Auto-update pre-commit hooks

.github/workflows/ci.yml

@@ -25,33 +25,18 @@ jobs:
         os: ["ubuntu-latest"]
         pandas: [""]
         pyarrow: ["4.0.1", "nightly"]
-        python: ["3.8"]
+        python: ["3.10"]
         include:
           - numfocus_nightly: true
             os: "ubuntu-latest"
             pandas: ""
             pyarrow: "nightly"
             python: "3.10"
-          - numfocus_nightly: false
-            os: "ubuntu-latest"
-            pandas: "1.5.3"
-            pyarrow: "4.0.1"
-            python: "3.11"
           - numfocus_nightly: false
             os: "ubuntu-latest"
             pandas: "1.5.3"
             pyarrow: "13.0.0"
             python: "3.11"
-          - numfocus_nightly: false
-            os: "ubuntu-latest"
-            pandas: ""
-            pyarrow: "5.0.0"
-            python: "3.9"
-          - numfocus_nightly: false
-            os: "ubuntu-latest"
-            pandas: ""
-            pyarrow: "6.0.1"
-            python: "3.9"
           - numfocus_nightly: false
             os: "ubuntu-latest"
             pandas: ""
@@ -103,10 +88,10 @@ jobs:
             pyarrow: "15.0.0"
             python: "3.12"
           - numfocus_nightly: false
-            os: "macos-latest"
+            os: "ubuntu-latest"
             pandas: ""
-            pyarrow: "4.0.1"
-            python: "3.8"
+            pyarrow: "18.1.0"
+            python: "3.12"
     continue-on-error: ${{ matrix.numfocus_nightly || matrix.pyarrow == 'nightly' }}
 
     runs-on: ${{ matrix.os }}

.github/workflows/docs.yml

@@ -19,12 +19,12 @@ jobs:
       - name: Setup Conda Environment
         uses: conda-incubator/setup-miniconda@v3
         with:
-          miniforge-variant: Mambaforge
-          miniforge-version: 4.11.0-0
+          miniforge-variant: Miniforge3
+          miniforge-version: 24.9.2-0
           use-mamba: true
           environment-file: docs/environment-docs.yml
           activate-environment: plateau-docs
-          python-version: 3.8
+          python-version: 3.12
 
       - name: List conda
         shell: bash -l {0}

.pre-commit-config.yaml

@@ -1,12 +1,12 @@
 repos:
   # Run ruff first because autofix behaviour is enabled
   - repo: https://github.com/Quantco/pre-commit-mirrors-ruff
-    rev: "0.7.2"
+    rev: "0.8.0"
     hooks:
      - id: ruff-conda
      - id: ruff-format-conda
   - repo: https://github.com/Quantco/pre-commit-mirrors-mypy
-    rev: "1.10.1"
+    rev: "1.13.0"
     hooks:
       - id: mypy-conda
         files: plateau
@@ -17,16 +17,16 @@ repos:
           - types-decorator
           - types-simplejson
           - hypothesis
-          - numpy=1.26
+          - numpy=2.1.3
           - minimalkv=1.4.2
   - repo: https://github.com/Quantco/pre-commit-mirrors-pyupgrade
-    rev: 3.15.2
+    rev: 3.19.0
     hooks:
       - id: pyupgrade-conda
         args:
-          - --py38-plus
+          - --py310-plus
   - repo: https://github.com/Quantco/pre-commit-mirrors-prettier
-    rev: 3.2.5
+    rev: 3.4.1
     hooks:
       - id: prettier-conda
         files: "\\.md$"
@@ -35,7 +35,7 @@ repos:
     hooks:
       - id: docformatter-conda
   - repo: https://github.com/Quantco/pre-commit-mirrors-pre-commit-hooks
-    rev: 4.6.0
+    rev: 5.0.0
     hooks:
       - id: trailing-whitespace-conda
       - id: end-of-file-fixer-conda

docs/environment-docs.yml

@@ -7,7 +7,7 @@ dependencies:
   - decorator
   - msgpack-python>=0.5.2
   # Currently dask and numpy==1.16.0 clash
-  - numpy!=1.15.0,!=1.16.0
+  - numpy!=1.15.0,!=1.16.0,<2
   - pandas>=0.23.0,!=1.0.0
   - pyarrow>=4
   - simplejson

environment.yml

@@ -3,12 +3,14 @@ channels:
   - conda-forge
   - nodefaults
 dependencies:
+  - python>=3.10
+  - pip
   - dask>=2022.5.1 # First version with dask.dataframe.from_map.
   - decorator
   - msgpack-python>=0.5.2
   # Currently dask and numpy==1.16.0 clash
   # TODO: add support for numpy>=1.23
-  - numpy!=1.15.0,!=1.16.0
+  - numpy!=1.15.0,!=1.16.0,<2
   - pandas>=0.23.0,!=1.0.0
   - pyarrow>=4
   - simplejson

plateau/core/common_metadata.py

@@ -1,9 +1,10 @@
 import difflib
 import logging
 import pprint
+from collections.abc import Sequence
 from copy import copy, deepcopy
 from functools import reduce
-from typing import Any, Dict, List, Optional, Sequence, Set, Tuple, Union
+from typing import Any
 
 import pandas as pd
 import pyarrow as pa
@@ -37,7 +38,7 @@ class SchemaWrapper:
     """Wrapper object for pyarrow.Schema to handle forwards and backwards
     compatibility."""
 
-    def __init__(self, schema, origin: Union[str, Set[str]]):
+    def __init__(self, schema, origin: str | set[str]):
         if isinstance(origin, str):
             origin = {origin}
         elif isinstance(origin, set):
@@ -49,7 +50,7 @@ def __init__(self, schema, origin: Union[str, Set[str]]):
         self.__origin = origin
         self._schema_compat()
 
-    def with_origin(self, origin: Union[str, Set[str]]) -> "SchemaWrapper":
+    def with_origin(self, origin: str | set[str]) -> "SchemaWrapper":
         """Create new SchemaWrapper with given origin.
 
         Parameters
@@ -89,7 +90,7 @@ def internal(self):
         return self.__schema
 
     @property
-    def origin(self) -> Set[str]:
+    def origin(self) -> set[str]:
         return copy(self.__origin)
 
     def __repr__(self):
@@ -283,10 +284,10 @@ def make_meta(obj, origin, partition_keys=None):
 
 def normalize_type(
     t_pa: pa.DataType,
-    t_pd: Optional[str],
-    t_np: Optional[str],
-    metadata: Optional[Dict[str, Any]],
-) -> Tuple[pa.DataType, Optional[str], Optional[str], Optional[Dict[str, Any]]]:
+    t_pd: str | None,
+    t_np: str | None,
+    metadata: dict[str, Any] | None,
+) -> tuple[pa.DataType, str | None, str | None, dict[str, Any] | None]:
     """This will normalize types as followed:
 
     - all signed integers (``int8``, ``int16``, ``int32``, ``int64``) will be converted to ``int64``
@@ -415,7 +416,7 @@ def _pandas_in_schemas(schemas):
 
 def _determine_schemas_to_compare(
     schemas: Sequence[SchemaWrapper], ignore_pandas: bool
-) -> Tuple[Optional[SchemaWrapper], List[Tuple[SchemaWrapper, List[str]]]]:
+) -> tuple[SchemaWrapper | None, list[tuple[SchemaWrapper, list[str]]]]:
     """Iterate over a list of `pyarrow.Schema` objects and prepares them for
     comparison by picking a reference and determining all null columns.
 
@@ -436,7 +437,7 @@ def _determine_schemas_to_compare(
         must be removed before comparing the schemas
     """
     has_pandas = _pandas_in_schemas(schemas) and not ignore_pandas
-    schemas_to_evaluate: List[Tuple[SchemaWrapper, List[str]]] = []
+    schemas_to_evaluate: list[tuple[SchemaWrapper, list[str]]] = []
     reference = None
     null_cols_in_reference = set()
 
@@ -695,7 +696,7 @@ def validate_shared_columns(schemas, ignore_pandas=False):
     ValueError
         Incompatible columns were found.
     """
-    seen: Dict[str, Any] = {}
+    seen: dict[str, Any] = {}
     has_pandas = _pandas_in_schemas(schemas) and not ignore_pandas
 
     for schema in schemas: