bw-processing 0.9__tar.gz → 0.9.6__tar.gz

bw_processing-0.9.6/MANIFEST.in

@@ -0,0 +1,3 @@
+include bw_processing/examples/*.zip
+include bw_processing/examples/datapackage_1/*.parquet
+recursive-exclude dev *

{bw-processing-0.9/bw_processing.egg-info → bw_processing-0.9.6}/PKG-INFO

@@ -1,43 +1,43 @@
 Metadata-Version: 2.1
-Name: bw-processing
-Version: 0.9
-Summary: Tools to create structured arrays in a common format
-Home-page: https://github.com/brightway-lca/bw_processing
-Author: Chris Mutel
-Author-email: <cmutel@gmail.com>
-Maintainer: Chris Mutel
-Maintainer-email: <cmutel@gmail.com>
-License: BSD-3-Clause
+Name: bw_processing
+Version: 0.9.6
+Summary: Foo
+Author-email: Chris Mutel <cmutel@gmail.com>
+Maintainer-email: Chris Mutel <cmutel@gmail.com>
 Project-URL: source, https://github.com/brightway-lca/bw_processing
 Project-URL: homepage, https://github.com/brightway-lca/bw_processing
 Project-URL: tracker, https://github.com/brightway-lca/bw_processing/issues
-Keywords: "brightway","development"
-Platform: any
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown; charset=UTF-8
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: fs
+Requires-Dist: fsspec
+Requires-Dist: morefs
 Requires-Dist: numpy
 Requires-Dist: pandas
 Provides-Extra: testing
-Requires-Dist: setuptools; extra == "testing"
+Requires-Dist: bw_processing; extra == "testing"
+Requires-Dist: pyarrow; extra == "testing"
 Requires-Dist: pytest; extra == "testing"
 Requires-Dist: pytest-cov; extra == "testing"
-Requires-Dist: pyarrow; extra == "testing"
+Requires-Dist: python-coveralls; extra == "testing"
 Provides-Extra: dev
+Requires-Dist: build; extra == "dev"
 Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: pylint; extra == "dev"
-Provides-Extra: docs
-Requires-Dist: sphinx; extra == "docs"
-Requires-Dist: myst_parser; extra == "docs"
-Requires-Dist: furo; extra == "docs"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-randomly; extra == "dev"
+Requires-Dist: setuptools; extra == "dev"
 
 # bw-processing
 
@@ -46,10 +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]
@@ -57,7 +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
@@ -148,10 +148,10 @@ class ExampleArrayInterface:
 Serialized datapackages cannot contain executable code, both because of our chosen data formats, and for security reasons. Therefore, when loading a datapackage with an interface, that interface object needs to be reconstituted as Python code - we call this cycle dehydration and rehydration. Dehydration happens automatically when a datapackage is finalized with `finalize_serialization()`, but rehydration needs to be done manually using `rehydrate_interface()`. For example:
 
 ```python
-from fs.zipfs import ZipFS
+from fsspec.implementations.zip import ZipFileSystem
 from bw_processing import load_datapackage
 
-my_dp = load_datapackage(ZipFS("some-path.zip"))
+my_dp = load_datapackage(ZipFileSystem("some-path.zip"))
 my_dp.rehydrate_interface("some-resource-name", ExampleVectorInterface())
 ```
 
@@ -160,7 +160,7 @@ You can list the dehydrated interfaces present with `.dehydrated_interfaces()`.
 You can store useful information for the interface object initialization under the resource key `config`. This can be used in instantiating an interface if you pass `initialize_with_config`:
 
 ```python
-from fs.zipfs import ZipFS
+from fsspec.implementations.zip import ZipFileSystem
 from bw_processing import load_datapackage
 import requests
 import numpy as np
@@ -174,7 +174,7 @@ class MyInterface:
         return np.array(requests.get(self.url).json())
 
 
-my_dp = load_datapackage(ZipFS("some-path.zip"))
+my_dp = load_datapackage(ZipFileSystem("some-path.zip"))
 data_obj, resource_metadata = my_dp.get_resource("some-interface")
 print(resource_metadata['config'])
 >>> {"url": "example.com"}

{bw-processing-0.9 → bw_processing-0.9.6}/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
@@ -107,10 +107,10 @@ class ExampleArrayInterface:
 Serialized datapackages cannot contain executable code, both because of our chosen data formats, and for security reasons. Therefore, when loading a datapackage with an interface, that interface object needs to be reconstituted as Python code - we call this cycle dehydration and rehydration. Dehydration happens automatically when a datapackage is finalized with `finalize_serialization()`, but rehydration needs to be done manually using `rehydrate_interface()`. For example:
 
 ```python
-from fs.zipfs import ZipFS
+from fsspec.implementations.zip import ZipFileSystem
 from bw_processing import load_datapackage
 
-my_dp = load_datapackage(ZipFS("some-path.zip"))
+my_dp = load_datapackage(ZipFileSystem("some-path.zip"))
 my_dp.rehydrate_interface("some-resource-name", ExampleVectorInterface())
 ```
 
@@ -119,7 +119,7 @@ You can list the dehydrated interfaces present with `.dehydrated_interfaces()`.
 You can store useful information for the interface object initialization under the resource key `config`. This can be used in instantiating an interface if you pass `initialize_with_config`:
 
 ```python
-from fs.zipfs import ZipFS
+from fsspec.implementations.zip import ZipFileSystem
 from bw_processing import load_datapackage
 import requests
 import numpy as np
@@ -133,7 +133,7 @@ class MyInterface:
         return np.array(requests.get(self.url).json())
 
 
-my_dp = load_datapackage(ZipFS("some-path.zip"))
+my_dp = load_datapackage(ZipFileSystem("some-path.zip"))
 data_obj, resource_metadata = my_dp.get_resource("some-interface")
 print(resource_metadata['config'])
 >>> {"url": "example.com"}

{bw-processing-0.9 → bw_processing-0.9.6}/bw_processing/__init__.py

@@ -26,16 +26,11 @@ __all__ = (
     "UndefinedInterface",
 )
 
-__version__ = "0.9"
+__version__ = "0.9.6"
 
 
 from .array_creation import create_array, create_structured_array
-from .constants import (
-    DEFAULT_LICENSES,
-    INDICES_DTYPE,
-    UNCERTAINTY_DTYPE,
-    MatrixSerializeFormat,
-)
+from .constants import DEFAULT_LICENSES, INDICES_DTYPE, UNCERTAINTY_DTYPE, MatrixSerializeFormat
 from .datapackage import (
     Datapackage,
     DatapackageBase,

{bw-processing-0.9 → bw_processing-0.9.6}/bw_processing/array_creation.py

@@ -68,7 +68,8 @@ def create_structured_array(iterable, dtype, nrows=None, sort=False, sort_fields
 
     ``iterable`` can be data already in memory, or a generator.
 
-    ``nrows`` can be supplied, if known. If ``iterable`` has a length, it will be determined automatically. If ``nrows`` is not known, this function generates chunked arrays until ``iterable`` is exhausted, and concatenates them."""
+    ``nrows`` can be supplied, if known. If ``iterable`` has a length, it will be determined automatically. If ``nrows`` is not known, this function generates chunked arrays until ``iterable`` is exhausted, and concatenates them.
+    """
     if nrows or hasattr(iterable, "__len__"):
         if not nrows:
             nrows = len(iterable)

{bw-processing-0.9 → bw_processing-0.9.6}/bw_processing/datapackage.py

@@ -6,9 +6,10 @@ from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd
-from fs.base import FS
-from fs.errors import ResourceNotFound
-from fs.memoryfs import MemoryFS
+from fsspec import AbstractFileSystem
+
+# Use this instead of fsspec MemoryFileSystem because that is a singleton!?
+from morefs.dict import DictFS
 
 from .constants import (
     DEFAULT_LICENSES,
@@ -31,7 +32,7 @@ from .errors import (
 from .filesystem import clean_datapackage_name
 from .io_helpers import file_reader, file_writer
 from .proxies import Proxy, UndefinedInterface
-from .utils import check_name, check_suffix, load_bytes, resolve_dict_iterator
+from .utils import check_name, check_suffix, load_bytes, resolve_dict_iterator, utc_now
 
 
 class DatapackageBase(ABC):
@@ -109,15 +110,13 @@ class DatapackageBase(ABC):
     def del_resource(self, name_or_index: Union[str, int]) -> None:
         """Remove a resource, and delete its data file, if any."""
         if self._modified:
-            raise PotentialInconsistency(
-                "Datapackage is modified; save modifications or reload"
-            )
+            raise PotentialInconsistency("Datapackage is modified; save modifications or reload")
 
         index = self._get_index(name_or_index)
 
         try:
-            self.fs.remove(self.resources[index]["path"])
-        except (KeyError, ResourceNotFound):
+            self.fs.rm(self.resources[index]["path"])
+        except (KeyError, FileNotFoundError):
             # Interface has no path
             pass
 
@@ -127,28 +126,21 @@ class DatapackageBase(ABC):
     def del_resource_group(self, name: str) -> None:
         """Remove a resource group, and delete its data files, if any.
 
-        Use ``exclude_resource_group`` if you want to keep the underlying resource in the filesystem."""
+        Use ``exclude_resource_group`` if you want to keep the underlying resource in the filesystem.
+        """
         if self._modified:
-            raise PotentialInconsistency(
-                "Datapackage is modified; save modifications or reload"
-            )
+            raise PotentialInconsistency("Datapackage is modified; save modifications or reload")
 
-        indices = [
-            i
-            for i, resource in enumerate(self.resources)
-            if resource.get("group") == name
-        ]
+        indices = [i for i, resource in enumerate(self.resources) if resource.get("group") == name]
 
         for obj in (obj for i, obj in enumerate(self.resources) if i in indices):
             try:
-                self.fs.remove(obj["path"])
-            except (KeyError, ResourceNotFound):
+                self.fs.rm(obj["path"])
+            except (KeyError, FileNotFoundError):
                 # Interface has no path
                 pass
 
-        self.resources = [
-            obj for i, obj in enumerate(self.resources) if i not in indices
-        ]
+        self.resources = [obj for i, obj in enumerate(self.resources) if i not in indices]
         self.data = [obj for i, obj in enumerate(self.data) if i not in indices]
 
     def get_resource(self, name_or_index: Union[str, int]) -> (Any, dict):
@@ -181,14 +173,13 @@ class DatapackageBase(ABC):
 
         All included objects are the same as in the original data package, i.e. no copies are made. No checks are made to ensure consistency with modifications to the original datapackage after the creation of this filtered datapackage.
 
-        This method was introduced to allow for the efficient construction of matrices; each datapackage can have data for multiple matrices, and we can then create filtered datapackages which exclusively have data for the matrix of interest. As such, they should be considered read-only, though this is not enforced."""
+        This method was introduced to allow for the efficient construction of matrices; each datapackage can have data for multiple matrices, and we can then create filtered datapackages which exclusively have data for the matrix of interest. As such, they should be considered read-only, though this is not enforced.
+        """
         fdp = FilteredDatapackage()
         fdp.fs = self.fs
         fdp.metadata = {k: v for k, v in self.metadata.items() if k != "resources"}
         fdp.metadata["resources"] = []
-        to_include = [
-            i for i, resource in enumerate(self.resources) if resource.get(key) == value
-        ]
+        to_include = [i for i, resource in enumerate(self.resources) if resource.get(key) == value]
         fdp.data = [o for i, o in enumerate(self.data) if i in to_include]
         fdp.resources = [o for i, o in enumerate(self.resources) if i in to_include]
         if hasattr(self, "indexer"):
@@ -223,17 +214,13 @@ class DatapackageBase(ABC):
             if any(resource.get(key) != value for key, value in filters.items())
         ]
         fdp.data = [o for i, o in enumerate(self.data) if i in indices_to_include]
-        fdp.resources = [
-            o for i, o in enumerate(self.resources) if i in indices_to_include
-        ]
+        fdp.resources = [o for i, o in enumerate(self.resources) if i in indices_to_include]
         return fdp
 
     def _dehydrate_interfaces(self) -> None:
         """Substitute an interface resource with ``UndefinedInterface``, in preparation for finalizing data on disk."""
         interface_indices = [
-            index
-            for index, obj in enumerate(self.resources)
-            if obj["profile"] == "interface"
+            index for index, obj in enumerate(self.resources) if obj["profile"] == "interface"
         ]
 
         for index in interface_indices:
@@ -299,7 +286,7 @@ class Datapackage(DatapackageBase):
         return hash((self.fs, self.metadata))
 
     def __eq__(self, other):
-        return (self.fs, self.metadata) == (other.fs, other.metadata)
+        return (id(self.fs), self.metadata) == (id(other.fs), other.metadata)
 
     def _check_length_consistency(self) -> None:
         if len(self.resources) != len(self.data):
@@ -310,7 +297,7 @@ class Datapackage(DatapackageBase):
             )
 
     def _load(
-        self, fs: FS, mmap_mode: Optional[str] = None, proxy: bool = False
+        self, fs: AbstractFileSystem, mmap_mode: Optional[str] = None, proxy: bool = False
     ) -> None:
         self.fs = fs
         self.metadata = file_reader(
@@ -336,7 +323,7 @@ class Datapackage(DatapackageBase):
 
     def _create(
         self,
-        fs: Optional[FS],
+        fs: Optional[AbstractFileSystem],
         name: Optional[str],
         id_: Optional[str],
         metadata: Optional[dict],
@@ -356,7 +343,7 @@ class Datapackage(DatapackageBase):
         name = clean_datapackage_name(name or uuid.uuid4().hex)
         check_name(name)
 
-        self.fs = fs or MemoryFS()
+        self.fs = fs or DictFS()
         if not isinstance(matrix_serialize_format_type, MatrixSerializeFormat):
             raise TypeError(
                 f"Matrix serialize format type ({matrix_serialize_format_type}) not recognized!"
@@ -369,7 +356,7 @@ 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": utc_now().isoformat("T") + "Z",
             "combinatorial": combinatorial,
             "sequential": sequential,
             "seed": seed,
@@ -386,7 +373,7 @@ class Datapackage(DatapackageBase):
     def finalize_serialization(self) -> None:
         if self._finalized:
             raise Closed("Datapackage already finalized")
-        elif isinstance(self.fs, MemoryFS):
+        elif isinstance(self.fs, DictFS):
             raise ValueError("In-memory file systems can't be serialized")
 
         self._dehydrate_interfaces()
@@ -398,7 +385,8 @@ class Datapackage(DatapackageBase):
             resource="datapackage.json",
             mimetype="application/json",
         )
-        self.fs.close()
+        if hasattr(self.fs, "close"):
+            self.fs.close()
         self._finalized = True
 
     def _prepare_modifications(self) -> None:
@@ -469,9 +457,7 @@ class Datapackage(DatapackageBase):
 
         # Check lengths
 
-        kwargs.update(
-            {"matrix": matrix, "category": "vector", "nrows": len(indices_array)}
-        )
+        kwargs.update({"matrix": matrix, "category": "vector", "nrows": len(indices_array)})
         name = self._prepare_name(name)
 
         indices_array = load_bytes(indices_array)
@@ -514,9 +500,7 @@ class Datapackage(DatapackageBase):
         if distributions_array is not None:
             distributions_array = load_bytes(distributions_array)
             # If no uncertainty, don't need to store it
-            if (distributions_array["uncertainty_type"] < 2).sum() < len(
-                distributions_array
-            ):
+            if (distributions_array["uncertainty_type"] < 2).sum() < len(distributions_array):
                 if distributions_array.shape != indices_array.shape:
                     raise ShapeMismatch(
                         "`distributions_array` shape ({}) doesn't match `indices_array` ({}).".format(
@@ -540,9 +524,7 @@ class Datapackage(DatapackageBase):
             if flip_array.sum():
                 if flip_array.dtype != bool:
                     raise WrongDatatype(
-                        "`flip_array` dtype is {}, but must be `bool`".format(
-                            flip_array.dtype
-                        )
+                        "`flip_array` dtype is {}, but must be `bool`".format(flip_array.dtype)
                     )
                 elif flip_array.shape != indices_array.shape:
                     raise ShapeMismatch(
@@ -577,9 +559,7 @@ class Datapackage(DatapackageBase):
         """ """
         self._prepare_modifications()
 
-        kwargs.update(
-            {"matrix": matrix, "category": "array", "nrows": len(indices_array)}
-        )
+        kwargs.update({"matrix": matrix, "category": "array", "nrows": len(indices_array)})
         name = self._prepare_name(name)
 
         indices_array = load_bytes(indices_array)
@@ -624,9 +604,7 @@ class Datapackage(DatapackageBase):
             if flip_array.sum():
                 if flip_array.dtype != bool:
                     raise WrongDatatype(
-                        "`flip_array` dtype is {}, but must be `bool`".format(
-                            flip_array.dtype
-                        )
+                        "`flip_array` dtype is {}, but must be `bool`".format(flip_array.dtype)
                     )
                 elif flip_array.shape != indices_array.shape:
                     raise ShapeMismatch(
@@ -714,9 +692,7 @@ class Datapackage(DatapackageBase):
         meta_type: Optional[str] = None,
         **kwargs,
     ) -> None:
-        assert (
-            array.ndim <= 2
-        ), f"Numpy array should be of dim 2 or less instead of {array.ndim}!"
+        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
@@ -739,13 +715,13 @@ class Datapackage(DatapackageBase):
                 f"Matrix serialize format type {matrix_serialize_format_type} is not recognized!"
             )
 
-        if not isinstance(self.fs, MemoryFS):
+        if not isinstance(self.fs, DictFS):
             file_writer(
                 data=array,
                 fs=self.fs,
                 resource=filename,
                 mimetype="application/octet-stream",
-                matrix_serialize_format_type=matrix_serialize_format_type,  # NIKO
+                matrix_serialize_format_type=matrix_serialize_format_type,
                 meta_object=meta_object,
                 meta_type=meta_type,
             )
@@ -791,9 +767,7 @@ class Datapackage(DatapackageBase):
     ) -> None:
         self._prepare_modifications()
 
-        kwargs.update(
-            {"matrix": matrix, "category": "vector", "nrows": len(indices_array)}
-        )
+        kwargs.update({"matrix": matrix, "category": "vector", "nrows": len(indices_array)})
         name = self._prepare_name(name)
 
         indices_array = load_bytes(indices_array)
@@ -813,9 +787,7 @@ class Datapackage(DatapackageBase):
             if flip_array.sum():
                 if flip_array.dtype != bool:
                     raise WrongDatatype(
-                        "`flip_array` dtype is {}, but must be `bool`".format(
-                            flip_array.dtype
-                        )
+                        "`flip_array` dtype is {}, but must be `bool`".format(flip_array.dtype)
                     )
                 elif flip_array.shape != indices_array.shape:
                     raise ShapeMismatch(
@@ -863,9 +835,7 @@ class Datapackage(DatapackageBase):
         if isinstance(flip_array, np.ndarray) and not flip_array.sum():
             flip_array = None
 
-        kwargs.update(
-            {"matrix": matrix, "category": "array", "nrows": len(indices_array)}
-        )
+        kwargs.update({"matrix": matrix, "category": "array", "nrows": len(indices_array)})
         name = self._prepare_name(name)
 
         indices_array = load_bytes(indices_array)
@@ -885,9 +855,7 @@ class Datapackage(DatapackageBase):
             if flip_array.sum():
                 if flip_array.dtype != bool:
                     raise WrongDatatype(
-                        "`flip_array` dtype is {}, but must be `bool`".format(
-                            flip_array.dtype
-                        )
+                        "`flip_array` dtype is {}, but must be `bool`".format(flip_array.dtype)
                     )
                 elif flip_array.shape != indices_array.shape:
                     raise ShapeMismatch(
@@ -975,9 +943,7 @@ class Datapackage(DatapackageBase):
         )
         self.resources.append(kwargs)
 
-    def add_json_metadata(
-        self, *, data: Any, valid_for: str, name: str = None, **kwargs
-    ) -> None:
+    def add_json_metadata(self, *, data: Any, valid_for: str, name: str = None, **kwargs) -> None:
         """Add an iterable metadata object to be stored as a JSON file.
 
         The purpose of storing metadata is to enable data exchange; therefore, this method assumes that data is written to disk.
@@ -1013,9 +979,7 @@ class Datapackage(DatapackageBase):
 
         filename = check_suffix(name, ".json")
 
-        file_writer(
-            data=data, fs=self.fs, resource=filename, mimetype="application/json"
-        )
+        file_writer(data=data, fs=self.fs, resource=filename, mimetype="application/json")
         self.data.append(data)
 
         kwargs.update(
@@ -1033,7 +997,7 @@ class Datapackage(DatapackageBase):
 
 
 def create_datapackage(
-    fs: Optional[FS] = None,
+    fs: Optional[AbstractFileSystem] = None,
     name: Optional[str] = None,
     id_: Optional[str] = None,
     metadata: Optional[dict] = None,
@@ -1046,24 +1010,23 @@ def create_datapackage(
 ) -> Datapackage:
     """Create a new data package.
 
-    All arguments are optional; if a `PyFilesystem2 <https://docs.pyfilesystem.org/en/latest/>`__ filesystem is not provided, a `MemoryFS <https://docs.pyfilesystem.org/en/latest/reference/memoryfs.html>`__ will be used.
+    All arguments are optional; if a `fsspec <https://filesystem-spec.readthedocs.io/en/latest/>`__ filesystem is not provided, an in-memory `DictFS <https://github.com/iterative/morefs?tab=readme-ov-file#dictfs>`__ will be used.
 
     All metadata elements should follow the `datapackage specification <https://frictionlessdata.io/specs/data-package/>`__.
 
     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.
-        * matrix_serialize_format_type. `MatrixSerializeFormat`, default `MatrixSerializeFormat.NUMPY`. Matrix serialization format type.
+        * fs: A ``Filesystem``, optional. A new ``DictFS`` 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:
 
@@ -1087,7 +1050,7 @@ def create_datapackage(
 
 
 def load_datapackage(
-    fs_or_obj: Union[DatapackageBase, FS],
+    fs_or_obj: Union[DatapackageBase, AbstractFileSystem],
     mmap_mode: Optional[str] = None,
     proxy: bool = False,
 ) -> Datapackage:
@@ -1099,9 +1062,9 @@ 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:
 
@@ -1116,29 +1079,34 @@ def load_datapackage(
     return obj
 
 
-def simple_graph(data: dict, fs: Optional[FS] = None, **metadata):
+def simple_graph(data: dict, fs: Optional[AbstractFileSystem] = 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."""
-    dp = create_datapackage(fs=fs, **metadata)
+    Returns:
+        the datapackage.
+
+    """
+    dp = create_datapackage(fs=fs or DictFS(), **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,

{bw-processing-0.9 → bw_processing-0.9.6}/bw_processing/errors.py

@@ -29,7 +29,8 @@ class ShapeMismatch(BrightwayProcessingError):
 class InvalidName(BrightwayProcessingError):
     """Name fails datapackage requirements:
 
-    A short url-usable (and preferably human-readable) name of the package. This MUST be lower-case and contain only alphanumeric characters along with ".", "_" or "-" characters."""
+    A short url-usable (and preferably human-readable) name of the package. This MUST be lower-case and contain only alphanumeric characters along with ".", "_" or "-" characters.
+    """
 
     pass