[pre-commit.ci] pre-commit autoupdate (#818)

* [pre-commit.ci] pre-commit autoupdate updates: - [github.com/astral-sh/ruff-pre-commit: v0.5.7 → v0.6.3](astral-sh/ruff-pre-commit@v0.5.7...v0.6.3) - [github.com/pre-commit/mirrors-mypy: v1.11.1 → v1.11.2](pre-commit/mirrors-mypy@v1.11.1...v1.11.2) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * making ruff happy --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Edoardo Abati <[email protected]>
narwhals-dev · Sep 7, 2024 · 5f91aa1 · 5f91aa1
1 parent 2969d75
commit 5f91aa1
Show file tree

Hide file tree

Showing 24 changed files with 501 additions and 476 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,15 +1,15 @@
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: 'v0.5.7'
+  rev: 'v0.6.3'
   hooks:
     # Run the formatter.
     - id: ruff-format
     # Run the linter.
     - id: ruff
       args: [--fix]
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: 'v1.11.1'
+  rev: 'v1.11.2'
   hooks:
     - id: mypy
       additional_dependencies: ['polars==1.4.1', 'pytest==8.3.2']

diff --git a/pyproject.toml b/pyproject.toml
@@ -79,6 +79,15 @@ lint.ignore = [
 "tpch/tests/*" = ["S101"]
 "utils/*" = ["S311", "PTH123"]
 "tpch/execute/*" = ["T201"]
+"tpch/notebooks/*" = [
+  "ANN001",
+  "ANN201",
+  "EM101",
+  "EXE002",
+  "PTH123",
+  "T203",
+  "TRY003",
+]
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"

diff --git a/tests/expr_and_series/arithmetic_test.py b/tests/expr_and_series/arithmetic_test.py
@@ -149,7 +149,7 @@ def test_truediv_same_dims(constructor_eager: Any, request: Any) -> None:
     compare_dicts({"a": result}, {"a": [2, 1, 1 / 3]})
 
 
-@pytest.mark.slow()
+@pytest.mark.slow
 @given(  # type: ignore[misc]
     left=st.integers(-100, 100),
     right=st.integers(-100, 100),
@@ -189,7 +189,7 @@ def test_floordiv(left: int, right: int) -> None:
     compare_dicts(result, expected)
 
 
-@pytest.mark.slow()
+@pytest.mark.slow
 @given(  # type: ignore[misc]
     left=st.integers(-100, 100),
     right=st.integers(-100, 100),

diff --git a/tests/expr_and_series/dt/ordinal_day_test.py b/tests/expr_and_series/dt/ordinal_day_test.py
@@ -17,7 +17,7 @@
     parse_version(pd.__version__) < parse_version("2.0.0"),
     reason="pyarrow dtype not available",
 )
-@pytest.mark.slow()
+@pytest.mark.slow
 def test_ordinal_day(dates: datetime) -> None:
     result_pd = nw.from_native(pd.Series([dates]), series_only=True).dt.ordinal_day()[0]
     result_pdms = nw.from_native(

diff --git a/tests/expr_and_series/dt/total_minutes_test.py b/tests/expr_and_series/dt/total_minutes_test.py
@@ -22,7 +22,7 @@
     parse_version(pd.__version__) < parse_version("2.2.0"),
     reason="pyarrow dtype not available",
 )
-@pytest.mark.slow()
+@pytest.mark.slow
 def test_total_minutes(timedeltas: timedelta) -> None:
     result_pd = nw.from_native(
         pd.Series([timedeltas]), series_only=True

diff --git a/tests/hypothesis/test_basic_arithmetic.py b/tests/hypothesis/test_basic_arithmetic.py
@@ -22,7 +22,7 @@
         max_size=3,
     ),
 )  # type: ignore[misc]
-@pytest.mark.slow()
+@pytest.mark.slow
 def test_mean(
     integer: st.SearchStrategy[list[int]],
     floats: st.SearchStrategy[float],

diff --git a/tests/hypothesis/test_concat.py b/tests/hypothesis/test_concat.py
@@ -31,7 +31,7 @@
     ),
     how=st.sampled_from(["horizontal", "vertical"]),
 )  # type: ignore[misc]
-@pytest.mark.slow()
+@pytest.mark.slow
 @pytest.mark.skipif(is_windows(), reason="pyarrow breaking on windows")
 def test_concat(  # pragma: no cover
     integers: list[int],

diff --git a/tests/hypothesis/test_join.py b/tests/hypothesis/test_join.py
@@ -42,7 +42,7 @@
 )  # type: ignore[misc]
 @pytest.mark.skipif(pl_version < parse_version("0.20.13"), reason="0.0 == -0.0")
 @pytest.mark.skipif(pd_version < parse_version("2.0.0"), reason="requires pyarrow")
-@pytest.mark.slow()
+@pytest.mark.slow
 def test_join(  # pragma: no cover
     integers: st.SearchStrategy[list[int]],
     other_integers: st.SearchStrategy[list[int]],
@@ -88,7 +88,7 @@ def test_join(  # pragma: no cover
         max_size=3,
     ),
 )  # type: ignore[misc]
-@pytest.mark.slow()
+@pytest.mark.slow
 @pytest.mark.skipif(pd_version < parse_version("2.0.0"), reason="requires pyarrow")
 def test_cross_join(  # pragma: no cover
     integers: st.SearchStrategy[list[int]],
@@ -135,7 +135,7 @@ def test_cross_join(  # pragma: no cover
         st.sampled_from(["a", "b", "d"]), min_size=1, max_size=3, unique=True
     ),
 )
-@pytest.mark.slow()
+@pytest.mark.slow
 @pytest.mark.filterwarnings("ignore:the default coalesce behavior")
 def test_left_join(  # pragma: no cover
     a_left_data: list[int],

diff --git a/tpch/notebooks/q1/execute.ipynb b/tpch/notebooks/q1/execute.ipynb
@@ -58,10 +58,12 @@
    },
    "outputs": [],
    "source": [
-    "from typing import Any\n",
     "from datetime import datetime\n",
+    "from typing import Any\n",
+    "\n",
     "import narwhals as nw\n",
     "\n",
+    "\n",
     "@nw.narwhalify\n",
     "def q1(lineitem_ds: Any) -> Any:\n",
     "    var_1 = datetime(1998, 9, 2)\n",
@@ -107,14 +109,14 @@
    "outputs": [],
    "source": [
     "dir_ = \"/kaggle/input/tpc-h-data-parquet-s-2/\"\n",
-    "region = dir_ + 'region.parquet'\n",
-    "nation = dir_ + 'nation.parquet'\n",
-    "customer = dir_ + 'customer.parquet'\n",
-    "lineitem = dir_ + 'lineitem.parquet'\n",
-    "orders = dir_ + 'orders.parquet'\n",
-    "supplier = dir_ + 'supplier.parquet'\n",
-    "part = dir_ + 'part.parquet'\n",
-    "partsupp = dir_ + 'partsupp.parquet'"
+    "region = dir_ + \"region.parquet\"\n",
+    "nation = dir_ + \"nation.parquet\"\n",
+    "customer = dir_ + \"customer.parquet\"\n",
+    "lineitem = dir_ + \"lineitem.parquet\"\n",
+    "orders = dir_ + \"orders.parquet\"\n",
+    "supplier = dir_ + \"supplier.parquet\"\n",
+    "part = dir_ + \"part.parquet\"\n",
+    "partsupp = dir_ + \"partsupp.parquet\""
    ]
   },
   {
@@ -133,16 +135,18 @@
    },
    "outputs": [],
    "source": [
-    "import pyarrow.parquet as pq\n",
     "import dask.dataframe as dd\n",
+    "import pyarrow.parquet as pq\n",
     "\n",
     "IO_FUNCS = {\n",
-    "    'pandas': lambda x: pd.read_parquet(x, engine='pyarrow'),\n",
-    "    'pandas[pyarrow]': lambda x: pd.read_parquet(x, engine='pyarrow', dtype_backend='pyarrow'),\n",
-    "    'polars[eager]': lambda x: pl.read_parquet(x),\n",
-    "    'polars[lazy]': lambda x: pl.scan_parquet(x),\n",
-    "    'pyarrow': lambda x: pq.read_table(x),\n",
-    "    'dask': lambda x: dd.read_parquet(x, engine='pyarrow', dtype_backend='pyarrow'),\n",
+    "    \"pandas\": lambda x: pd.read_parquet(x, engine=\"pyarrow\"),\n",
+    "    \"pandas[pyarrow]\": lambda x: pd.read_parquet(\n",
+    "        x, engine=\"pyarrow\", dtype_backend=\"pyarrow\"\n",
+    "    ),\n",
+    "    \"polars[eager]\": lambda x: pl.read_parquet(x),\n",
+    "    \"polars[lazy]\": lambda x: pl.scan_parquet(x),\n",
+    "    \"pyarrow\": lambda x: pq.read_table(x),\n",
+    "    \"dask\": lambda x: dd.read_parquet(x, engine=\"pyarrow\", dtype_backend=\"pyarrow\"),\n",
     "}"
    ]
   },
@@ -171,7 +175,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tool = 'pyarrow'\n",
+    "tool = \"pyarrow\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(fn(lineitem))\n",
     "results[tool] = timings.all_runs"
@@ -210,7 +214,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'pandas'\n",
+    "tool = \"pandas\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(lineitem_ds=fn(lineitem))\n",
     "results[tool] = timings.all_runs"
@@ -249,7 +253,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'pandas[pyarrow]'\n",
+    "tool = \"pandas[pyarrow]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(fn(lineitem))\n",
     "results[tool] = timings.all_runs"
@@ -288,7 +292,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'polars[eager]'\n",
+    "tool = \"polars[eager]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(fn(lineitem))\n",
     "results[tool] = timings.all_runs"
@@ -327,7 +331,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'polars[lazy]'\n",
+    "tool = \"polars[lazy]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(fn(lineitem)).collect()\n",
     "results[tool] = timings.all_runs"
@@ -348,7 +352,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tool = 'dask'\n",
+    "tool = \"dask\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q1(fn(lineitem)).collect()\n",
     "results[tool] = timings.all_runs"
@@ -370,8 +374,9 @@
    "outputs": [],
    "source": [
     "import json\n",
-    "with open('results.json', 'w') as fd:\n",
-    "    json.dump(results, fd)\n"
+    "\n",
+    "with open(\"results.json\", \"w\") as fd:\n",
+    "    json.dump(results, fd)"
    ]
   }
  ],

diff --git a/tpch/notebooks/q10/execute.ipynb b/tpch/notebooks/q10/execute.ipynb
@@ -55,22 +55,23 @@
    },
    "outputs": [],
    "source": [
-    "from typing import Any\n",
     "from datetime import datetime\n",
+    "from typing import Any\n",
+    "\n",
     "import narwhals as nw\n",
     "\n",
+    "\n",
     "def q10(\n",
     "    customer_ds_raw: Any,\n",
     "    nation_ds_raw: Any,\n",
     "    lineitem_ds_raw: Any,\n",
     "    orders_ds_raw: Any,\n",
     ") -> Any:\n",
-    "\n",
     "    nation_ds = nw.from_native(nation_ds_raw)\n",
     "    line_item_ds = nw.from_native(lineitem_ds_raw)\n",
     "    orders_ds = nw.from_native(orders_ds_raw)\n",
     "    customer_ds = nw.from_native(customer_ds_raw)\n",
-    "    \n",
+    "\n",
     "    var1 = datetime(1993, 10, 1)\n",
     "    var2 = datetime(1994, 1, 1)\n",
     "\n",
@@ -81,8 +82,7 @@
     "        .filter(nw.col(\"o_orderdate\").is_between(var1, var2, closed=\"left\"))\n",
     "        .filter(nw.col(\"l_returnflag\") == \"R\")\n",
     "        .with_columns(\n",
-    "            (nw.col(\"l_extendedprice\") * (1 - nw.col(\"l_discount\")))\n",
-    "            .alias(\"revenue\")\n",
+    "            (nw.col(\"l_extendedprice\") * (1 - nw.col(\"l_discount\"))).alias(\"revenue\")\n",
     "        )\n",
     "        .group_by(\n",
     "            \"c_custkey\",\n",
@@ -127,10 +127,10 @@
    "outputs": [],
    "source": [
     "dir_ = \"/kaggle/input/tpc-h-data-parquet-s-2/\"\n",
-    "nation = dir_ + 'nation.parquet'\n",
-    "lineitem = dir_ + 'lineitem.parquet'\n",
-    "orders = dir_ + 'orders.parquet'\n",
-    "customer = dir_ + 'customer.parquet'"
+    "nation = dir_ + \"nation.parquet\"\n",
+    "lineitem = dir_ + \"lineitem.parquet\"\n",
+    "orders = dir_ + \"orders.parquet\"\n",
+    "customer = dir_ + \"customer.parquet\""
    ]
   },
   {
@@ -149,10 +149,12 @@
    "outputs": [],
    "source": [
     "IO_FUNCS = {\n",
-    "    'pandas': lambda x: pd.read_parquet(x, engine='pyarrow'),\n",
-    "    'pandas[pyarrow]': lambda x: pd.read_parquet(x, engine='pyarrow', dtype_backend='pyarrow'),\n",
-    "    'polars[eager]': lambda x: pl.read_parquet(x),\n",
-    "    'polars[lazy]': lambda x: pl.scan_parquet(x),\n",
+    "    \"pandas\": lambda x: pd.read_parquet(x, engine=\"pyarrow\"),\n",
+    "    \"pandas[pyarrow]\": lambda x: pd.read_parquet(\n",
+    "        x, engine=\"pyarrow\", dtype_backend=\"pyarrow\"\n",
+    "    ),\n",
+    "    \"polars[eager]\": lambda x: pl.read_parquet(x),\n",
+    "    \"polars[lazy]\": lambda x: pl.scan_parquet(x),\n",
     "}"
    ]
   },
@@ -196,7 +198,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'pandas'\n",
+    "tool = \"pandas\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q10(fn(customer), fn(nation), fn(lineitem), fn(orders))\n",
     "results[tool] = timings.all_runs"
@@ -233,7 +235,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'pandas[pyarrow]'\n",
+    "tool = \"pandas[pyarrow]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q10(fn(customer), fn(nation), fn(lineitem), fn(orders))\n",
     "results[tool] = timings.all_runs"
@@ -270,7 +272,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'polars[eager]'\n",
+    "tool = \"polars[eager]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q10(fn(customer), fn(nation), fn(lineitem), fn(orders))\n",
     "results[tool] = timings.all_runs"
@@ -307,7 +309,7 @@
    },
    "outputs": [],
    "source": [
-    "tool = 'polars[lazy]'\n",
+    "tool = \"polars[lazy]\"\n",
     "fn = IO_FUNCS[tool]\n",
     "timings = %timeit -o -q q10(fn(customer), fn(nation), fn(lineitem), fn(orders)).collect()\n",
     "results[tool] = timings.all_runs"
@@ -327,8 +329,9 @@
    "outputs": [],
    "source": [
     "import json\n",
-    "with open('results.json', 'w') as fd:\n",
-    "    json.dump(results, fd)\n"
+    "\n",
+    "with open(\"results.json\", \"w\") as fd:\n",
+    "    json.dump(results, fd)"
    ]
   }
  ],