Merge branch 'dev' into add-torch-mqcnn

.github/workflows/lints.yml

@@ -0,0 +1,23 @@
+name: Ruff & Docformat
+
+on: [push, pull_request]
+
+jobs:
+ lint:
+ runs-on: ubuntu-latest
+ strategy:
+ matrix:
+ check: ["ruff", "docformatter"]
+
+ steps:
+ - uses: actions/checkout@v3
+ - uses: actions/setup-python@v4
+ - name: Install tools
+ run: pip install "ruff==0.2.2" "docformatter[tomli]==1.5.0"
+ - name: Ruff (Flake8)
+ if: matrix.check == 'ruff'
+ working-directory: src/
+ run: ruff check .
+ - name: Docformatter
+ if: matrix.check == 'docformatter'
+ run: docformatter --check -r src/

Justfile

@@ -34,7 +34,7 @@ release:
  python setup.py sdist
 
 black:
- black --check --color src test examples
+ black --check --diff --color src test examples
 
 mypy:
  python setup.py type_check

examples/persist_model.py

@@ -12,7 +12,7 @@
 # permissions and limitations under the License.
 
 """
-This example shows how to serialize and deserialize a model
+This example shows how to serialize and deserialize a model.
 """
 import os
 import pprint

pyproject.toml

@@ -22,17 +22,15 @@ filterwarnings = "ignore"
 line-length = 79
 
 lint.ignore = [
- # line-length is handled by black
- "E501",
-
- # TODO: remove usage of `l`
- "E741"
+ "E501", # line-length is handled by black
+ "E741" # TODO: remove usage of `l`
 ]
 
 exclude = ["src/gluonts/nursery"]
 
 
 [tool.docformatter]
+black = true
 pre-summary-newline = true
 make-summary-multi-line = true
 wrap-descriptions = 79

requirements/requirements-extras-anomaly-evaluation.txt

@@ -1,2 +1,2 @@
 numba~=0.51,<0.54
-scikit-learn~=0.22
+scikit-learn~=1.0

requirements/requirements-extras-sagemaker-sdk.txt

@@ -1,4 +1,4 @@
-sagemaker~=2.0
+sagemaker~=2.0,>2.214.3
 s3fs~=0.6; python_version >= "3.7.0"
 s3fs~=0.5; python_version < "3.7.0"
 fsspec~=0.8,<0.9; python_version < "3.7.0"

requirements/requirements-rotbaum.txt

@@ -1,2 +1,2 @@
 xgboost>=0.90,<2
-scikit-learn>=0.22,<2
+scikit-learn~=1.0

setup.py

@@ -41,7 +41,9 @@ def get_version_cmdclass(version_file) -> dict:
 
 
 class TypeCheckCommand(distutils.cmd.Command):
- """A custom command to run MyPy on the project sources."""
+ """
+ A custom command to run MyPy on the project sources.
+ """
 
  description = "run MyPy on Python source files"
  user_options = []

src/gluonts/core/serde/_base.py

@@ -287,6 +287,15 @@ def encode_partial(v: partial) -> Any:
  }
 
 
+decode_disallow = [
+ eval,
+ exec,
+ compile,
+ open,
+ input,
+]
+
+
 def decode(r: Any) -> Any:
  """
  Decodes a value from an intermediate representation `r`.
@@ -312,7 +321,10 @@ def decode(r: Any) -> Any:
  kind = r["__kind__"]
  cls = cast(Any, locate(r["class"]))
 
- assert cls is not None, f"Can not locate {r['class']}."
+ if cls is None:
+ raise ValueError(f"Cannot locate {r['class']}.")
+ if cls in decode_disallow:
+ raise ValueError(f"{r['class']} cannot be run.")
 
  if kind == Kind.Type:
  return cls

src/gluonts/dataset/artificial/recipe.py

@@ -1063,10 +1063,10 @@ def normalized_ar1(tau, x0=None, norm="minmax", sigma=1.0):
  r"""
  Returns an ar1 process with an auto correlation time of tau.
 
- norm can be
- None -> no normalization
- 'minmax' -> min_max_scaled
- 'standard' -> 0 mean, unit variance
+ norm can be:
+  - None -> no normalization
+  - 'minmax' -> min_max_scaled
+  - 'standard' -> 0 mean, unit variance
  """
  assert norm in [None, "minmax", "standard"]
  phi = lifted_numpy.exp(-1.0 / tau)

src/gluonts/dataset/common.py

@@ -128,10 +128,11 @@ def infer_file_type(path):
 
 
 def _rglob(path: Path, pattern="*", levels=1):
- """Like ``path.rglob(pattern)`` except this limits the number of sub
- directories that are traversed. ``levels = 0`` is thus the same as
- ``path.glob(pattern)``.
+ """
+ Like ``path.rglob(pattern)`` except this limits the number of sub
+ directories that are traversed.
 
+ ``levels = 0`` is thus the same as ``path.glob(pattern)``.
  """
  if levels is not None:
  levels -= 1

src/gluonts/dataset/jsonl.py

@@ -146,6 +146,7 @@ def __len__(self):
  def _line_starts(self):
  """
  Calculate the position for each line in the file.
+
  This information can be used with ``file.seek`` to directly jump to a
  specific line in the file.
  """

src/gluonts/dataset/multivariate_grouper.py

@@ -92,8 +92,9 @@ def _preprocess(self, dataset: Dataset) -> None:
  The preprocess function iterates over the dataset to gather data that
  is necessary for alignment.
 
- This includes 1) Storing first/last timestamp in the dataset 2)
- Storing the frequency of the dataset
+ This includes:
+ 1. Storing first/last timestamp in the dataset
+ 2. Storing the frequency of the dataset
  """
  for data in dataset:
  timestamp = data[FieldName.START]

src/gluonts/dataset/schema/translate.py

@@ -44,7 +44,9 @@ def fields(self):
 
 @dataclass
 class Get(Op):
- """Extracts the field ``name`` from the input."""
+ """
+ Extracts the field ``name`` from the input.
+ """
 
  name: str
 
@@ -69,7 +71,9 @@ def fields(self):
 
 @dataclass
 class GetAttr(Op):
- """Invokes ``obj.name``"""
+ """
+ Invokes ``obj.name``.
+ """
 
  obj: Op
  name: str
@@ -298,7 +302,8 @@ def parse(x: Union[str, list]) -> Op:
 
 @dataclass
 class Translator:
- """Simple translation for GluonTS Datasets.
+ """
+ Simple translation for GluonTS Datasets.
 
  A given translator transforms an input dictionary (data-entry) into an
  output dictionary.

src/gluonts/dataset/split.py

@@ -86,8 +86,8 @@ def periods_between(
  end: pd.Period,
 ) -> int:
  """
- Count how many periods fit between ``start`` and ``end``
- (inclusive). The frequency is taken from ``start``.
+ Count how many periods fit between ``start`` and ``end`` (inclusive). The
+ frequency is taken from ``start``.
 
  For example:
 

src/gluonts/ev/aggregations.py

@@ -34,7 +34,8 @@ def get(self) -> np.ndarray:
 
 @dataclass
 class Sum(Aggregation):
- """Map-reduce way of calculating the sum of a stream of values.
+ """
+ Map-reduce way of calculating the sum of a stream of values.
 
  `partial_result` represents one of two things, depending on the axis:
  Case 1 - axis 0 is aggregated (axis is None or 0):
@@ -75,7 +76,8 @@ def get(self) -> np.ndarray:
 
 @dataclass
 class Mean(Aggregation):
- """Map-reduce way of calculating the mean of a stream of values.
+ """
+ Map-reduce way of calculating the mean of a stream of values.
 
  `partial_result` represents one of two things, depending on the axis:
  Case 1 - axis 0 is aggregated (axis is None or 0):