feat(ruff): enable flake8-comprehensions, flake8-copyright, flake8-da…

…tetimez (#22610)

.ruff.toml

@@ -179,9 +179,12 @@ select = [
   "ASYNC", # flake8-async
   "B",     # flake8-bugbear
   "BLE",   # flake8-blind-except
+  "C4",    # flake8-comprehensions
   "C90",   # mccabe
   "COM",   # flake8-commas
+  "CPY",   # flake8-copyright
   "D",     # pydocstyle
+  "DTZ",   # flake8-datetimez
   "E",     # pycodestyle
   "EM",    # flake8-errmsg
   "EXE",   # flake8-executable

aerospace/hm-aerosandbox/src/main.py

@@ -113,7 +113,7 @@ def main() -> None:
     aero = vlm.run()
     for k, v in aero.items():
         logger.info(f"{k.rjust(4)} : {v}")
-    vlm.draw(show_kwargs=dict(jupyter_backend="static"))
+    vlm.draw(show_kwargs={"jupyter_backend": "static"})
 
     # Operating Point Optimization
     opti = asb.Opti()
@@ -161,7 +161,7 @@ def main() -> None:
     opti.minimize(aero["CD"])
     sol = opti.solve()
     vlm = sol(vlm)
-    vlm.draw(show_kwargs=dict(jupyter_backend="static"))
+    vlm.draw(show_kwargs={"jupyter_backend": "static"})
 
     # Compare our optimized solution with known analytic solution (an elliptical lift distribution)
     plt.plot(

data-orchestration/hm-airflow/dags/greet.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import UTC, datetime
 
 from airflow.decorators import task, task_group
 from airflow.models import DAG
@@ -7,7 +7,7 @@
 
 with DAG(
     "greet",
-    start_date=datetime(2022, 1, 1),
+    start_date=datetime(2022, 1, 1, tzinfo=UTC),
     schedule_interval="@once",
     catchup=False,
     params={
@@ -52,7 +52,7 @@ def greet(initials: str, ti: TaskInstance | None = None) -> str:
         if time is None:
             msg = "Failed to get time from xcom"
             raise ValueError(msg)
-        dt = datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
+        dt = datetime.strptime(time, "%Y-%m-%d %H:%M:%S").astimezone(UTC)
         return f"Hello {initials}, {dt.strftime('at %H:%M on %B %d, %Y')}!"
 
     @task_group

data-orchestration/hm-airflow/dags/s3_download.py

@@ -1,5 +1,5 @@
 import os
-from datetime import datetime
+from datetime import UTC, datetime
 from pathlib import Path
 
 from airflow import DAG
@@ -8,7 +8,7 @@
 
 with DAG(
     "s3_download",
-    start_date=datetime(2022, 1, 1),
+    start_date=datetime(2022, 1, 1, tzinfo=UTC),
     schedule_interval="@once",
     catchup=False,
 ) as dag:

data-processing/hm-spark/applications/find-taxi-top-routes-sql/src/utils/trip.py

@@ -8,5 +8,5 @@ def load_trips(spark: SparkSession, data_paths: list[str]) -> DataFrame:
 
 
 def preprocess_trips(df: DataFrame) -> DataFrame:
-    column_names = list(map(lambda x: x.lower(), df.columns))
+    column_names = [x.lower() for x in df.columns]
     return df.toDF(*column_names)

data-processing/hm-spark/applications/find-taxi-top-routes-sql/src/utils/zone.py

@@ -11,6 +11,6 @@ def load_zones(spark: SparkSession, zone_data_path: str) -> DataFrame:
 
 
 def preprocess_zones(df: DataFrame) -> DataFrame:
-    column_names = list(map(lambda x: x.lower(), df.columns))
+    column_names = [x.lower() for x in df.columns]
     df = df.toDF(*column_names)
     return df.drop("objectid")

data-processing/hm-spark/applications/find-taxi-top-routes/src/utils/trip.py

@@ -8,5 +8,5 @@ def load_trips(spark: SparkSession, data_paths: list[str]) -> DataFrame:
 
 
 def preprocess_trips(df: DataFrame) -> DataFrame:
-    column_names = list(map(lambda x: x.lower(), df.columns))
+    column_names = [x.lower() for x in df.columns]
     return df.toDF(*column_names)

data-processing/hm-spark/applications/find-taxi-top-routes/src/utils/zone.py

@@ -11,6 +11,6 @@ def load_zones(spark: SparkSession, zone_data_path: str) -> DataFrame:
 
 
 def preprocess_zones(df: DataFrame) -> DataFrame:
-    column_names = list(map(lambda x: x.lower(), df.columns))
+    column_names = [x.lower() for x in df.columns]
     df = df.toDF(*column_names)
     return df.drop("objectid")

data-visualization/iads/iads-data-manager/iads-data-reader/src/utils/iads_util.py

@@ -3,7 +3,7 @@
 import shutil
 import subprocess
 import tempfile
-from datetime import datetime
+from datetime import UTC, datetime
 from decimal import Decimal
 from pathlib import Path
 from typing import Any
@@ -61,7 +61,7 @@ def get_irig_times(iads_metadata_path: Path) -> tuple[str, str, int]:
                 elif line.startswith("FlightDate"):
                     # Parse date using datetime (format: MM/DD/YY)
                     date_str = line.split("=")[1].strip()
-                    date = datetime.strptime(date_str, "%m/%d/%y")
+                    date = datetime.strptime(date_str, "%m/%d/%y").astimezone(UTC)
                     year = date.year
 
         if not irig_start_time or not irig_end_time or year is None:

embedded-systems/decode-can-data/src/main.py

@@ -104,7 +104,7 @@ def initialize_schema_dict(
         unit_dict: dict[str, dict[str, str]],
     ) -> dict[str, pa.Schema]:
         schema_dict = {}
-        unique_types = set(unit["type"] for unit in unit_dict.values())
+        unique_types = {unit["type"] for unit in unit_dict.values()}
         for unit_type in unique_types:
             if unit_type not in schema_dict:
                 schema_dict[unit_type] = CanUtils.get_dbc_schema(dbc_dict, unit_type)

machine-learning/feature-store/generate_training_data.py

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import UTC, datetime, timedelta
 
 import pandas as pd
 from feast import FeatureStore
@@ -10,9 +10,9 @@
         "driver_id": [1001, 1002, 1003],
         "label_driver_reported_satisfaction": [1, 5, 3],
         "event_timestamp": [
-            datetime.now() - timedelta(minutes=11),
-            datetime.now() - timedelta(minutes=36),
-            datetime.now() - timedelta(minutes=73),
+            datetime.now(tz=UTC) - timedelta(minutes=11),
+            datetime.now(tz=UTC) - timedelta(minutes=36),
+            datetime.now(tz=UTC) - timedelta(minutes=73),
         ],
     },
 )

machine-learning/hm-faster-whisper/src/main.py

@@ -17,7 +17,7 @@ def main(audio_path: Path, transcription_file: Path) -> None:
         audio_path,
         beam_size=5,
         vad_filter=True,
-        vad_parameters=dict(min_silence_duration_ms=500, speech_pad_ms=400),
+        vad_parameters={"min_silence_duration_ms": 500, "speech_pad_ms": 400},
         language="en",
         task="transcribe",
         initial_prompt=None,

machine-learning/hm-rasa/actions/actions.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import UTC, datetime
 from typing import Any
 
 from rasa_sdk import Action, FormValidationAction, Tracker
@@ -16,7 +16,7 @@ def run(
         tracker: Tracker,
         domain: dict[str, Any],
     ) -> list[dict[str, Any]]:
-        now = datetime.now()
+        now = datetime.now(tz=UTC)
         dispatcher.utter_message(text=f"{now}")
         return []
 

machine-learning/hm-streamlit/applications/live-line-chart/src/main.py

@@ -1,5 +1,5 @@
 import time
-from datetime import datetime
+from datetime import UTC, datetime
 
 import numpy as np
 import polars as pl
@@ -23,7 +23,7 @@ def main() -> None:
     placeholder = st.empty()
 
     while True:
-        current_time = datetime.now()
+        current_time = datetime.now(tz=UTC)
         new_data_point = (
             generator.standard_normal(2) / 10.0 + prev_values
             if prev_values is not None

machine-learning/stable-diffusion/src/main.py

@@ -1,6 +1,6 @@
 import logging
 import secrets
-from datetime import datetime
+from datetime import UTC, datetime
 from pathlib import Path
 
 import torch
@@ -87,7 +87,7 @@ def generate_images(
 
             # Save images
             for idx, image in enumerate(result.images):
-                timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+                timestamp = datetime.now(tz=UTC).strftime("%Y%m%d_%H%M%S")
                 path = output_dir / f"{timestamp}_{idx}.png"
                 image.save(path)