Declare the environment file in config.py

openml · Jan 25, 2025 · edc4c90 · edc4c90
1 parent 70e9901
commit edc4c90
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git a/openml/config.py b/openml/config.py
@@ -23,6 +23,7 @@
 file_handler: logging.handlers.RotatingFileHandler | None = None
 
 OPENML_CACHE_DIR_ENV_VAR = "OPENML_CACHE_DIR"
+OPENML_SKIP_PARQUET_ENV_VAR = "OPENML_SKIP_PARQUET"
 
 
 class _Config(TypedDict):

diff --git a/openml/datasets/dataset.py b/openml/datasets/dataset.py
@@ -18,6 +18,7 @@
 import xmltodict
 
 from openml.base import OpenMLBase
+from openml.config import OPENML_SKIP_PARQUET_ENV_VAR
 from openml.exceptions import PyOpenMLError
 
 from .data_feature import OpenMLDataFeature
@@ -359,7 +360,7 @@ def _download_data(self) -> None:
         # import required here to avoid circular import.
         from .functions import _get_dataset_arff, _get_dataset_parquet
 
-        skip_parquet = os.environ.get("OPENML_SKIP_PQ", "false").casefold() == "true"
+        skip_parquet = os.environ.get(OPENML_SKIP_PARQUET_ENV_VAR, "false").casefold() == "true"
         if self._parquet_url is not None and not skip_parquet:
             parquet_file = _get_dataset_parquet(self)
             self.parquet_file = None if parquet_file is None else str(parquet_file)

diff --git a/openml/datasets/functions.py b/openml/datasets/functions.py
@@ -21,6 +21,7 @@
 
 import openml._api_calls
 import openml.utils
+from openml.config import OPENML_SKIP_PARQUET_ENV_VAR
 from openml.exceptions import (
     OpenMLHashException,
     OpenMLPrivateDatasetError,
@@ -562,7 +563,7 @@ def get_dataset(  # noqa: C901, PLR0912
             qualities_file = _get_dataset_qualities_file(did_cache_dir, dataset_id)
 
         parquet_file = None
-        skip_parquet = os.environ.get("OPENML_SKIP_PQ", "false").casefold() == "true"
+        skip_parquet = os.environ.get(OPENML_SKIP_PARQUET_ENV_VAR, "false").casefold() == "true"
         download_parquet = "oml:parquet_url" in description and not skip_parquet
         if download_parquet and (download_data or download_all_files):
             try: