data",
             keep_proxy=keep_proxy,
+            matrix_serialize_format_type=matrix_serialize_format_type,
+            meta_object="matrix",
+            meta_type="generic",
             **kwargs,
         )
         if flip_array is not None:
@@ -598,17 +640,63 @@ class Datapackage(DatapackageBase):
                     name=name + ".flip",
                     kind="flip",
                     keep_proxy=keep_proxy,
+                    matrix_serialize_format_type=matrix_serialize_format_type,
+                    meta_object="vector",
+                    meta_type="generic",
                     **kwargs,
                 )
 
     def write_modified(self):
         """Write the data in modified files to the filesystem (if allowed)."""
         for index in self._modified:
+            # get resource
+            resource = self.resources[index]
+            mediatype = resource["mediatype"]
+            path = resource["path"]
+            matrix_serialize_format_type = MatrixSerializeFormat.NUMPY  # by default
+            # only used for parquet format
+            meta_object = None
+            meta_type = None
+            if mediatype == "application/octet-stream":
+                format = resource.get("format", None)
+                if format == PARQUET_SERIALIZE_FORMAT_NAME:
+                    # parquet format
+                    matrix_serialize_format_type = MatrixSerializeFormat.PARQUET
+                    # try to guess object and type
+                    kind = resource["kind"]
+                    category = resource.get("category", None)
+                    if kind == "indices":
+                        meta_object = "vector"
+                        meta_type = "indices"
+                    elif kind == "flip":
+                        meta_object = "vector"
+                        meta_type = "generic"
+                    elif kind == "distributions":
+                        meta_object = "vector"
+                        meta_type = "distributions"
+                    elif kind == "data":
+                        meta_type = "generic"
+                        if category == "vector":
+                            meta_object = "vector"
+                        elif category == "array":
+                            meta_object = "matrix"
+                        else:
+                            raise NotImplementedError(
+                                f"Parquet format not available for resource with kind={kind} and category={category}!"
+                            )
+                    else:
+                        raise NotImplementedError(
+                            f"Parquet format not available for resource with kind={kind}!"
+                        )
+
             file_writer(
                 data=self.data[index],
                 fs=self.fs,
-                resource=self.resources[index]["path"],
-                mimetype=self.resources[index]["mediatype"],
+                resource=path,
+                mimetype=mediatype,
+                matrix_serialize_format_type=matrix_serialize_format_type,
+                meta_object=meta_object,
+                meta_type=meta_type,
             )
 
         self._modified = set()
@@ -621,9 +709,35 @@ class Datapackage(DatapackageBase):
         matrix: str,
         kind: str,
         keep_proxy: bool = False,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
+        meta_object: Optional[str] = None,
+        meta_type: Optional[str] = None,
         **kwargs,
     ) -> None:
-        filename = check_suffix(name, ".npy")
+        assert (
+            array.ndim <= 2
+        ), f"Numpy array should be of dim 2 or less instead of {array.ndim}!"
+
+        if matrix_serialize_format_type is None:
+            # use instance default serialization format
+            matrix_serialize_format_type = self._matrix_serialize_format_type
+        else:
+            assert isinstance(
+                matrix_serialize_format_type, MatrixSerializeFormat
+            ), f"Matrix serialization format {matrix_serialize_format_type} not recognized!"
+
+        filename = None
+        format = None
+        if matrix_serialize_format_type == MatrixSerializeFormat.NUMPY:
+            filename = check_suffix(name, NUMPY_SERIALIZE_FORMAT_EXTENSION)
+            format = NUMPY_SERIALIZE_FORMAT_NAME
+        elif matrix_serialize_format_type == MatrixSerializeFormat.PARQUET:
+            filename = check_suffix(name, PARQUET_SERIALIZE_FORMAT_EXTENSION)
+            format = PARQUET_SERIALIZE_FORMAT_NAME
+        else:
+            raise TypeError(
+                f"Matrix serialize format type {matrix_serialize_format_type} is not recognized!"
+            )
 
         if not isinstance(self.fs, MemoryFS):
             file_writer(
@@ -631,6 +745,9 @@ class Datapackage(DatapackageBase):
                 fs=self.fs,
                 resource=filename,
                 mimetype="application/octet-stream",
+                matrix_serialize_format_type=matrix_serialize_format_type,  # NIKO
+                meta_object=meta_object,
+                meta_type=meta_type,
             )
 
         if keep_proxy:
@@ -649,7 +766,7 @@ class Datapackage(DatapackageBase):
         resource = {
             # Datapackage generic
             "profile": "data-resource",
-            "format": "npy",
+            "format": format,
             "mediatype": "application/octet-stream",
             "name": name,
             # Brightway specific
@@ -669,6 +786,7 @@ class Datapackage(DatapackageBase):
         name: Optional[str] = None,
         flip_array: Optional[np.ndarray] = None,  # Not interface
         keep_proxy: bool = False,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
         **kwargs,
     ) -> None:
         self._prepare_modifications()
@@ -685,6 +803,9 @@ class Datapackage(DatapackageBase):
             group=name,
             kind="indices",
             keep_proxy=keep_proxy,
+            matrix_serialize_format_type=matrix_serialize_format_type,
+            meta_object="vector",
+            meta_type="indices",
             **kwargs,
         )
         if flip_array is not None:
@@ -708,6 +829,9 @@ class Datapackage(DatapackageBase):
                     name=name + ".flip",
                     kind="flip",
                     keep_proxy=keep_proxy,
+                    matrix_serialize_format_type=matrix_serialize_format_type,
+                    meta_object="vector",
+                    meta_type="generic",
                     **kwargs,
                 )
 
@@ -730,6 +854,7 @@ class Datapackage(DatapackageBase):
         name: Optional[str] = None,
         flip_array: Optional[np.ndarray] = None,
         keep_proxy: bool = False,
+        matrix_serialize_format_type: Optional[MatrixSerializeFormat] = None,
         **kwargs,
     ) -> None:
         """`interface` must support the presamples API."""
@@ -750,6 +875,9 @@ class Datapackage(DatapackageBase):
             group=name,
             kind="indices",
             keep_proxy=keep_proxy,
+            matrix_serialize_format_type=matrix_serialize_format_type,
+            meta_object="vector",
+            meta_type="indices",
             **kwargs,
         )
         if flip_array is not None:
@@ -773,6 +901,9 @@ class Datapackage(DatapackageBase):
                     name=name + ".flip",
                     kind="flip",
                     keep_proxy=keep_proxy,
+                    matrix_serialize_format_type=matrix_serialize_format_type,
+                    meta_object="vector",
+                    meta_type="generic",
                     **kwargs,
                 )
 
@@ -911,6 +1042,7 @@ def create_datapackage(
     seed: Optional[int] = None,
     sum_intra_duplicates: bool = True,
     sum_inter_duplicates: bool = False,
+    matrix_serialize_format_type: MatrixSerializeFormat = MatrixSerializeFormat.NUMPY,
 ) -> Datapackage:
     """Create a new data package.
 
@@ -921,16 +1053,16 @@ def create_datapackage(
     Licenses are specified as a list in ``metadata``. The default license is the `Open Data Commons Public Domain Dedication and License v1.0 <http://opendatacommons.org/licenses/pddl/>`__.
 
     Args:
-
-        * fs: A `Filesystem`, optional. A new `MemoryFS` is used if not provided.
-        * name: `str`, optional. A new uuid is used if not provided.
-        * id_. `str`, optional. A new uuid is used if not provided.
-        * metadata. `dict`, optional. Metadata dictionary following datapackage specification; see above.
-        * combinatorial. `bool`, default `False.: Policy on how to sample columns across multiple data arrays; see readme.
-        * sequential. `bool`, default `False.: Policy on how to sample columns in data arrays; see readme.
-        * seed. `int`, optional. Seed to use in random number generator.
-        * sum_intra_duplicates. `bool`, default `True`. Should duplicate elements in a single data resource be summed together, or should the last value replace previous values.
-        * sum_inter_duplicates. `bool`, default `False`. Should duplicate elements in across data resources be summed together, or should the last value replace previous values. Order of data resources is given by the order they are added to the data package.
+        * fs: A ``Filesystem``, optional. A new ``MemoryFS`` is used if not provided.
+        * name: ``str``, optional. A new uuid is used if not provided.
+        * `id_`: ``str``, optional. A new uuid is used if not provided.
+        * metadata: ``dict``, optional. Metadata dictionary following datapackage specification; see above.
+        * combinatorial: ``bool``, default ``False`` .: Policy on how to sample columns across multiple data arrays; see readme.
+        * sequential: ``bool``, default ``False`` .: Policy on how to sample columns in data arrays; see readme.
+        * seed: ``int``, optional. Seed to use in random number generator.
+        * sum_intra_duplicates: ``bool``, default ``True``. Should duplicate elements in a single data resource be summed together, or should the last value replace previous values.
+        * sum_inter_duplicates: ``bool``, default ``False``. Should duplicate elements in across data resources be summed together, or should the last value replace previous values. Order of data resources is given by the order they are added to the data package.
+        * matrix_serialize_format_type: ``MatrixSerializeFormat``, default ``MatrixSerializeFormat.NUMPY``. Matrix serialization format type.
 
     Returns:
 
@@ -948,6 +1080,7 @@ def create_datapackage(
         seed=seed,
         sum_intra_duplicates=sum_intra_duplicates,
         sum_inter_duplicates=sum_inter_duplicates,
+        matrix_serialize_format_type=matrix_serialize_format_type,
     )
     return obj
 
@@ -965,9 +1098,9 @@ def load_datapackage(
 
     Args:
 
-        * fs_or_obj. A `Filesystem` or an instance of `DatapackageBase`.
-        * mmap_mode. `str`, optional. Define memory mapping mode to use when loading Numpy arrays.
-        * proxy. bool, default `False`. Load proxies instead of complete Numpy arrays; see above.
+        * fs_or_obj: A `Filesystem` or an instance of `DatapackageBase`.
+        * mmap_mode: `str`, optional. Define memory mapping mode to use when loading Numpy arrays.
+        * proxy: bool, default `False`. Load proxies instead of complete Numpy arrays; see above.
 
     Returns:
 
@@ -982,27 +1115,36 @@ def load_datapackage(
     return obj
 
 
-def simple_graph(data: dict, fs: Optional[FS]=None, **metadata):
+def simple_graph(data: dict, fs: Optional[FS] = None, **metadata)->Datapackage:
     """Easy creation of simple datapackages with only persistent vectors.
 
-    ``data`` is a dictionary with the form:
+    Args:
+        * data: is a dictionary.
+            The data dictionary has the form::
 
-    ..code-block:: python
+                {
+                    matrix_name: [ 
+                    (row_id, col_id, value, flip) 
+                    ]
+                }
 
-        matrix_name (str): [
-            (row id (int), col id (int), value (float), flip (bool, default False))
-        ]
 
-    ``fs`` is a filesystem.
+            Where `row_id` and `col_id are an `int` s, value is a `float` and flip is a `bool`  (False by default).
 
-    ``metadata`` are passed as kwargs to ``create_datapackage()``.
+        * fs: is a filesystem.
+        * metadata: are passed as kwargs to ``create_datapackage()``.
 
-    Returns the datapackage."""
+    Returns:
+        the datapackage.
+
+    """
     dp = create_datapackage(fs=fs, **metadata)
     for key, value in data.items():
         indices_array = np.array([row[:2] for row in value], dtype=INDICES_DTYPE)
         data_array = np.array([row[2] for row in value])
-        flip_array = np.array([row[3] if len(row) > 3 else False for row in value], dtype=bool)
+        flip_array = np.array(
+            [row[3] if len(row) > 3 else False for row in value], dtype=bool
+        )
         dp.add_persistent_vector(
             matrix=key,
             data_array=data_array,