refactor(python): add timestamp for logger (#22176)

aerospace/hm-aerosandbox/src/main.py

@@ -7,6 +7,8 @@
 import aerosandbox.tools.pretty_plots as p
 import matplotlib.pyplot as plt
 
+logger = logging.getLogger(__name__)
+
 
 def main() -> None:
     wing_airfoil = asb.Airfoil("sd7037")
@@ -110,7 +112,7 @@ def main() -> None:
     )
     aero = vlm.run()
     for k, v in aero.items():
-        logging.info(f"{k.rjust(4)} : {v}")
+        logger.info(f"{k.rjust(4)} : {v}")
     vlm.draw(show_kwargs=dict(jupyter_backend="static"))
 
     # Operating Point Optimization
@@ -126,7 +128,7 @@ def main() -> None:
     opti.minimize(-L_over_D)
     sol = opti.solve()
     best_alpha = sol(alpha)
-    logging.info(f"Alpha for max L/D: {best_alpha:.3f} deg")
+    logger.info(f"Alpha for max L/D: {best_alpha:.3f} deg")
 
     # Aerodynamic Shape Optimization
     opti = asb.Opti()
@@ -183,5 +185,7 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
     main()

aerospace/hm-openaerostruct/src/main.py

@@ -7,6 +7,8 @@
 from openaerostruct.geometry.utils import generate_mesh
 from openmdao.api import n2
 
+logger = logging.getLogger(__name__)
+
 
 def main() -> None:
     # Create a dictionary to store options about the mesh
@@ -102,5 +104,7 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
     main()

api-rust/scripts/download_model.py

@@ -5,6 +5,8 @@
 import torch
 import torchvision.models as models
 
+logger = logging.getLogger(__name__)
+
 
 def download_labels():
     labels_url = (
@@ -13,30 +15,32 @@ def download_labels():
     labels_path = Path("models/labels.txt")
 
     if not labels_path.exists():
-        logging.info("Downloading labels...")
+        logger.info("Downloading labels...")
         with httpx.Client() as client:
             response = client.get(labels_url)
             labels_path.write_bytes(response.content)
-        logging.info("Labels downloaded successfully")
+        logger.info("Labels downloaded successfully")
     else:
-        logging.info("Labels file already exists")
+        logger.info("Labels file already exists")
 
 
 def download_resnet18():
     model_path = Path("models/resnet18.ot")
 
     if not model_path.exists():
-        logging.info("Downloading ResNet18...")
+        logger.info("Downloading ResNet18...")
         model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
         model.eval()
         traced_model = torch.jit.trace(model, torch.randn(1, 3, 224, 224))
         traced_model.save(model_path)
-        logging.info("Model downloaded and saved successfully")
+        logger.info("Model downloaded and saved successfully")
     else:
-        logging.info("Model file already exists")
+        logger.info("Model file already exists")
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
     download_resnet18()
     download_labels()

cloud-computing/hm-ray/applications/calculate/src/main.py

@@ -3,6 +3,8 @@
 
 import ray
 
+logger = logging.getLogger(__name__)
+
 
 @ray.remote
 def square(n: int) -> int:
@@ -16,17 +18,19 @@ def sum_list(numbers: list[int]) -> int:
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
     ray.init()
-    logging.info(ray.cluster_resources())
+    logger.info(ray.cluster_resources())
 
     numbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
     squared_tasks = [square.remote(n) for n in numbers]
     squared_results: list[int] = ray.get(squared_tasks)
-    logging.info(f"{squared_results = }")
+    logger.info(f"{squared_results = }")
 
     sum_task = sum_list.remote(squared_results)
     total_sum = ray.get(sum_task)
-    logging.info(f"{total_sum = }")
+    logger.info(f"{total_sum = }")
 
     ray.shutdown()

cloud-computing/hm-ray/applications/process-flight-data/src/main.py

@@ -7,6 +7,8 @@
 import pandas as pd
 import ray
 
+logger = logging.getLogger(__name__)
+
 
 @ray.remote
 def process_flight_data(
@@ -36,10 +38,12 @@ def process_flight_data(
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
 
     ray.init()
-    logging.info(ray.cluster_resources())
+    logger.info(ray.cluster_resources())
 
     mlflow_tracking_server_host = config.MLFLOW_TRACKING_SERVER_HOST
     mlflow_tracking_server_user_name = config.MLFLOW_TRACKING_USERNAME
@@ -88,7 +92,7 @@ def process_flight_data(
 
     results = ray.get(tasks)
     for i, df_head in enumerate(results):
-        logging.info(f"Experiment {i}")
-        logging.info(f"{df_head = }")
+        logger.info(f"Experiment {i}")
+        logger.info(f"{df_head = }")
 
     ray.shutdown()

cloud-infrastructure/terraform/environments/production/aws/general/files/aws-glue/spark-scripts/src/hm_write_parquet_to_delta_table_adsb_2x_flight_trace_data.py

@@ -9,7 +9,10 @@
 from pyspark.sql import DataFrame
 from pyspark.sql.functions import col, concat, date_format, from_unixtime, lit, when
 
-logging.basicConfig(level=logging.INFO)
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+)
+logger = logging.getLogger(__name__)
 
 raw_parquet_paths = [
     "s3://hm-production-bucket/data/raw-parquet/adsb_2x_flight_trace_data/"
@@ -142,7 +145,7 @@ def add_coordinate_column(
 df = s3_node.toDF()
 
 if df.isEmpty():
-    logging.info("DataFrame is empty.")
+    logger.info("DataFrame is empty.")
     job.commit()
     os._exit(os.EX_OK)
 

cloud-infrastructure/terraform/environments/production/aws/general/files/aws-glue/spark-scripts/src/hm_write_parquet_to_delta_table_motor_data.py

@@ -7,7 +7,10 @@
 from awsglue.utils import getResolvedOptions
 from pyspark.context import SparkContext
 
-logging.basicConfig(level=logging.INFO)
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+)
+logger = logging.getLogger(__name__)
 
 raw_parquet_paths = ["s3://hm-production-bucket/data/parquet/motor/"]
 delta_table_path = "s3://hm-production-bucket/data/delta-tables/motor_data/"
@@ -34,7 +37,7 @@
 df = s3_node.toDF()
 
 if df.isEmpty():
-    logging.info("DataFrame is empty.")
+    logger.info("DataFrame is empty.")
     job.commit()
     os._exit(os.EX_OK)
 

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/get_test_data_loader.py

@@ -5,9 +5,11 @@
 import torch.utils.data.distributed
 from torchvision import datasets, transforms
 
+logger = logging.getLogger(__name__)
+
 
 def get_test_data_loader(test_batch_size, training_dir, **kwargs):
-    logging.info("Get test data loader")
+    logger.info("Get test data loader")
     return torch.utils.data.DataLoader(
         datasets.MNIST(
             training_dir,

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/get_train_data_loader.py

@@ -5,9 +5,11 @@
 import torch.utils.data.distributed
 from torchvision import datasets, transforms
 
+logger = logging.getLogger(__name__)
+
 
 def get_train_data_loader(batch_size, training_dir, is_distributed, **kwargs):
-    logging.info("Get train data loader")
+    logger.info("Get train data loader")
     dataset = datasets.MNIST(
         training_dir,
         train=True,

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/save_model.py

@@ -5,8 +5,10 @@
 import torch.utils.data
 import torch.utils.data.distributed
 
+logger = logging.getLogger(__name__)
+
 
 def save_model(model, model_dir):
-    logging.info("Save the model.")
+    logger.info("Save the model.")
     path = os.path.join(model_dir, "model.pth")
     torch.save(model.cpu().state_dict(), path)

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/test.py

@@ -5,6 +5,8 @@
 import torch.utils.data
 import torch.utils.data.distributed
 
+logger = logging.getLogger(__name__)
+
 
 def test(model, test_loader, device):
     model.eval()
@@ -21,7 +23,7 @@ def test(model, test_loader, device):
             correct += pred.eq(target.view_as(pred)).sum().item()
 
     test_loss /= len(test_loader.dataset)
-    logging.info(
+    logger.info(
         "Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n".format(
             test_loss,
             correct,

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/train.py

@@ -14,13 +14,15 @@
 from utils.save_model import save_model
 from utils.test import test
 
+logger = logging.getLogger(__name__)
+
 
 def train(args):
     is_distributed = len(args.hosts) > 1 and args.backend is not None
-    logging.info("Distributed training:", is_distributed)
+    logger.info("Distributed training:", is_distributed)
 
     use_cuda = args.num_gpus > 0
-    logging.info("Number of gpus available:", args.num_gpus)
+    logger.info("Number of gpus available:", args.num_gpus)
     kwargs = {"num_workers": 1, "pin_memory": True} if use_cuda else {}
     device = torch.device("cuda" if use_cuda else "cpu")
 
@@ -33,7 +35,7 @@ def train(args):
         dist.init_process_group(
             backend=args.backend, rank=host_rank, world_size=world_size
         )
-        logging.info(
+        logger.info(
             "Initialized the distributed environment: '{}' backend on {} nodes. ".format(
                 args.backend, dist.get_world_size()
             )
@@ -52,15 +54,15 @@ def train(args):
     )
     test_loader = get_test_data_loader(args.test_batch_size, args.data_dir, **kwargs)
 
-    logging.info(
+    logger.info(
         "Processes {}/{} ({:.0f}%) of train data".format(
             len(train_loader.sampler),
             len(train_loader.dataset),
             100.0 * len(train_loader.sampler) / len(train_loader.dataset),
         )
     )
 
-    logging.info(
+    logger.info(
         "Processes {}/{} ({:.0f}%) of test data".format(
             len(test_loader.sampler),
             len(test_loader.dataset),
@@ -91,7 +93,7 @@ def train(args):
                 average_gradients(model)
             optimizer.step()
             if batch_idx % args.log_interval == 0:
-                logging.info(
+                logger.info(
                     "Train Epoch: {} [{}/{} ({:.0f}%)] Loss: {:.6f}".format(
                         epoch,
                         batch_idx * len(data),

computer-vision/hm-imagebind/src/main.py

@@ -10,6 +10,7 @@
 from lancedb.pydantic import LanceModel, Vector
 from lancedb.table import Table
 
+logger = logging.getLogger(__name__)
 EMBEDDINGS = get_registry().get("imagebind").create()
 DATA_DIR = Path("data")
 
@@ -54,7 +55,7 @@ def download_file(client: httpx.Client, url: str, is_audio: bool = True) -> Path
         if response.status_code == 200:
             with open(local_file_path, "wb") as file:
                 file.write(response.content)
-                logging.info(f"Downloaded file: {local_file_path}")
+                logger.info(f"Downloaded file: {local_file_path}")
             return local_file_path
         else:
             raise RuntimeError(f"Download failed: {response}")
@@ -164,5 +165,7 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    logging.basicConfig(level=logging.INFO)
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
     main()