Updates pre-commit hooks

Fixes pre-commit hooks. TBD what was happening, but this updates
everything, and adds known_first_party to disambiguate the use of the
hamilton package. Should make it stable across all systems, and ensures
we use the latest linting/checking rules.

.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
@@ -21,12 +21,12 @@ repos:
     # valid python file
     -   id: check-ast
 # isort python package import sorting
--   repo: https://github.com/pre-commit/mirrors-isort
-    rev: 'v5.10.1'
+-   repo: https://github.com/pycqa/isort
+    rev: '5.12.0'
     hooks:
     -   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/hamilton/contrib/dagworks/text_summarization/__init__.py

@@ -14,7 +14,6 @@
     from tqdm import tqdm
     import litellm
 
-
 from hamilton.function_modifiers import config
 
 

contrib/hamilton/contrib/user/zilto/text_summarization/__init__.py

@@ -14,7 +14,6 @@
     from tenacity import retry, stop_after_attempt, wait_random_exponential
     from tqdm import tqdm
 
-
 from hamilton.function_modifiers import config
 
 

contrib/setup.cfg

@@ -2,8 +2,16 @@
 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
+
+[isort]
+known_first_party=hamilton

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

plugin_tests/h_ray/test_h_ray_workflow.py

@@ -1,11 +1,11 @@
 import pandas as pd
 import pytest
 import ray
+from plugin_tests.h_ray.resources import example_module, smoke_screen_module
 from ray import workflow
 
 from hamilton import base, driver
 from hamilton.plugins import h_ray
-from plugin_tests.h_ray.resources import example_module, smoke_screen_module
 
 
 @pytest.fixture(scope="module")

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

tests/execution/test_executors.py

@@ -3,6 +3,14 @@
 
 import numpy as np
 import pytest
+from tests.resources.dynamic_parallelism import (
+    inputs_in_collect,
+    no_parallel,
+    parallel_collect_multiple_arguments,
+    parallel_complex,
+    parallel_delayed,
+    parallel_linear_basic,
+)
 
 import hamilton.ad_hoc_utils
 from hamilton import base, driver
@@ -21,14 +29,6 @@
     TaskImplementation,
 )
 from hamilton.htypes import Collect, Parallelizable
-from tests.resources.dynamic_parallelism import (
-    inputs_in_collect,
-    no_parallel,
-    parallel_collect_multiple_arguments,
-    parallel_complex,
-    parallel_delayed,
-    parallel_linear_basic,
-)
 
 ADAPTER = base.DefaultAdapter()
 

tests/execution/test_node_grouping.py

@@ -1,3 +1,5 @@
+from tests.resources.dynamic_parallelism import no_parallel, parallel_complex, parallel_linear_basic
+
 from hamilton import ad_hoc_utils, base, graph, node
 from hamilton.execution import grouping
 from hamilton.execution.grouping import (
@@ -9,7 +11,6 @@
 )
 from hamilton.graph import FunctionGraph
 from hamilton.node import NodeType
-from tests.resources.dynamic_parallelism import no_parallel, parallel_complex, parallel_linear_basic
 
 
 def test_group_individually():

tests/function_modifiers/test_macros.py

@@ -3,9 +3,9 @@
 
 import pandas as pd
 import pytest
+import tests.resources.pipe
 
 import hamilton.function_modifiers
-import tests.resources.pipe
 from hamilton import base, driver, function_modifiers, models, node
 from hamilton.function_modifiers import does
 from hamilton.function_modifiers.dependencies import source, value

tests/function_modifiers/test_recursive.py

@@ -3,8 +3,8 @@
 from typing import Tuple
 
 import pytest
-
 import tests.resources.reuse_subdag
+
 from hamilton import ad_hoc_utils, graph
 from hamilton.function_modifiers import (
     InvalidDecoratorException,

tests/function_modifiers/test_validation.py

@@ -1,6 +1,11 @@
 import numpy as np
 import pandas as pd
 import pytest
+from tests.resources.dq_dummy_examples import (
+    DUMMY_VALIDATORS_FOR_TESTING,
+    SampleDataValidator2,
+    SampleDataValidator3,
+)
 
 from hamilton import node
 from hamilton.data_quality.base import DataValidationError, ValidationResult
@@ -11,11 +16,6 @@
     check_output_custom,
 )
 from hamilton.node import DependencyType
-from tests.resources.dq_dummy_examples import (
-    DUMMY_VALIDATORS_FOR_TESTING,
-    SampleDataValidator2,
-    SampleDataValidator3,
-)
 
 
 def test_check_output_node_transform():

tests/io/test_materialization.py

@@ -2,9 +2,9 @@
 from typing import Any, Collection, Dict, List, Optional, Tuple, Type
 
 import pytest
-
 import tests.resources.cyclic_functions
 import tests.resources.test_default_args
+
 from hamilton import base, graph, node, registry
 from hamilton.function_modifiers import load_from, save_to, value
 from hamilton.io import materialization

tests/test_caching.py

@@ -3,11 +3,11 @@
 
 import pandas as pd
 import pytest
+from tests import nodes
 
 from hamilton import base
 from hamilton.driver import Driver
 from hamilton.experimental import h_cache
-from tests import nodes
 
 
 @pytest.fixture

tests/test_common.py

@@ -1,7 +1,7 @@
 import pytest
-
 import tests.resources.cyclic_functions
 import tests.resources.test_default_args
+
 from hamilton import common, driver
 
 

tests/test_default_data_quality.py

@@ -6,6 +6,12 @@
 import numpy as np
 import pandas as pd
 import pytest
+from tests.resources.dq_dummy_examples import (
+    DUMMY_VALIDATORS_FOR_TESTING,
+    SampleDataValidator1,
+    SampleDataValidator2,
+    SampleDataValidator3,
+)
 
 import hamilton.data_quality.base
 from hamilton.data_quality import default_validators
@@ -14,12 +20,6 @@
     AVAILABLE_DEFAULT_VALIDATORS,
     resolve_default_validators,
 )
-from tests.resources.dq_dummy_examples import (
-    DUMMY_VALIDATORS_FOR_TESTING,
-    SampleDataValidator1,
-    SampleDataValidator2,
-    SampleDataValidator3,
-)
 
 
 @pytest.mark.parametrize(

tests/test_end_to_end.py

@@ -4,10 +4,10 @@
 from typing import Any, Callable, Dict, List, Type
 
 import pytest
-
 import tests.resources.data_quality
 import tests.resources.dynamic_config
 import tests.resources.overrides
+
 from hamilton import ad_hoc_utils, base, driver, settings
 from hamilton.base import DefaultAdapter
 from hamilton.data_quality.base import DataValidationError, ValidationResult

tests/test_graph.py

@@ -5,9 +5,6 @@
 
 import pandas as pd
 import pytest
-
-import hamilton.graph_utils
-import hamilton.htypes
 import tests.resources.bad_functions
 import tests.resources.config_modifier
 import tests.resources.cyclic_functions
@@ -22,6 +19,9 @@
 import tests.resources.parametrized_nodes
 import tests.resources.test_default_args
 import tests.resources.typing_vs_not_typing
+
+import hamilton.graph_utils
+import hamilton.htypes
 from hamilton import ad_hoc_utils, base, graph, node
 from hamilton.execution import graph_functions
 from hamilton.node import NodeType

tests/test_hamilton_driver.py

@@ -2,13 +2,13 @@
 
 import pandas as pd
 import pytest
-
 import tests.resources.cyclic_functions
 import tests.resources.dummy_functions
 import tests.resources.dynamic_parallelism.parallel_linear_basic
 import tests.resources.tagging
 import tests.resources.test_default_args
 import tests.resources.very_simple_dag
+
 from hamilton import base, node
 from hamilton.driver import (
     Builder,

writeups/garbage_collection/memory_test.py

@@ -56,7 +56,6 @@ def foo_i(foo_i_minus_one: pd.DataFrame) -> pd.DataFrame:
 
 
 if __name__ == "__main__":
-
     import os
 
     import psutil