fix: cache dataset before dropping columns to prevent validation errors

Author: liquidz00

CHANGELOG.md

@@ -5,6 +5,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v2.0.3] - 2025-02-05
+### Fixed
+- Data sets are cached before dropping ignored columns so that analysis can complete as expected
+
 ## [v2.0.2] - 2025-02-02
 ### Added
 - Support for tracking `softwareTitleId` from Jamf API Response

src/patcher/__about__.py

@@ -1,2 +1,2 @@
 __title__ = "patcher"
-__version__ = "2.0.2"
+__version__ = "2.0.3"

src/patcher/utils/data_manager.py

@@ -190,6 +190,7 @@ def export_to_excel(self, patch_titles: List[PatchTitle], output_dir: Union[str,
 
         current_date = datetime.now().strftime("%m-%d-%y")
         df = self._create_dataframe(patch_titles)
+        self._cache_data(df)
         df = df.drop(
             columns=[col.replace("_", " ").title() for col in DataManager._IGNORED], errors="ignore"
         )  # Drop excluded columns
@@ -199,7 +200,6 @@ def export_to_excel(self, patch_titles: List[PatchTitle], output_dir: Union[str,
             excel_path = os.path.join(output_dir, f"patch-report-{current_date}.xlsx")
             df.to_excel(excel_path, index=False)
             self.log.info(f"Excel report created successfully to {excel_path}.")
-            self._cache_data(df)
             self.latest_excel_file = excel_path
             return excel_path
         except (OSError, PermissionError) as e:

tests/test_data_manager.py

@@ -37,7 +37,9 @@ def test_export_to_excel_success(sample_patch_reports, temp_output_dir):
         args, _ = mock_cache_data.call_args
         cached_df = args[0]
 
-        assert_frame_equal(df, cached_df)
+        # Account for cached dataframe having all columns
+        common_columns = df.columns.intersection(cached_df.columns)
+        assert_frame_equal(df[common_columns], cached_df[common_columns], check_like=True)
 
 
 def test_export_to_excel_dataframe_creation_error(temp_output_dir):