Implement logger for roman_photoz

roman_photoz/__init__.py

@@ -1,10 +1,16 @@
+# Import after logger setup to avoid circular imports
 from .create_simulated_catalog import SimulatedCatalog
 from .default_config_file import *  # noqa: F403
+
+# Import logger from the dedicated logger module
+from .logger import logger, setup_logging
 from .roman_catalog_handler import RomanCatalogHandler
 from .roman_catalog_process import RomanCatalogProcess
 
 __all__ = [
     "RomanCatalogProcess",
     "RomanCatalogHandler",
     "SimulatedCatalog",
+    "setup_logging",
+    "logger",
 ]

roman_photoz/create_roman_filters.py

@@ -7,6 +7,8 @@
 from lephare.data_retrieval import get_auxiliary_data
 from lephare.filter import Filter  # type: ignore
 
+from roman_photoz.logger import logger
+
 # date of the file
 DEFAULT_FILE_DATE = "20210614"
 
@@ -157,7 +159,7 @@ def create_path(filepath: str = "") -> Path:
         # save files to custom path
         path = Path(filepath).resolve()
     # create path if they don't exist
-    print("Creating directory structure...")
+    logger.info("Creating directory structure...")
     path.mkdir(parents=True, exist_ok=True)
     return path
 
@@ -191,24 +193,28 @@ def run(input_filename: str = "", input_path: str = ""):
     input_path : str
         The path where the results will be saved.
     """
+    logger.info("Starting filter file creation...")
     # create dataframe from file
     data = read_effarea_file(filename=input_filename, header=1)
 
     # get auxiliary data
+    logger.info("Getting auxiliary data...")
     get_auxiliary_data()
 
     # format and create the file for each filter
     # containing lambda vs transmission
+    logger.info("Creating individual filter files...")
     create_files(data=data, filepath=input_path)
 
     # run filter command to create the filter
     # file containing lambda vs transmission for all filters
     # (merge all the filter files created in the previous call)
+    logger.info("Running filter command to merge filter files...")
     run_filter_command(config_file_path=input_path)
+    logger.info("Filter file creation completed successfully")
 
 
 if __name__ == "__main__":
-
     # this module takes a filename as input containing
     # the monochromatic effective area of each filter per column
     # and creates one file for each filter as well as
@@ -221,4 +227,4 @@ def run(input_filename: str = "", input_path: str = ""):
 
     run(input_filename=input_filename, input_path=input_path)
 
-    print("Done.")
+    logger.info("Done.")

roman_photoz/create_simulated_catalog.py

@@ -13,6 +13,7 @@
 
 from roman_photoz import create_roman_filters
 from roman_photoz.default_config_file import default_roman_config
+from roman_photoz.logger import logger
 
 ROMAN_DEFAULT_CONFIG = default_roman_config
 
@@ -116,12 +117,13 @@ def get_filters(self):
             Path(self.lephare_config["FILTER_REP"], "roman"), "roman_"
         )
         if not filter_files_present:
+            logger.info("Filter files not found, generating them...")
             create_roman_filters.run()
 
         self.filter_lib = lp.FilterSvc.from_keymap(
             lp.all_types_to_keymap(self.lephare_config)
         )
-        print(
+        logger.info(
             f"Created filter library using the filter files in {self.lephare_config['FILTER_REP']}/roman."
         )
 
@@ -146,6 +148,7 @@ def create_simulated_data(self):
             "LIB_ASCII": "YES",
         }
 
+        logger.info("Preparing LePhare environment for simulated data generation...")
         lp.prepare(
             config=self.lephare_config,
             star_config=star_overrides,
@@ -154,6 +157,7 @@ def create_simulated_data(self):
         )
 
         self.simulated_data_filename = gal_overrides.get("GAL_LIB_OUT")
+        logger.info("Simulated data generated successfully")
 
     def create_simulated_input_catalog(
         self,
@@ -300,9 +304,9 @@ def save_catalog(
         """
         output_path = Path(output_path).as_posix()
         output_filename = output_filename
+        logger.info(f"Saving catalog to {output_path}/{output_filename}...")
         self.roman_catalog_template.save(output_filename, dir_path=output_path)
-
-        print(f"Saved simulated input catalog to {output_path}/{output_filename}.")
+        logger.info("Catalog saved successfully")
 
     def add_ids(self, catalog):
         """
@@ -462,7 +466,7 @@ def process(
             output_path=output_path,
         )
 
-        print("DONE")
+        logger.info("DONE")
 
 
 if __name__ == "__main__":
@@ -487,7 +491,9 @@ def parse_args():
 
     args = parse_args()
 
+    logger.info("Starting simulated catalog creation...")
     rcp = SimulatedCatalog()
     rcp.process(args.output_path, args.output_filename)
+    logger.info("Simulated catalog creation completed successfully")
 
-    print("Done.")
+    logger.info("Done.")

roman_photoz/logger.py

@@ -0,0 +1,37 @@
+import logging
+
+
+def setup_logging(log_file="roman_photoz.log", level=logging.INFO):
+    """Set up logging configuration for roman_photoz module"""
+    # Create a logger specific to our module instead of configuring the root logger
+    logger = logging.getLogger("roman_photoz")
+
+    # Only configure if it hasn't been configured yet
+    if not logger.handlers:
+        # Set propagate to False to prevent messages from being passed to the root logger
+        logger.propagate = False
+
+        # Set the level
+        logger.setLevel(level)
+
+        # Create formatter
+        formatter = logging.Formatter(
+            "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+        )
+
+        # Create handlers
+        console_handler = logging.StreamHandler()
+        console_handler.setFormatter(formatter)
+
+        file_handler = logging.FileHandler(log_file, mode="a")
+        file_handler.setFormatter(formatter)
+
+        # Add handlers to logger
+        logger.addHandler(console_handler)
+        logger.addHandler(file_handler)
+
+    return logger
+
+
+# Create the default logger instance
+logger = setup_logging()

roman_photoz/roman_catalog_handler.py

@@ -5,6 +5,7 @@
 from roman_datamodels import datamodels as rdm
 
 from roman_photoz.default_config_file import default_roman_config
+from roman_photoz.logger import logger
 
 
 class RomanCatalogHandler:
@@ -32,7 +33,7 @@ def __init__(self, catname: str = ""):
         self.cat_temp_filename = "cat_temp_file.csv"
         # get Roman's filter names from default config file
         filter_list = default_roman_config.get("FILTER_LIST")
-        if filter_list is not None:
+        if (filter_list is not None):
             self.filter_names = (
                 filter_list.replace(".pb", "").replace("roman/", "").split(",")
             )
@@ -43,7 +44,7 @@ def format_catalog(self):
         """
         Format the catalog by appending necessary fields and columns.
         """
-        print("Formatting catalog...")
+        logger.info("Formatting catalog...")
         # self.format_colnames()
 
         self.catalog = self.cat_array[["id"]].copy()
@@ -79,19 +80,19 @@ def format_catalog(self):
             self.cat_array["string_data"].astype(str),
             usemask=False,
         )
-        print("Done.")
+        logger.info("Catalog formatting completed")
 
     def read_catalog(self):
         """
         Read the catalog file and convert it to a numpy structured array.
         """
-        print(f"Parsing catalog {self.cat_name}...")
+        logger.info(f"Reading catalog {self.cat_name}...")
         dm = rdm.open(self.cat_name)
         self.cat_array = (
             dm.source_catalog.as_array()
         )  # Convert Table to numpy structured array
 
-        print("Done.")
+        logger.info("Catalog read successfully")
 
     def process(self):
         """

roman_photoz/roman_catalog_process.py

@@ -17,6 +17,7 @@
 
 from roman_photoz.default_config_file import default_roman_config
 from roman_photoz.roman_catalog_handler import RomanCatalogHandler
+from roman_photoz.logger import logger
 
 DS = RailStage.data_store
 DS.__class__.allow_overwrite = True
@@ -124,6 +125,7 @@ def get_data(
         """
         # full qualified path to the catalog file
         filename = Path(input_path, input_filename).as_posix()
+        logger.info(f"Reading catalog from {filename}")
 
         # read in catalog data
         if Path(filename).suffix == ".asdf":
@@ -147,7 +149,7 @@ def format_data(self, cat_data: Table):
         """
         # get information about Roman filters
         bands = self.config["FILTER_LIST"].split(",")
-        print(len(bands))
+        logger.debug(f"Found {len(bands)} bands in filter list")
 
         # loop over the filters we want to keep to get
         # the number of the filter, n, and the name, b
@@ -164,6 +166,7 @@ def format_data(self, cat_data: Table):
         self.data["string_data"] = np.array(cat_data[cat_data.colnames[-1]]).astype(
             bytes
         )
+        logger.info("Catalog data formatted successfully")
 
     def create_informer_stage(self):
         """
@@ -254,13 +257,14 @@ def save_results(
         if self.estimated is not None:
             ancil_data = self.estimated.data.ancil
         else:
+            logger.error("No results to save")
             raise ValueError("No results to save.")
 
         tree = {"roman_photoz_results": ancil_data}
         with AsdfFile(tree) as af:
             af.write_to(output_filename)
 
-        print(f"Results saved to {output_filename}")
+        logger.info(f"Results saved to {output_filename}")
 
     def process(
         self,
@@ -350,6 +354,7 @@ def main(argv=None):
 
     args = parser.parse_args(argv)
 
+    logger.info("Starting Roman catalog processing")
     rcp = RomanCatalogProcess(config_filename=args.config_filename)
 
     rcp.process(
@@ -360,4 +365,4 @@ def main(argv=None):
         save_results=args.save_results,
     )
 
-    print("Done.")
+    logger.info("Roman catalog processing completed")