Apply ruff formatter and ditch black

.pre-commit-config.yaml

@@ -15,17 +15,14 @@ repos:
     - id: check-yaml
     - id: check-toml
 
-  - repo: https://github.com/psf/black
-    rev: 23.7.0
-    hooks:
-    - id: black
-
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.2.1'
+    rev: 'v0.2.2'
     hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]
       types_or: [python, jupyter]
+    - id: ruff-format
+      types_or: [python, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.8.0
@@ -34,15 +31,14 @@ repos:
       entry: python3 -m mypy --config-file pyproject.toml
       language: system
       types: [python]
-      exclude: "use_cases|tests|cyclops/(models|monitor|report/plot)"
+      exclude: "tests|cyclops/(models|monitor|report/plot)"
 
   - repo: local
     hooks:
     - id: nbstripout
       name: nbstripout
       language: system
       entry: python3 -m nbstripout
-      exclude: ^docs/source/tutorials/gemini/.*\.ipynb$
 
   - repo: https://github.com/nbQA-dev/nbQA
     rev: 1.7.1

cyclops/data/df/handle_types.py

@@ -1013,7 +1013,8 @@ def collect_indicators(
         # Get categories
         data[cat] = np.argmax(data[indicators].values, axis=1)
         indicator_names = [
-            indicator[len(cat) + 1 :] for indicator in indicators  # noqa: E203
+            indicator[len(cat) + 1 :]
+            for indicator in indicators  # noqa: E203
         ]
         map_dict = {
             i: (name if name != MISSING_CATEGORY else np.nan)

cyclops/data/df/vectorized.py

@@ -144,7 +144,8 @@ def split_vectorized(
     )
 
     splits = [
-        vec.split_by_indices(axes_list[i], index_splits) for i, vec in enumerate(vecs)  # type: ignore
+        vec.split_by_indices(axes_list[i], index_splits)
+        for i, vec in enumerate(vecs)  # type: ignore
     ]
 
     return tuple(splits)

cyclops/data/slicer.py

@@ -96,11 +96,13 @@ class SliceSpec:
     ...         {"feature_1": {"value": ["value_1", "value_2"]}},
     ...         {"feature_1": {"value": "value_1", "negate": True, "keep_nulls": True}},
     ...         {"feature_1": {"min_value": "2020-01-01", "max_value": "2020-12-31"}},
-    ...         {"feature_1": {
-    ...             "min_value": 5,
-    ...             "max_value": 60,
-    ...             "min_inclusive": False,
-    ...             "max_inclusive": False}
+    ...         {
+    ...             "feature_1": {
+    ...                 "min_value": 5,
+    ...                 "max_value": 60,
+    ...                 "min_inclusive": False,
+    ...                 "max_inclusive": False,
+    ...             }
     ...         },
     ...         {"feature_1": {"year": [2020, 2021, 2022]}},
     ...         {"feature_1": {"month": [6, 7, 8]}},
@@ -110,7 +112,8 @@ class SliceSpec:
     ...         {
     ...             "feature_1": {"value": "value_1"},
     ...             "feature_2": {
-    ...                 "min_value": "2020-01-01", "keep_nulls": False,
+    ...                 "min_value": "2020-01-01",
+    ...                 "keep_nulls": False,
     ...             },
     ...             "feature_3": {"year": ["2000", "2010", "2020"]},
     ...         },

cyclops/evaluate/evaluator.py

@@ -268,7 +268,8 @@ def _compute_metrics(
                         stacklevel=1,
                     )
                     metric_output: Dict[str, Array] = {
-                        metric_name: float("NaN") for metric_name in metrics  # type: ignore[attr-defined,misc]
+                        metric_name: float("NaN")
+                        for metric_name in metrics  # type: ignore[attr-defined,misc]
                     }
                 elif (
                     batch_size is None or batch_size < 0

cyclops/evaluate/fairness/evaluator.py

@@ -755,7 +755,8 @@ def _compute_metrics(  # noqa: C901, PLR0912
         if len(dataset) == 0:
             warnings.warn(empty_dataset_msg, RuntimeWarning, stacklevel=1)
             results: Dict[str, Any] = {
-                metric_name: float("NaN") for metric_name in metrics  # type: ignore[attr-defined]
+                metric_name: float("NaN")
+                for metric_name in metrics  # type: ignore[attr-defined]
             }
         elif (
             batch_size is None or batch_size <= 0

cyclops/evaluate/metrics/accuracy.py

@@ -108,8 +108,10 @@ class MulticlassAccuracy(MulticlassStatScores, registry_key="multiclass_accuracy
     array([1.        , 0.        , 0.66666667])
     >>> metric.reset_state()
     >>> target = [[0, 1, 2], [2, 1, 0]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]]]
+    >>> preds = [
+    ...     [[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
+    ...     [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()
@@ -184,8 +186,7 @@ class MultilabelAccuracy(MultilabelStatScores, registry_key="multilabel_accuracy
     array([1., 1., 0.])
     >>> metric.reset_state()
     >>> target = [[[0, 1, 1], [1, 0, 0]], [[1, 0, 0], [0, 1, 1]]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
+    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]], [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()
@@ -291,8 +292,10 @@ class Accuracy(Metric, registry_key="accuracy", force_register=True):
     array([1.        , 0.        , 0.66666667])
     >>> metric.reset_state()
     >>> target = [[0, 1, 2], [2, 1, 0]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]]]
+    >>> preds = [
+    ...     [[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
+    ...     [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()
@@ -307,8 +310,7 @@ class Accuracy(Metric, registry_key="accuracy", force_register=True):
     array([1., 1., 0.])
     >>> metric.reset_state()
     >>> target = [[[0, 1, 1], [1, 0, 0]], [[1, 0, 0], [0, 1, 1]]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
+    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]], [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()

cyclops/evaluate/metrics/auroc.py

@@ -108,15 +108,21 @@ class MulticlassAUROC(MulticlassPrecisionRecallCurve, registry_key="multiclass_a
     --------
     >>> from cyclops.evaluate.metrics import MulticlassAUROC
     >>> target = [0, 1, 2, 0]
-    >>> preds = [[0.9, 0.05, 0.05], [0.05, 0.89, 0.06],
-    ...         [0.05, 0.01, 0.94], [0.9, 0.05, 0.05]]
+    >>> preds = [
+    ...     [0.9, 0.05, 0.05],
+    ...     [0.05, 0.89, 0.06],
+    ...     [0.05, 0.01, 0.94],
+    ...     [0.9, 0.05, 0.05],
+    ... ]
     >>> metric = MulticlassAUROC(num_classes=3)
     >>> metric(target, preds)
     array([1., 1., 1.])
     >>> metric.reset_state()
     >>> target = [[0, 1, 0], [1, 0, 1]]
-    >>> preds = [[[0.1, 0.9, 0.0], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
-    ...         [[0.1, 0.1, 0.8], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]]]
+    >>> preds = [
+    ...     [[0.1, 0.9, 0.0], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
+    ...     [[0.1, 0.1, 0.8], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()
@@ -278,15 +284,21 @@ class AUROC(Metric, registry_key="auroc", force_register=True):
     >>> # (multiclass)
     >>> from cyclops.evaluate.metrics import MulticlassAUROC
     >>> target = [0, 1, 2, 0]
-    >>> preds = [[0.9, 0.05, 0.05], [0.05, 0.89, 0.06],
-    ...         [0.05, 0.01, 0.94], [0.9, 0.05, 0.05]]
+    >>> preds = [
+    ...     [0.9, 0.05, 0.05],
+    ...     [0.05, 0.89, 0.06],
+    ...     [0.05, 0.01, 0.94],
+    ...     [0.9, 0.05, 0.05],
+    ... ]
     >>> metric = MulticlassAUROC(num_classes=3)
     >>> metric(target, preds)
     array([1., 1., 1.])
     >>> metric.reset_state()
     >>> target = [[0, 1, 0], [1, 0, 1]]
-    >>> preds = [[[0.1, 0.9, 0.0], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
-    ...         [[0.1, 0.1, 0.8], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]]]
+    >>> preds = [
+    ...     [[0.1, 0.9, 0.0], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
+    ...     [[0.1, 0.1, 0.8], [0.7, 0.2, 0.1], [0.2, 0.3, 0.5]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update_state(t, p)
     >>> metric.compute()

cyclops/evaluate/metrics/experimental/accuracy.py

@@ -92,8 +92,10 @@ class MulticlassAccuracy(
     Array(0.6, dtype=float32)
     >>> metric.reset()
     >>> target = [[0, 1, 2], [2, 1, 0]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]]]
+    >>> preds = [
+    ...     [[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
+    ...     [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()
@@ -160,8 +162,7 @@ class MultilabelAccuracy(
     Array(0.6666667, dtype=float32)
     >>> metric.reset()
     >>> target = [[[0, 1, 1], [1, 0, 0]], [[1, 0, 0], [0, 1, 1]]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
+    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]], [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()

cyclops/evaluate/metrics/experimental/auroc.py

@@ -79,7 +79,11 @@ def _compute_metric(self) -> Array:  # type: ignore[override]
             if self.thresholds is None
             else self.confmat  # type: ignore[attr-defined]
         )
-        return _binary_auroc_compute(state, thresholds=self.thresholds, max_fpr=self.max_fpr)  # type: ignore
+        return _binary_auroc_compute(
+            state,
+            thresholds=self.thresholds,
+            max_fpr=self.max_fpr,
+        )  # type: ignore
 
 
 class MulticlassAUROC(MulticlassPrecisionRecallCurve, registry_key="multiclass_auroc"):
@@ -117,12 +121,15 @@ class MulticlassAUROC(MulticlassPrecisionRecallCurve, registry_key="multiclass_a
     >>> from cyclops.evaluate.metrics.experimental import MulticlassAUROC
     >>> target = anp.asarray([0, 1, 2, 0, 1, 2])
     >>> preds = anp.asarray(
-    ...     [[0.11, 0.22, 0.67],
-    ...     [0.84, 0.73, 0.12],
-    ...     [0.33, 0.92, 0.44],
-    ...     [0.11, 0.22, 0.67],
-    ...     [0.84, 0.73, 0.12],
-    ...     [0.33, 0.92, 0.44]])
+    ...     [
+    ...         [0.11, 0.22, 0.67],
+    ...         [0.84, 0.73, 0.12],
+    ...         [0.33, 0.92, 0.44],
+    ...         [0.11, 0.22, 0.67],
+    ...         [0.84, 0.73, 0.12],
+    ...         [0.33, 0.92, 0.44],
+    ...     ]
+    ... )
     >>> auroc = MulticlassAUROC(num_classes=3, average="macro", thresholds=None)
     >>> auroc(target, preds)
     Array(0.33333334, dtype=float32)

cyclops/evaluate/metrics/experimental/average_precision.py

@@ -125,14 +125,19 @@ class MulticlassAveragePrecision(
     >>> from cyclops.evaluate.metrics.experimental import MulticlassAveragePrecision
     >>> target = anp.asarray([0, 1, 2, 0, 1, 2])
     >>> preds = anp.asarray(
-    ...     [[0.11, 0.22, 0.67],
-    ...     [0.84, 0.73, 0.12],
-    ...     [0.33, 0.92, 0.44],
-    ...     [0.11, 0.22, 0.67],
-    ...     [0.84, 0.73, 0.12],
-    ...     [0.33, 0.92, 0.44]])
+    ...     [
+    ...         [0.11, 0.22, 0.67],
+    ...         [0.84, 0.73, 0.12],
+    ...         [0.33, 0.92, 0.44],
+    ...         [0.11, 0.22, 0.67],
+    ...         [0.84, 0.73, 0.12],
+    ...         [0.33, 0.92, 0.44],
+    ...     ]
+    ... )
     >>> metric = MulticlassAveragePrecision(
-    ...     num_classes=3, thresholds=None, average=None,
+    ...     num_classes=3,
+    ...     thresholds=None,
+    ...     average=None,
     ... )
     >>> metric(target, preds)
     Array([0.33333334, 0.5       , 0.5       ], dtype=float32)
@@ -224,7 +229,9 @@ class MultilabelAveragePrecision(
     ...     [[0.11, 0.22, 0.67], [0.84, 0.73, 0.12], [0.33, 0.92, 0.44]],
     ... )
     >>> metric = MultilabelAveragePrecision(
-    ...     num_labels=3, thresholds=None, average=None,
+    ...     num_labels=3,
+    ...     thresholds=None,
+    ...     average=None,
     ... )
     >>> metric(target, preds)
     Array([1.       , 0.5833334, 0.5      ], dtype=float32)

cyclops/evaluate/metrics/experimental/confusion_matrix.py

@@ -119,8 +119,12 @@ class BinaryConfusionMatrix(
     Array([[2, 1],
            [1, 2]], dtype=int64)
     >>> target = anp.asarray([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
-    >>> preds = anp.asarray([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
-    ...                     [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
+    >>> preds = anp.asarray(
+    ...     [
+    ...         [[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
+    ...         [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]],
+    ...     ]
+    ... )
 
     """
 
@@ -205,10 +209,14 @@ class MulticlassConfusionMatrix(Metric, registry_key="multiclass_confusion_matri
            [0, 1, 0],
            [0, 0, 1]], dtype=int64)
     >>> target = anp.asarray([2, 1, 0, 0])
-    >>> preds = anp.asarray([[0.16, 0.26, 0.58],
-    ...                     [0.22, 0.61, 0.17],
-    ...                     [0.71, 0.09, 0.20],
-    ...                     [0.05, 0.82, 0.13]])
+    >>> preds = anp.asarray(
+    ...     [
+    ...         [0.16, 0.26, 0.58],
+    ...         [0.22, 0.61, 0.17],
+    ...         [0.71, 0.09, 0.20],
+    ...         [0.05, 0.82, 0.13],
+    ...     ]
+    ... )
     >>> metric = MulticlassConfusionMatrix(num_classes=3)
     >>> metric(target, preds)
     Array([[1, 1, 0],

cyclops/evaluate/metrics/experimental/f_score.py

@@ -120,8 +120,10 @@ class MulticlassFBetaScore(
     Array(0.6, dtype=float32)
     >>> metric.reset()
     >>> target = [[0, 1, 2], [2, 1, 0]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]]]
+    >>> preds = [
+    ...     [[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
+    ...     [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()
@@ -219,8 +221,7 @@ class MultilabelFBetaScore(
     Array(0.6666667, dtype=float32)
     >>> metric.reset()
     >>> target = [[[0, 1, 1], [1, 0, 0]], [[1, 0, 0], [0, 1, 1]]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
+    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]], [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()
@@ -359,8 +360,10 @@ class MulticlassF1Score(MulticlassFBetaScore, registry_key="multiclass_f1_score"
     Array(0.6, dtype=float32)
     >>> metric.reset()
     >>> target = [[0, 1, 2], [2, 1, 0]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]]]
+    >>> preds = [
+    ...     [[0.05, 0.95, 0], [0.1, 0.8, 0.1], [0.2, 0.6, 0.2]],
+    ...     [[0.1, 0.8, 0.1], [0.05, 0.95, 0], [0.2, 0.6, 0.2]],
+    ... ]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()
@@ -433,8 +436,7 @@ class MultilabelF1Score(
     Array(0.6666667, dtype=float32)
     >>> metric.reset()
     >>> target = [[[0, 1, 1], [1, 0, 0]], [[1, 0, 0], [0, 1, 1]]]
-    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]],
-    ...          [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
+    >>> preds = [[[0.05, 0.95, 0], [0.1, 0.8, 0.1]], [[0.1, 0.8, 0.1], [0.05, 0.95, 0]]]
     >>> for t, p in zip(target, preds):
     ...     metric.update(anp.asarray(t), anp.asarray(p))
     >>> metric.compute()