Updates pre-commit

.pre-commit-config.yaml

@@ -6,12 +6,12 @@
 
 repos:
 -   repo: https://github.com/ambv/black
-    rev: 22.3.0
+    rev: 23.11.0
     hooks:
     - id: black
       args: [--line-length=100]
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.5.0
     hooks:
     -   id: trailing-whitespace
     # ensures files are either empty or end with a blank line
@@ -27,6 +27,6 @@ repos:
     -   id: isort
         args: ["--profile", "black", --line-length=100]
 -   repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
+    rev: 6.1.0
     hooks:
     - id: flake8

contrib/setup.cfg

@@ -2,8 +2,13 @@
 max-line-length = 100
 exclude = build/,.git/,venv/
 ignore =
-    E203, # whitespace before ':' \
-    E402, # module level import not at top of file \
-    E501, # line too long \
-    W503, # line break before binary operator \
-    W605  # invalid escape sequence
+    # whitespace before ':'
+    E203,
+    # module level import not at top of file
+    E402,
+    # line too long
+    E501,
+    # line break before binary operator
+    W503,
+    # invalid escape sequence
+    W605

examples/data_quality/pandera/run_ray.py

@@ -26,7 +26,6 @@
 from hamilton.plugins import h_ray
 
 if __name__ == "__main__":
-
     logging.basicConfig(stream=sys.stdout)
     logger = logging.getLogger(__name__)
     # Setup a local cluster.

examples/data_quality/simple/run_ray.py

@@ -26,7 +26,6 @@
 from hamilton.plugins import h_ray
 
 if __name__ == "__main__":
-
     logging.basicConfig(stream=sys.stdout)
     logger = logging.getLogger(__name__)
     # Setup a local cluster.

examples/decoupling_io/adapters.py

@@ -45,7 +45,6 @@
 
 @dataclasses.dataclass
 class SklearnPlotSaver(DataSaver):
-
     path: Union[str, PathLike]
     # kwargs
     dpi: float = 200

examples/model_examples/time-series/utils.py

@@ -19,7 +19,6 @@ def reduce_mem_usage(df: pd.DataFrame, name: str, verbose=True):
     for col in df.columns:
         col_type = df[col].dtypes
         if col_type in numerics:
-
             c_min = df[col].min()
             c_max = df[col].max()
             if str(col_type)[:3] == "int":

hamilton/experimental/h_async.py

@@ -67,7 +67,7 @@ async def new_fn(fn=callabl, **fn_kwargs):
             task_dict = {key: process_value(value) for key, value in fn_kwargs.items()}
             fn_kwargs = await await_dict_of_tasks(task_dict)
             if inspect.iscoroutinefunction(fn):
-                return await (fn(**fn_kwargs))
+                return await fn(**fn_kwargs)
             return fn(**fn_kwargs)
 
         coroutine = new_fn(**kwargs)

hamilton/plugins/sklearn_plot_extensions.py

@@ -46,7 +46,6 @@
 
 @dataclasses.dataclass
 class SklearnPlotSaver(DataSaver):
-
     path: Union[str, PathLike]
     # kwargs
     dpi: float = 200

scripts/test_memory.py

@@ -49,7 +49,7 @@ def foo_0(memory_size: int = 100_000_000) -> pd.DataFrame:
 
 
 @parameterize(
-    **{f"foo_{i}": {"foo_i_minus_one": source(f"foo_{i-1}")} for i in range(1, NUM_ITERS)}
+    **{f"foo_{i}": {"foo_i_minus_one": source(f"foo_{i - 1}")} for i in range(1, NUM_ITERS)}
 )
 def foo_i(foo_i_minus_one: pd.DataFrame) -> pd.DataFrame:
     global count
@@ -61,4 +61,4 @@ def foo_i(foo_i_minus_one: pd.DataFrame) -> pd.DataFrame:
 if __name__ == "__main__":
     mod = create_temporary_module(foo_i, foo_0)
     dr = driver.Builder().with_modules(mod).build()
-    output = dr.execute([f"foo_{NUM_ITERS-1}"], inputs=dict(memory_size=100_000_000))
+    output = dr.execute([f"foo_{NUM_ITERS - 1}"], inputs=dict(memory_size=100_000_000))

setup.cfg

@@ -2,8 +2,13 @@
 max-line-length = 100
 exclude = build/,.git/,venv/
 ignore =
-    E203, # whitespace before ':' \
-    E402, # module level import not at top of file \
-    E501, # line too long \
-    W503, # line break before binary operator \
-    W605  # invalid escape sequence
+    # whitespace before ':'
+    E203,
+    # module level import not at top of file
+    E402,
+    # line too long
+    E501,
+    # line break before binary operator
+    W503,
+    # invalid escape sequence
+    W605

writeups/garbage_collection/memory_test.py

@@ -46,7 +46,7 @@ def foo_0(memory_size: int = 100_000_000) -> pd.DataFrame:
 
 
 @parameterize(
-    **{f"foo_{i}": {"foo_i_minus_one": source(f"foo_{i-1}")} for i in range(1, NUM_ITERS)}
+    **{f"foo_{i}": {"foo_i_minus_one": source(f"foo_{i - 1}")} for i in range(1, NUM_ITERS)}
 )
 def foo_i(foo_i_minus_one: pd.DataFrame) -> pd.DataFrame:
     global count
@@ -56,7 +56,6 @@ def foo_i(foo_i_minus_one: pd.DataFrame) -> pd.DataFrame:
 
 
 if __name__ == "__main__":
-
     import os
 
     import psutil