add diff for join columns (#339)

capitalone · Oct 17, 2024 · 1078a82 · 1078a82
1 parent 67d0fa2
commit 1078a82
Show file tree

Hide file tree

Showing 4 changed files with 16 additions and 4 deletions.
diff --git a/datacompy/core.py b/datacompy/core.py
@@ -179,7 +179,10 @@ def _validate_dataframe(
             dataframe.columns = pd.Index([str(col) for col in dataframe.columns])
         # Check if join_columns are present in the dataframe
         if not set(self.join_columns).issubset(set(dataframe.columns)):
-            raise ValueError(f"{index} must have all columns from join_columns")
+            missing_cols = set(self.join_columns) - set(dataframe.columns)
+            raise ValueError(
+                f"{index} must have all columns from join_columns: {missing_cols}"
+            )
 
         if len(set(dataframe.columns)) < len(dataframe.columns):
             raise ValueError(f"{index} must have unique column names")

diff --git a/datacompy/polars.py b/datacompy/polars.py
@@ -176,7 +176,10 @@ def _validate_dataframe(
 
         # Check if join_columns are present in the dataframe
         if not set(self.join_columns).issubset(set(dataframe.columns)):
-            raise ValueError(f"{index} must have all columns from join_columns")
+            missing_cols = set(self.join_columns) - set(dataframe.columns)
+            raise ValueError(
+                f"{index} must have all columns from join_columns: {missing_cols}"
+            )
 
         if len(set(dataframe.columns)) < len(dataframe.columns):
             raise ValueError(f"{index} must have unique column names")

diff --git a/datacompy/spark/pandas.py b/datacompy/spark/pandas.py
@@ -181,7 +181,10 @@ def _validate_dataframe(
             dataframe.columns = [str(col) for col in dataframe.columns]
         # Check if join_columns are present in the dataframe
         if not set(self.join_columns).issubset(set(dataframe.columns)):
-            raise ValueError(f"{index} must have all columns from join_columns")
+            missing_cols = set(self.join_columns) - set(dataframe.columns)
+            raise ValueError(
+                f"{index} must have all columns from join_columns: {missing_cols}"
+            )
 
         if len(set(dataframe.columns)) < len(dataframe.columns):
             raise ValueError(f"{index} must have unique column names")

diff --git a/datacompy/spark/sql.py b/datacompy/spark/sql.py
@@ -241,7 +241,10 @@ def _validate_dataframe(
         # Check if join_columns are present in the dataframe
         dataframe = getattr(self, index)  # refresh
         if not set(self.join_columns).issubset(set(dataframe.columns)):
-            raise ValueError(f"{index} must have all columns from join_columns")
+            missing_cols = set(self.join_columns) - set(dataframe.columns)
+            raise ValueError(
+                f"{index} must have all columns from join_columns: {missing_cols}"
+            )
 
         if len(set(dataframe.columns)) < len(dataframe.columns):
             raise ValueError(f"{index} must have unique column names")