matrix-utils 0.4.2__tar.gz → 0.5__tar.gz

{matrix_utils-0.4.2 → matrix_utils-0.5}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+### [0.5] - 2024-08-20
+
+* Default is not 64 bit integers for indexing; compatible with `bw_processing` 1.0
+
+### [0.4.3] - 2024-06-04
+
+* Allow `MappedMatrixDict` to take extra `kwargs` for compatiblity with custom matrix classes
+
 ### [0.4.2] - 2024-06-04
 
 * Fix diagonal `MappedMatrixDict` - `col_mapper` is not required

{matrix_utils-0.4.2 → matrix_utils-0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: matrix_utils
-Version: 0.4.2
+Version: 0.5
 Summary: Tools to create matrices from data packages
 Author-email: Chris Mutel <cmutel@gmail.com>
 Maintainer-email: Chris Mutel <cmutel@gmail.com>
@@ -26,9 +26,9 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy
-Requires-Dist: scipy
+Requires-Dist: scipy>=1.10
 Requires-Dist: pandas
-Requires-Dist: bw_processing
+Requires-Dist: bw_processing>=1.0
 Requires-Dist: stats_arrays
 Provides-Extra: testing
 Requires-Dist: matrix_utils; extra == "testing"

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils/__init__.py

@@ -11,7 +11,7 @@ __all__ = (
     "SparseMatrixDict",
 )
 
-__version__ = "0.4.2"
+__version__ = "0.5"
 
 from .array_mapper import ArrayMapper
 from .indexers import CombinatorialIndexer, Proxy, RandomIndexer, SequentialIndexer

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils/indexers.py

@@ -1,10 +1,12 @@
 from itertools import product
 from typing import List, Union
 
+from numpy import int32, int64
 from numpy.random import PCG64, Generator
 
 # Max signed 32 bit integer, compatible with Windows
 MAX_SIGNED_32BIT_INT = 2147483647
+MAX_SIGNED_64BIT_INT = 9223372036854775807
 
 
 class Indexer:
@@ -18,15 +20,21 @@ class RandomIndexer(Generator, Indexer):
 
     Returns indices for a sample array.
 
+    Because we are creating Python indices, and Python starts indices with zero, the value
+    `max_value` is never reached - the maximum generated index is `max_value - 1`.
+
     max_value: Number of columns in the array for which a column index is returned.
     seed: Seed for RNG. Optional."""
 
-    def __init__(self, seed: Union[int, None] = None):
+    def __init__(self, seed: Union[int, None] = None, max_value: int = MAX_SIGNED_64BIT_INT):
         self.seed = seed
+        self.max_value = max_value
         self.reset()
 
     def __next__(self):
-        self.index = self.integers(0, MAX_SIGNED_32BIT_INT)
+        self.index = self.integers(
+            0, self.max_value, dtype=int32 if self.max_value == MAX_SIGNED_32BIT_INT else int64
+        )
         return self.index
 
     def reset(self):

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils/mapped_matrix.py

@@ -178,6 +178,9 @@ class MappedMatrix:
             self.rebuild_matrix()
 
     def rebuild_matrix(self) -> None:
+        # In theory, setting this to zero instead of multiplying it would
+        # save some nanoseconds, but it led to weird Numpy dtype errors and
+        # wasn't worth thinking about too much for very little gain.
         self.matrix.data *= 0
         for group in self.groups:
             row, col, data = group.calculate()
@@ -211,7 +214,10 @@ class MappedMatrix:
                 for obj in resources:
                     obj.add_indexer(indexer=package.indexer)
             else:
-                package.indexer = RandomIndexer(seed=seed_override or package.metadata["seed"])
+                package.indexer = RandomIndexer(
+                    seed=seed_override or package.metadata["seed"],
+                    max_value=package.get_max_index_value(),
+                )
                 for obj in resources:
                     obj.add_indexer(indexer=package.indexer)
 
@@ -270,7 +276,7 @@ class MappedMatrix:
 
         array = np.zeros(len(given), dtype=UNCERTAINTY_DTYPE)
         for field in FIELDS:
-            array[field] = np.NaN
+            array[field] = np.nan
         array["loc"] = given
         array["uncertainty_type"] = uncertainty_type
         return array

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils/mapped_matrix_dict.py

@@ -26,7 +26,7 @@ class SparseMatrixDict(dict):
             return SparseMatrixDict(
                 {unroll(a, b): c @ d.matrix for a, c in self.items() for b, d in other.items()}
             )
-        elif sparse.base.issparse(other):
+        elif sparse.issparse(other):
             return SparseMatrixDict({a: b @ other for a, b in self.items()})
         else:
             raise TypeError(f"Can't understand matrix multiplication for type {type(other)}")
@@ -51,6 +51,7 @@ class MappedMatrixDict(Mapping):
         empty_ok: bool = False,
         sequential: bool = False,
         matrix_class: Type[MappedMatrix] = MappedMatrix,
+        **kwargs,
     ):
         """A thin wrapper around a dict of `MappedMatrix` objects. See its docstring
         for details on `custom_filter` and `indexer_override`.
@@ -143,6 +144,7 @@ class MappedMatrixDict(Mapping):
                 transpose=transpose,
                 custom_filter=custom_filter,
                 empty_ok=empty_ok,
+                **kwargs,
             )
             for key, packages in packages.items()
         }
@@ -178,7 +180,7 @@ class MappedMatrixDict(Mapping):
 
         Note that the mapped matrix dict must come first, i.e. `MappedMatrixDict @ other`.
         """
-        if sparse.base.issparse(other):
+        if sparse.issparse(other):
             return SparseMatrixDict(
                 [(key, value.matrix @ other) for key, value in self.matrices.items()]
             )

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils/resource_group.py

@@ -120,7 +120,9 @@ class ResourceGroup:
         """The source data for the indices array."""
         indices = self.get_resource_by_suffix("indices")
         if self.transpose:
-            indices = indices.astype([("col", np.int32), ("row", np.int32)], copy=False)
+            indices = indices.astype(
+                [("col", indices.dtype[0]), ("row", indices.dtype[0])], copy=False
+            )
         return indices
 
     def get_resource_by_suffix(self, suffix: str) -> Any:

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: matrix_utils
-Version: 0.4.2
+Version: 0.5
 Summary: Tools to create matrices from data packages
 Author-email: Chris Mutel <cmutel@gmail.com>
 Maintainer-email: Chris Mutel <cmutel@gmail.com>
@@ -26,9 +26,9 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy
-Requires-Dist: scipy
+Requires-Dist: scipy>=1.10
 Requires-Dist: pandas
-Requires-Dist: bw_processing
+Requires-Dist: bw_processing>=1.0
 Requires-Dist: stats_arrays
 Provides-Extra: testing
 Requires-Dist: matrix_utils; extra == "testing"

matrix_utils-0.5/matrix_utils.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+CHANGELOG.md
+CODE_OF_CONDUCT.md
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+matrix_utils/__init__.py
+matrix_utils/aggregation.py
+matrix_utils/array_mapper.py
+matrix_utils/errors.py
+matrix_utils/indexers.py
+matrix_utils/mapped_matrix.py
+matrix_utils/mapped_matrix_dict.py
+matrix_utils/resource_group.py
+matrix_utils/utils.py
+matrix_utils.egg-info/PKG-INFO
+matrix_utils.egg-info/SOURCES.txt
+matrix_utils.egg-info/dependency_links.txt
+matrix_utils.egg-info/requires.txt
+matrix_utils.egg-info/top_level.txt

{matrix_utils-0.4.2 → matrix_utils-0.5}/matrix_utils.egg-info/requires.txt

@@ -1,7 +1,7 @@
 numpy
-scipy
+scipy>=1.10
 pandas
-bw_processing
+bw_processing>=1.0
 stats_arrays
 
 [dev]

{matrix_utils-0.4.2 → matrix_utils-0.5}/pyproject.toml

@@ -37,9 +37,9 @@ dependencies = [
     # dependencies as strings with quotes, e.g. "foo"
     # You can add version requirements like "foo>2.0"
     "numpy",
-    "scipy",
+    "scipy>=1.10",
     "pandas",
-    "bw_processing",
+    "bw_processing>=1.0",
     "stats_arrays",
 ]
 

matrix_utils-0.4.2/.gitignore

@@ -1,104 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# pyenv
-.python-version
-
-# celery beat schedule file
-celerybeat-schedule
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/

matrix_utils-0.4.2/.pre-commit-config.yaml

@@ -1,53 +0,0 @@
-exclude: '^docs/conf.py'
-
-repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.4.0
-  hooks:
-  - id: trailing-whitespace
-  - id: check-added-large-files
-  - id: check-ast
-  - id: check-json
-  - id: check-merge-conflict
-  - id: check-xml
-  - id: check-yaml
-  - id: debug-statements
-  - id: end-of-file-fixer
-  - id: requirements-txt-fixer
-  - id: mixed-line-ending
-    args: ['--fix=auto']  # replace 'auto' with 'lf' to enforce Linux/Mac line endings or 'crlf' for Windows
-
-## If you want to avoid flake8 errors due to unused vars or imports:
-# - repo: https://github.com/myint/autoflake
-#   rev: v1.4
-#   hooks:
-#   - id: autoflake
-#     args: [
-#       --in-place,
-#       --remove-all-unused-imports,
-#       --remove-unused-variables,
-#     ]
-
-- repo: https://github.com/pycqa/isort
-  rev: 5.11.5
-  hooks:
-  - id: isort
-    args: [--settings-path=pyproject.toml]
-
-- repo: https://github.com/psf/black
-  rev: 23.10.0
-  hooks:
-  - id: black
-    args: [--config=pyproject.toml]
-
-# - repo: https://github.com/adamchainz/blacken-docs
-#   rev: 1.16.0
-#   hooks:
-#   - id: blacken-docs
-#     additional_dependencies: [black]
-
-- repo: https://github.com/PyCQA/flake8
-  rev: 6.0.0
-  hooks:
-  - id: flake8
-    additional_dependencies: [Flake8-pyproject]