Apply ruff everywhere (notebooks and scripts)

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ ci:
   autoupdate_branch: ""
   autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
   autoupdate_schedule: quarterly
-  skip: ["verify-alpha-spec", "nbqa-isort"]
+  skip: ["verify-alpha-spec"]
   submodules: false
 
 repos:
@@ -41,13 +41,6 @@ repos:
                "python/cudf_polars/cudf_polars",
                "python/dask_cudf/dask_cudf"]
         pass_filenames: false
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.9.1
-    hooks:
-      - id: nbqa-isort
-        # Use the cudf_kafka isort orderings in notebooks so that dask
-        # and RAPIDS packages have their own sections.
-        args: ["--settings-file=python/cudf_kafka/pyproject.toml"]
   - repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v16.0.6
     hooks:
@@ -153,13 +146,11 @@ repos:
             ^CHANGELOG.md$
           )
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.0
+    rev: v0.9.3
     hooks:
       - id: ruff
         args: ["--fix"]
-        files: python/.*$
       - id: ruff-format
-        files: python/.*$
   - repo: https://github.com/rapidsai/pre-commit-hooks
     rev: v0.4.0
     hooks:

ci/cudf_pandas_scripts/fetch_pandas_versions.py

@@ -1,24 +1,34 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.
+# Copyright (c) 2024-2025, NVIDIA CORPORATION.
+
+import argparse
 
 import requests
-from packaging.version import Version
 from packaging.specifiers import SpecifierSet
-import argparse
+from packaging.version import Version
+
 
 def get_pandas_versions(pandas_range):
     url = "https://pypi.org/pypi/pandas/json"
     response = requests.get(url)
     data = response.json()
-    versions = [Version(v) for v in data['releases']]
+    versions = [Version(v) for v in data["releases"]]
     specifier = SpecifierSet(pandas_range.lstrip("pandas"))
     matching_versions = [v for v in versions if v in specifier]
-    matching_minors = sorted(set(".".join((str(v.major), str(v.minor))) for v in matching_versions), key=Version)
+    matching_minors = sorted(
+        set(".".join((str(v.major), str(v.minor))) for v in matching_versions),
+        key=Version,
+    )
     return matching_minors
 
+
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Filter pandas versions by prefix.")
-    parser.add_argument("pandas_range", type=str, help="The version prefix to filter by.")
+    parser = argparse.ArgumentParser(
+        description="Filter pandas versions by prefix."
+    )
+    parser.add_argument(
+        "pandas_range", type=str, help="The version prefix to filter by."
+    )
     args = parser.parse_args()
 
     versions = get_pandas_versions(args.pandas_range)
-    print(','.join(versions))
+    print(",".join(versions))

ci/cudf_pandas_scripts/pandas-tests/job-summary.py

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2023-2024, NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION & AFFILIATES.
 # All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
@@ -68,17 +68,27 @@ def emoji_failed(x):
 pr_df = pd.DataFrame.from_dict(pr_results, orient="index").sort_index()
 main_df = pd.DataFrame.from_dict(main_results, orient="index").sort_index()
 total_usage = main_df["_slow_function_call"] + main_df["_fast_function_call"]
-main_df["CPU Usage"] = ((main_df["_slow_function_call"] / total_usage) * 100.0).round(1)
-main_df["GPU Usage"] = ((main_df["_fast_function_call"] / total_usage) * 100.0).round(1)
+main_df["CPU Usage"] = (
+    (main_df["_slow_function_call"] / total_usage) * 100.0
+).round(1)
+main_df["GPU Usage"] = (
+    (main_df["_fast_function_call"] / total_usage) * 100.0
+).round(1)
 
 total_usage = pr_df["_slow_function_call"] + pr_df["_fast_function_call"]
-pr_df["CPU Usage"] = ((pr_df["_slow_function_call"] / total_usage) * 100.0).round(1)
-pr_df["GPU Usage"] = ((pr_df["_fast_function_call"] / total_usage) * 100.0).round(1)
+pr_df["CPU Usage"] = (
+    (pr_df["_slow_function_call"] / total_usage) * 100.0
+).round(1)
+pr_df["GPU Usage"] = (
+    (pr_df["_fast_function_call"] / total_usage) * 100.0
+).round(1)
 
 cpu_usage_mean = pr_df["CPU Usage"].mean().round(2)
 gpu_usage_mean = pr_df["GPU Usage"].mean().round(2)
 
-gpu_usage_rate_change = abs(pr_df["GPU Usage"].mean() - main_df["GPU Usage"].mean())
+gpu_usage_rate_change = abs(
+    pr_df["GPU Usage"].mean() - main_df["GPU Usage"].mean()
+)
 pr_df["CPU Usage"] = pr_df["CPU Usage"].fillna(0)
 pr_df["GPU Usage"] = pr_df["GPU Usage"].fillna(0)
 main_df["CPU Usage"] = main_df["CPU Usage"].fillna(0)
@@ -92,8 +102,12 @@ def emoji_failed(x):
 pr_df["CPU Usage"] = pr_df["CPU Usage"].astype(str) + "%"
 pr_df["GPU Usage"] = pr_df["GPU Usage"].astype(str) + "%"
 
-pr_df = pr_df[["total", "passed", "failed", "skipped", "CPU Usage", "GPU Usage"]]
-diff_df = diff_df[["total", "passed", "failed", "skipped", "CPU Usage", "GPU Usage"]]
+pr_df = pr_df[
+    ["total", "passed", "failed", "skipped", "CPU Usage", "GPU Usage"]
+]
+diff_df = diff_df[
+    ["total", "passed", "failed", "skipped", "CPU Usage", "GPU Usage"]
+]
 diff_df.columns = diff_df.columns + "_diff"
 diff_df["passed_diff"] = diff_df["passed_diff"].map(emoji_passed)
 diff_df["failed_diff"] = diff_df["failed_diff"].map(emoji_failed)

ci/utils/nbtestlog2junitxml.py

@@ -1,15 +1,16 @@
-# Copyright (c) 2020-2022, NVIDIA CORPORATION.
+# Copyright (c) 2020-2025, NVIDIA CORPORATION.
 # Generate a junit-xml file from parsing a nbtest log
 
 import re
-from xml.etree.ElementTree import Element, ElementTree
-from os import path
 import string
 from enum import Enum
-
+from os import path
+from xml.etree.ElementTree import Element, ElementTree
 
 startingPatt = re.compile(r"^STARTING: ([\w\.\-]+)$")
-skippingPatt = re.compile(r"^SKIPPING: ([\w\.\-]+)\s*(\(([\w\.\-\ \,]+)\))?\s*$")
+skippingPatt = re.compile(
+    r"^SKIPPING: ([\w\.\-]+)\s*(\(([\w\.\-\ \,]+)\))?\s*$"
+)
 exitCodePatt = re.compile(r"^EXIT CODE: (\d+)$")
 folderPatt = re.compile(r"^FOLDER: ([\w\.\-]+)$")
 timePatt = re.compile(r"^real\s+([\d\.ms]+)$")
@@ -37,12 +38,8 @@ def makeFailureElement(outputLines):
 
 
 def setFileNameAttr(attrDict, fileName):
-    attrDict.update(file=fileName,
-                    classname="",
-                    line="",
-                    name="",
-                    time=""
-                   )
+    attrDict.update(file=fileName, classname="", line="", name="", time="")
+
 
 def setClassNameAttr(attrDict, className):
     attrDict["classname"] = className
@@ -76,11 +73,12 @@ def parseLog(logFile, testSuiteElement):
         testSuiteElement.attrib["timestamp"] = ""
 
         attrDict = {}
-        #setFileNameAttr(attrDict, logFile)
+        # setFileNameAttr(attrDict, logFile)
         setFileNameAttr(attrDict, "nbtest")
 
-        parserStateEnum = Enum("parserStateEnum",
-                               "newTest startingLine finishLine exitCode")
+        parserStateEnum = Enum(
+            "parserStateEnum", "newTest startingLine finishLine exitCode"
+        )
         parserState = parserStateEnum.newTest
 
         testOutput = ""
@@ -98,7 +96,9 @@ def parseLog(logFile, testSuiteElement):
                     setTimeAttr(attrDict, "0m0s")
                     skippedElement = makeTestCaseElement(attrDict)
                     message = m.group(3) or ""
-                    skippedElement.append(Element("skipped", message=message, type=""))
+                    skippedElement.append(
+                        Element("skipped", message=message, type="")
+                    )
                     testSuiteElement.append(skippedElement)
                     incrNumAttr(testSuiteElement, "skipped")
                     incrNumAttr(testSuiteElement, "tests")
@@ -160,4 +160,6 @@ def parseLog(logFile, testSuiteElement):
     testSuiteElement = Element("testsuite", name="nbtest", hostname="")
     parseLog(sys.argv[1], testSuiteElement)
     testSuitesElement.append(testSuiteElement)
-    ElementTree(testSuitesElement).write(sys.argv[1]+".xml", xml_declaration=True)
+    ElementTree(testSuitesElement).write(
+        sys.argv[1] + ".xml", xml_declaration=True
+    )

cpp/scripts/sort_ninja_log.py

@@ -4,13 +4,12 @@
 import argparse
 import os
 import re
-import sys
-import xml.etree.ElementTree as ET
 from pathlib import Path
-from xml.dom import minidom
 
 parser = argparse.ArgumentParser()
-parser.add_argument("log_file", type=str, default=".ninja_log", help=".ninja_log file")
+parser.add_argument(
+    "log_file", type=str, default=".ninja_log", help=".ninja_log file"
+)
 parser.add_argument(
     "--fmt",
     type=str,
@@ -146,8 +145,8 @@ def format_file_size(input_size):
 
 
 def replace_placeholder_patterns(input_string: str) -> str:
-    pattern = r'(_h_env_placehold)[_placehold]+'
-    return re.sub(pattern, r'\1...', input_string)
+    pattern = r"(_h_env_placehold)[_placehold]+"
+    return re.sub(pattern, r"\1...", input_string)
 
 
 # adjust name for display
@@ -262,7 +261,9 @@ def output_html(entries, sorted_list, cmp_entries, args):
 
     # output detail table in build-time descending order
     print("<table id='detail' bgcolor='#EEEEEE'>")
-    print("<tr><th>File</th>", "<th>Compile time</th>", "<th>Size</th>", sep="")
+    print(
+        "<tr><th>File</th>", "<th>Compile time</th>", "<th>Size</th>", sep=""
+    )
     if cmp_entries:
         print("<th>t-cmp</th>", sep="")
     print("</tr>")
@@ -282,7 +283,9 @@ def output_html(entries, sorted_list, cmp_entries, args):
         print("<td align='right'>", build_time_str, "</td>", sep="", end="")
         print("<td align='right'>", file_size_str, "</td>", sep="", end="")
         # output diff column
-        cmp_entry = cmp_entries[name] if cmp_entries and name in cmp_entries else None
+        cmp_entry = (
+            cmp_entries[name] if cmp_entries and name in cmp_entries else None
+        )
         if cmp_entry:
             diff_time = build_time - (cmp_entry[1] - cmp_entry[0])
             diff_time_str = format_build_time(diff_time)
@@ -347,7 +350,9 @@ def output_csv(entries, sorted_list, cmp_entries, args):
         entry = entries[name]
         build_time = entry[1] - entry[0]
         file_size = entry[2]
-        cmp_entry = cmp_entries[name] if cmp_entries and name in cmp_entries else None
+        cmp_entry = (
+            cmp_entries[name] if cmp_entries and name in cmp_entries else None
+        )
         print(build_time, file_size, name, sep=",", end="")
         if cmp_entry:
             diff_time = build_time - (cmp_entry[1] - cmp_entry[0])

docs/cudf/source/_ext/PandasCompat.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2024, NVIDIA CORPORATION
+# Copyright (c) 2021-2025, NVIDIA CORPORATION
 
 # This file is adapted from official sphinx tutorial for `todo` extension:
 # https://www.sphinx-doc.org/en/master/development/tutorials/todo.html
@@ -7,7 +7,6 @@
 from typing import cast
 
 from docutils import nodes
-from docutils.nodes import Element
 from docutils.parsers.rst import Directive
 from docutils.parsers.rst.directives.admonitions import BaseAdmonition
 from sphinx import addnodes
@@ -39,7 +38,6 @@ def run(self):
 
 
 class PandasCompatDirective(BaseAdmonition, SphinxDirective):
-
     # this enables content in the directive
     has_content = True
 
@@ -119,18 +117,24 @@ def __init__(self, app, doctree, docname):
         self.builder = app.builder
         self.config = app.config
         self.env = app.env
-        self.domain = cast(PandasCompatDomain, app.env.get_domain("pandascompat"))
+        self.domain = cast(
+            PandasCompatDomain, app.env.get_domain("pandascompat")
+        )
         self.document = new_document("")
         self.process(doctree, docname)
 
     def process(self, doctree: nodes.document, docname: str) -> None:
-        pandascompats = [v for vals in self.domain.pandascompats.values() for v in vals]
+        pandascompats = [
+            v for vals in self.domain.pandascompats.values() for v in vals
+        ]
         for node in doctree.findall(PandasCompatList):
             if not self.config.include_pandas_compat:
                 node.parent.remove(node)
                 continue
 
-            content: list[Element | None] = [nodes.target()] if node.get("ids") else []
+            content: list[nodes.Element | None] = (
+                [nodes.target()] if node.get("ids") else []
+            )
 
             for pandascompat in pandascompats:
                 # Create a copy of the pandascompat node
@@ -149,13 +153,16 @@ def create_reference(self, pandascompat, docname):
         para = nodes.paragraph()
         newnode = nodes.reference("", "")
         innernode = nodes.emphasis(
-            get_translation_sphinx("[source]"), get_translation_sphinx("[source]")
+            get_translation_sphinx("[source]"),
+            get_translation_sphinx("[source]"),
         )
         newnode["refdocname"] = pandascompat["docname"]
         try:
-            newnode["refuri"] = self.builder.get_relative_uri(
-                docname, pandascompat["docname"]
-            ) + "#" + pandascompat["target"]["refid"]
+            newnode["refuri"] = (
+                self.builder.get_relative_uri(docname, pandascompat["docname"])
+                + "#"
+                + pandascompat["target"]["refid"]
+            )
         except NoUri:
             # ignore if no URI can be determined, e.g. for LaTeX output
             pass

docs/cudf/source/conf.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2018-2024, NVIDIA CORPORATION.
+# Copyright (c) 2018-2025, NVIDIA CORPORATION.
 #
 # cudf documentation build configuration file, created by
 # sphinx-quickstart on Wed May  3 10:59:22 2017.
@@ -36,7 +36,7 @@
 from pygments.token import Text as PText
 from sphinx.addnodes import pending_xref
 from sphinx.ext import intersphinx
-from sphinx.ext.autodoc import ClassDocumenter, bool_option
+from sphinx.ext.autodoc import ClassDocumenter
 from sphinx.highlighting import lexers
 
 
@@ -694,15 +694,16 @@ def add_content(self, more_content) -> None:
         enum_object: IntEnum = self.object
 
         if self.object.__name__ != "Kind":
-            self.add_line(f"See also :cpp:enum:`cudf::{self.object.__name__}`.", source_name)
+            self.add_line(
+                f"See also :cpp:enum:`cudf::{self.object.__name__}`.",
+                source_name,
+            )
         self.add_line("", source_name)
         self.add_line("Enum members", source_name)
         self.add_line("", source_name)
 
         for the_member_name in enum_object.__members__:  # type: ignore[attr-defined]
-            self.add_line(
-                f"* ``{the_member_name}``", source_name
-            )
+            self.add_line(f"* ``{the_member_name}``", source_name)
             self.add_line("", source_name)
 
 

docs/cudf/source/user_guide/10min.ipynb

@@ -37,12 +37,11 @@
    "source": [
     "import os\n",
     "\n",
+    "import cudf\n",
     "import cupy as cp\n",
     "import dask_cudf\n",
     "import pandas as pd\n",
     "\n",
-    "import cudf\n",
-    "\n",
     "cp.random.seed(12)\n",
     "\n",
     "#### Portions of this were borrowed and adapted from the\n",