Packaging updates (#986)

* Packaging updates

- Use pyproject.toml, hatch, hatch-vcs
- Use ruff

Closes #984

* restore env

* ignore _version

Author: TomAugspurger

.gitignore

@@ -125,3 +125,5 @@ docs/source/auto_examples/
 docs/source/examples/mydask.png
 
 dask-worker-space
+.direnv
+dask_ml/_version.py

.pre-commit-config.yaml

@@ -1,19 +1,10 @@
 repos:
--   repo: https://github.com/psf/black
-    rev: 23.12.1
-    hooks:
-    - id: black
-      language_version: python3
-      args:
-          - --target-version=py39
--   repo: https://github.com/pycqa/flake8
-    rev: 7.0.0
-    hooks:
-    - id: flake8
-      language_version: python3
-      args: ["--ignore=E501,W503,E203,E741,E731"]
--   repo: https://github.com/pycqa/isort
-    rev: 5.13.2
-    hooks:
-    - id: isort
-      language_version: python3
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.3.4
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format

dask_ml/__init__.py

@@ -1,18 +1,6 @@
-from pkg_resources import DistributionNotFound, get_distribution
-
 # Ensure we always register tokenizers
-from dask_ml.model_selection import _normalize
-
-__all__ = []
-
-try:
-    __version__ = get_distribution(__name__).version
-    __all__.append("__version__")
-except DistributionNotFound:
-    # package is not installed
-    pass
+from dask_ml.model_selection import _normalize  # noqa: F401
 
+from ._version import __version__
 
-del DistributionNotFound
-del get_distribution
-del _normalize
+__all__ = ["__version__"]

dask_ml/cluster/spectral.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
-"""Algorithms for spectral clustering
-"""
+"""Algorithms for spectral clustering"""
+
 import logging
 
 import dask.array as da
@@ -272,9 +272,7 @@ def fit(self, X, y=None):
         # Eq 16. This is OK when V2 is orthogonal
         V2 = da.sqrt(float(n_components) / n) * da.vstack([A2, B2.T]).dot(
             U_A[:, :n_clusters]
-        ).dot(
-            da.diag(1.0 / da.sqrt(S_A[:n_clusters]))
-        )  # (n, k)
+        ).dot(da.diag(1.0 / da.sqrt(S_A[:n_clusters])))  # (n, k)
         _log_array(logger, V2, "V2.1")
 
         if isinstance(B2, da.Array):
@@ -366,9 +364,9 @@ def _slice_mostly_sorted(array, keep, rest, ind=None):
     slices.append([keep[0]])
     windows = zip(keep[:-1], keep[1:])
 
-    for l, r in windows:
-        if r > l + 1:  # avoid creating empty slices
-            slices.append(slice(l + 1, r))
+    for left, r in windows:
+        if r > left + 1:  # avoid creating empty slices
+            slices.append(slice(left + 1, r))
         slices.append([r])
 
     if keep[-1] < len(array) - 1:  # avoid creating empty slices

dask_ml/decomposition/truncated_svd.py

@@ -148,8 +148,9 @@ def fit(self, X, y=None):
     def _check_array(self, X):
         if self.n_components >= X.shape[1]:
             raise ValueError(
-                "n_components must be < n_features; "
-                "got {} >= {}".format(self.n_components, X.shape[1])
+                "n_components must be < n_features; " "got {} >= {}".format(
+                    self.n_components, X.shape[1]
+                )
             )
         return X
 

dask_ml/ensemble/_blockwise.py

@@ -41,7 +41,7 @@ def fit(self, X, y, **kwargs):
         ]
         results = [
             estimator_.fit(X_, y_, **kwargs)
-            for estimator_, X_, y_, in zip(estimators, Xs, ys)
+            for estimator_, X_, y_ in zip(estimators, Xs, ys)
         ]
         results = list(dask.compute(*results))
         self.estimators_ = results

dask_ml/impute.py

@@ -35,8 +35,9 @@ def fit(self, X, y=None):
         allowed_strategies = ["mean", "median", "most_frequent", "constant"]
         if self.strategy not in allowed_strategies:
             raise ValueError(
-                "Can only use these strategies: {0} "
-                " got strategy={1}".format(allowed_strategies, self.strategy)
+                "Can only use these strategies: {0} " " got strategy={1}".format(
+                    allowed_strategies, self.strategy
+                )
             )
 
         if not (pd.isna(self.missing_values) or self.strategy == "constant"):

dask_ml/linear_model/glm.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 """Generalized Linear Models for large datasets."""
+
 import textwrap
 
 from dask_glm import algorithms, families

dask_ml/linear_model/utils.py

@@ -1,5 +1,4 @@
-"""
-"""
+""" """
 
 import dask.array as da
 import dask.dataframe as dd

dask_ml/metrics/scorer.py

@@ -39,8 +39,9 @@ def get_scorer(scoring: Union[str, Callable], compute: bool = True) -> Callable:
             scorer, kwargs = SCORERS[scoring]
         except KeyError:
             raise ValueError(
-                "{} is not a valid scoring value. "
-                "Valid options are {}".format(scoring, sorted(SCORERS))
+                "{} is not a valid scoring value. " "Valid options are {}".format(
+                    scoring, sorted(SCORERS)
+                )
             )
     else:
         scorer = scoring