Use configure_logger to set same format to all log prints (#385)

Co-authored-by: Jonathan Liberman <[email protected]>

Author: shayts7

.github/workflows/license-check.yml

@@ -50,8 +50,11 @@ jobs:
         with:
           requirements: "backend/requirements-all.txt"
           fail: "Copyleft,Other,Error"
-          exclude: '(envier.*0\.5\.0|psycopg2.*2\.9\.3|fqdn.*1\.5\.1|pyzmq.*25\.1\.2|debugpy.*1\.6\.7|certifi.*2024\.8\.30|tqdm.*4\.67\..*|webencodings.*0\.5\.1|torch.*1\.10\.2.*|torch.*1\.11\.0.*|pytorch-ignite.*0\.4\.10.*|torchaudio.*0\.11\.0.*|torchvision.*0\.12\.0.*|terminado.*0\.15\.0|qudida.*0\.0\.4|expiringdict.*1\.2\.2|botocore.*1\.29\.80|orderedmultidict.*1\.0\.1|deepchecks.*)'
+          exclude: '(category_encoders.*2\.7\..*|attrs.*25\.1\..*|referencing.*0\.36\..*|envier.*0\.5\.0|psycopg2.*2\.9\.3|fqdn.*1\.5\.1|pyzmq.*25\.1\.2|debugpy.*1\.6\.7|certifi.*2025\.1\.31|tqdm.*4\.67\..*|webencodings.*0\.5\.1|torch.*1\.10\.2.*|torch.*1\.11\.0.*|pytorch-ignite.*0\.4\.10.*|torchaudio.*0\.11\.0.*|torchvision.*0\.12\.0.*|terminado.*0\.15\.0|qudida.*0\.0\.4|expiringdict.*1\.2\.2|botocore.*1\.29\.80|orderedmultidict.*1\.0\.1|deepchecks.*)'
           # psycopg2 is LGPL 2
+          # category_encoders is BSD https://github.com/scikit-learn-contrib/category_encoders/tree/master?tab=BSD-3-Clause-1-ov-file
+          # attrs is MIT https://github.com/python-attrs/attrs/blob/main/LICENSE
+          # referencing is MIT https://github.com/python-jsonschema/referencing?tab=MIT-1-ov-file
           # pyzmq is Revised BSD https://github.com/zeromq/pyzmq/blob/main/examples/LICENSE
           # debugpy is MIT https://github.com/microsoft/debugpy/blob/main/LICENSE
           # certifi is MPL-2.0 https://github.com/certifi/python-certifi/blob/master/LICENSE

backend/deepchecks_monitoring/bgtasks/alert_task.py

@@ -112,7 +112,7 @@ async def execute_monitor(
         logger: t.Optional[logging.Logger] = None,
 ) -> t.List[Alert]:
     """Execute monitor alert rules."""
-    logger = logger or logging.getLogger('monitor-executor')
+    logger = logger or configure_logger('monitor-executor')
     logger.info('Execution of Monitor(id:%s) for timestamp %s', monitor_id, timestamp)
 
     monitor = t.cast(Monitor, await session.scalar(

backend/deepchecks_monitoring/bgtasks/scheduler.py

@@ -67,7 +67,7 @@ def __init__(
         self.engine = engine
         self.async_session_factory = sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
         self.sleep_seconds = sleep_seconds
-        self.logger = logger or logging.getLogger('alerts-scheduler')
+        self.logger = logger or configure_logger('alerts-scheduler')
 
     async def run(self):
         """Start alert scheduler."""

backend/deepchecks_monitoring/ee/integrations/slack.py

@@ -14,6 +14,7 @@
 from deepchecks_monitoring.ee.config import SlackSettings
 from deepchecks_monitoring.monitoring_utils import CheckParameterTypeEnum as CheckParameterKind
 from deepchecks_monitoring.monitoring_utils import MonitorCheckConfSchema as MonitorConfig
+from deepchecks_monitoring.monitoring_utils import configure_logger
 from deepchecks_monitoring.schema_models import Alert, AlertRule, AlertSeverity, Check, Model, Monitor
 from deepchecks_monitoring.utils.alerts import prepare_alert_link
 from deepchecks_monitoring.utils.text import format_float
@@ -84,7 +85,7 @@ def __init__(
     ):
         self.settings = settings
         self.client = SlackClient()
-        self.logger = logger or logging.getLogger("slack.installation")
+        self.logger = logger or configure_logger("slack.installation")
         self.state_utils = OAuthStateUtils()
 
     def generate_authorization_url(self, state, redirect_path) -> str:

backend/deepchecks_monitoring/ee/middlewares.py

@@ -19,6 +19,7 @@
 from starlette.types import ASGIApp, Message, Receive, Scope, Send
 
 from deepchecks_monitoring.exceptions import LicenseError
+from deepchecks_monitoring.monitoring_utils import configure_logger
 from deepchecks_monitoring.public_models import User
 from deepchecks_monitoring.utils.auth import CurrentUser
 
@@ -82,7 +83,7 @@ def __init__(
             log_stream_name=log_stream_name,
         )
         h.setLevel(logging.INFO)
-        self.logger = logging.getLogger("access-audit")
+        self.logger = configure_logger("access-audit")
         self.logger.addHandler(h)
         self.app = app
 

backend/deepchecks_monitoring/ee/resources.py

@@ -18,6 +18,7 @@
 from deepchecks_monitoring.ee.notifications import AlertNotificator as EEAlertNotificator
 from deepchecks_monitoring.features_control import FeaturesControl
 from deepchecks_monitoring.integrations.email import EmailSender
+from deepchecks_monitoring.monitoring_utils import configure_logger
 from deepchecks_monitoring.public_models import User
 from deepchecks_monitoring.resources import ResourcesProvider as OpenSourceResourcesProvider
 
@@ -27,6 +28,8 @@
 
 __all__ = ["ResourcesProvider"]
 
+logger: logging.Logger = configure_logger("server")
+
 
 class ResourcesProvider(OpenSourceResourcesProvider):
     """Provider of resources."""
@@ -64,7 +67,7 @@ def get_features_control(self, user: User) -> FeaturesControl:
     def parallel_check_executors_pool(self) -> "ActorPool | None":
         parallel_check_executor_flag = self.settings.parallel_check_executor_flag
 
-        logging.getLogger("server").info({
+        logger.info({
             "mesage": f"'parallelCheckExecutorEnabled' is set to {parallel_check_executor_flag}"
         })
         if parallel_check_executor_flag:

backend/deepchecks_monitoring/integrations/email.py

@@ -21,12 +21,13 @@
 from typing_extensions import Self
 
 from deepchecks_monitoring.config import EmailSettings
+from deepchecks_monitoring.monitoring_utils import configure_logger
 
 # TODO: change this
 TEMPLATES_DIR = pathlib.Path(__file__).absolute().parent.parent / "templates"
 templates = Jinja2Templates(directory=str(TEMPLATES_DIR))
 
-logger: logging.Logger = logging.getLogger(__name__)
+logger: logging.Logger = configure_logger(__name__)
 
 
 class Recepient(BaseModel):

backend/deepchecks_monitoring/logic/model_logic.py

@@ -22,7 +22,8 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.orm import selectinload
 
-from deepchecks_monitoring.monitoring_utils import CheckParameterTypeEnum, MonitorCheckConfSchema, fetch_or_404
+from deepchecks_monitoring.monitoring_utils import (CheckParameterTypeEnum, MonitorCheckConfSchema, configure_logger,
+                                                    fetch_or_404)
 from deepchecks_monitoring.schema_models import Check, Model, ModelVersion
 from deepchecks_monitoring.schema_models.column_type import (SAMPLE_LABEL_COL, SAMPLE_PRED_COL, SAMPLE_PRED_PROBA_COL,
                                                              SAMPLE_TS_COL, ColumnType)
@@ -33,6 +34,8 @@
 
 DEFAULT_N_SAMPLES = 5000
 
+logger: logging.Logger = configure_logger('monitor_run_logger')
+
 
 async def get_model_versions_for_time_range(session: AsyncSession,
                                             model_id: int,
@@ -317,7 +320,7 @@ def run_deepchecks(
             if not (msg := getattr(e, 'message', None))
             else msg
         )
-        logging.getLogger('monitor_run_logger').exception(
+        logger.exception(
             'For model(id=%s) version(id=%s) check(%s) '
             'got exception: %s',
             model.id,
@@ -372,7 +375,7 @@ async def get_results_for_model_versions_for_reference(
         except errors.DeepchecksBaseError as e:
             message = f'For model(id={model.id}) version(id={model_version.id}) check({dp_check.name()}) ' \
                 f'got exception: {e.message}'
-            logging.getLogger('monitor_run_logger').error(message)
+            logger.error(message)
             curr_result = None
 
         reduced_outs.append({'result': curr_result})

backend/deepchecks_monitoring/notifications.py

@@ -19,6 +19,7 @@
 from typing_extensions import Self
 
 from deepchecks_monitoring import __version__
+from deepchecks_monitoring.monitoring_utils import configure_logger
 from deepchecks_monitoring.public_models import Organization, User
 from deepchecks_monitoring.schema_models import Check, Model
 from deepchecks_monitoring.schema_models.alert import Alert
@@ -85,7 +86,7 @@ def __init__(
         self.alert_rule = alert_rule
         self.session = session
         self.resources_provider = resources_provider
-        self.logger = logger or logging.getLogger("alert-notificator")
+        self.logger = logger or configure_logger("alert-notificator")
 
     async def send_emails(self) -> bool:
         """Send notification emails."""

backend/deepchecks_monitoring/resources.py

@@ -32,7 +32,7 @@
 from deepchecks_monitoring.features_control import FeaturesControl
 from deepchecks_monitoring.integrations.email import EmailSender
 from deepchecks_monitoring.logic.cache_functions import CacheFunctions
-from deepchecks_monitoring.monitoring_utils import ExtendedAsyncSession, json_dumps
+from deepchecks_monitoring.monitoring_utils import ExtendedAsyncSession, configure_logger, json_dumps
 from deepchecks_monitoring.notifications import AlertNotificator
 from deepchecks_monitoring.public_models import Organization
 from deepchecks_monitoring.public_models.user import User
@@ -42,6 +42,8 @@
 
 __all__ = ["ResourcesProvider"]
 
+logger: logging.Logger = configure_logger("server")
+
 
 class BaseResourcesProvider:
     """Base class for all resources provides."""
@@ -348,11 +350,11 @@ def parallel_check_executors_pool(self):
             import ray  # noqa
             from ray.util.actor_pool import ActorPool  # noqa
         except ImportError:
-            logging.getLogger("server").info({"message": "Ray is not installed"})
+            logger.info({"message": "Ray is not installed"})
             return
 
         if not ray.is_initialized():
-            logging.getLogger("server").info({
+            logger.info({
                 "message": "Ray is not initialized"
             })
             return
@@ -389,7 +391,7 @@ def shutdown_parallel_check_executors_pool(self):
         wait=tenacity.wait_fixed(1),
         retry=tenacity.retry_if_exception_type(KafkaError),
         reraise=True,
-        before_sleep=tenacity.before_sleep_log(logging.getLogger("server"), logging.WARNING),
+        before_sleep=tenacity.before_sleep_log(logger, logging.WARNING),
     )
     def ensure_kafka_topic(self, topic_name, num_partitions=1) -> bool:
         """Ensure that kafka topic exist. If not, creating it.
@@ -462,14 +464,14 @@ def _get_mixpanel_event_reporter(self) -> MixpanelEventReporter | None:
         if mixpanel is not None:
             return mixpanel
         if self.settings.enable_analytics is False:
-            logging.getLogger("server").warning({"message": "Analytics gathering is disabled"})
+            logger.warning({"message": "Analytics gathering is disabled"})
             return
         if token := self.settings.mixpanel_id:
             mixpanel = MixpanelEventReporter.from_token(token)
             self._mixpanel_event_reporter = mixpanel
             return mixpanel
 
-        logging.getLogger("server").warning({"message": "Mixpanel token is not provided"})
+        logger.warning({"message": "Mixpanel token is not provided"})
 
     def get_features_control(self, user: User) -> FeaturesControl:  # pylint: disable=unused-argument
         """Return features control."""