Clean up logging statements

catalyst-cooperative · Jan 8, 2024 · b472667 · b472667
1 parent 69d40d2
commit b472667
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 13 deletions.
diff --git a/src/pudl/extract/epacems.py b/src/pudl/extract/epacems.py
@@ -173,20 +173,16 @@ def __init__(self, datastore: Datastore):
 
     def get_data_frame(self, partition: EpaCemsPartition) -> pd.DataFrame:
         """Constructs dataframe from a zipfile for a given (year_quarter) partition."""
-        logger.info(f"Getting dataframe for {partition}")
         archive = self.datastore.get_zipfile_resource(
             "epacems", **partition.get_filters()
         )
-        logger.info(f"Got zipfile for partition {partition}")
         with archive.open(str(partition.get_quarterly_file()), "r") as csv_file:
-            logger.info(f"Opened zipfile for partition {partition}")
             df = self._csv_to_dataframe(
                 csv_file,
                 ignore_cols=API_IGNORE_COLS,
                 rename_dict=API_RENAME_DICT,
                 dtype_dict=API_DTYPE_DICT,
             )
-            logger.info(f"Returning DF for {partition}.")
         return df
 
     def _csv_to_dataframe(
@@ -233,7 +229,7 @@ def extract(year_quarter: str, ds: Datastore) -> pd.DataFrame:
     year = partition.year
     # We have to assign the reporting year for partitioning purposes
     try:
-        logger.info(f"Processing data frame for {partition}")
+        logger.info(f"Extracting data frame for {year_quarter}")
         df = ds.get_data_frame(partition).assign(year=year)
     # If the requested quarter is not found, return an empty df with expected columns:
     except KeyError:

diff --git a/src/pudl/workspace/datastore.py b/src/pudl/workspace/datastore.py
@@ -376,13 +376,11 @@ def get_resources(
                 logger.info(f"{res} is already optimally cached.")
                 continue
             if self._cache.contains(res):
-                logger.info(f"Retrieved {res} from cache.")
                 contents = self._cache.get(res)
-                logger.info(f"Got resource {res} from cache.")
+                logger.info(f"Retrieved {res} from cache.")
                 if not self._cache.is_optimally_cached(res):
                     logger.info(f"{res} was not optimally cached yet, adding.")
                     self._cache.add(res, contents)
-                logger.info("Yielding resource {res} from cache")
                 yield (res, contents)
             elif not cached_only:
                 logger.info(f"Retrieved {res} from zenodo.")
@@ -396,7 +394,6 @@ def remove_from_cache(self, res: PudlResourceKey) -> None:
 
     def get_unique_resource(self, dataset: str, **filters: Any) -> bytes:
         """Returns content of a resource assuming there is exactly one that matches."""
-        logger.info("Getting unique resource.")
         res = self.get_resources(dataset, **filters)
         try:
             _, content = next(res)
@@ -410,7 +407,6 @@ def get_unique_resource(self, dataset: str, **filters: Any) -> bytes:
 
     def get_zipfile_resource(self, dataset: str, **filters: Any) -> zipfile.ZipFile:
         """Retrieves unique resource and opens it as a ZipFile."""
-        logger.info("Getting zipfile resource.")
         return zipfile.ZipFile(io.BytesIO(self.get_unique_resource(dataset, **filters)))
 
     def get_zipfile_resources(

diff --git a/src/pudl/workspace/resource_cache.py b/src/pudl/workspace/resource_cache.py
@@ -203,11 +203,8 @@ def num_layers(self):
 
     def get(self, resource: PudlResourceKey) -> bytes:
         """Returns content of a given resource."""
-        logger.info(f"Getting resource {resource}")
         for i, cache in enumerate(self._caches):
-            logger.info(f"Getting {i}, {cache}")
             if cache.contains(resource):
-                logger.info(f"Cache contains {resource}. Getting cache.")
                 logger.debug(
                     f"get:{resource} found in {i}-th layer ({cache.__class__.__name__})."
                 )