Fix drop() method to handle quoted column names consistently

python/datafusion/dataframe.py

@@ -409,16 +409,32 @@
     def drop(self, *columns: str) -> DataFrame:
         """Drop arbitrary amount of columns.
 
+        Column names are case-sensitive and do not require double quotes like 
+        other operations such as `select`. Leading and trailing double quotes 
+        are allowed and will be automatically stripped if present.
+
         Args:
-            columns: Column names to drop from the dataframe.
+            columns: Column names to drop from the dataframe. Both 'column_name' 
+                    and '"column_name"' are accepted.
 
         Returns:
             DataFrame with those columns removed in the projection.
+
+        Example Usage:
+            df.drop('ID_For_Students')      # Works
+            df.drop('"ID_For_Students"')    # Also works (quotes stripped)
         """
-        return DataFrame(self.df.drop(*columns))
+        normalized_columns = []
+        for col in columns:
+            if col.startswith('"') and col.endswith('"'):
+                normalized_columns.append(col.strip('"')) # Removes quotes from both sides of col
+            else:
+                normalized_columns.append(col)
+
+        return DataFrame(self.df.drop(*normalized_columns))
 
     def filter(self, *predicates: Expr) -> DataFrame:
         """Return a DataFrame for which ``predicate`` evaluates to ``True``.
 
         Rows for which ``predicate`` evaluates to ``False`` or ``None`` are filtered
         out.  If more than one predicate is provided, these predicates will be

python/tests/test_dataframe.py

@@ -216,10 +216,19 @@
     assert result.column(0) == pa.array([4, 5, 6])
     assert result.column(1) == pa.array([1, 2, 3])
 
-
+def test_drop_quoted_columns():
+    ctx = SessionContext()
+    batch = pa.RecordBatch.from_arrays([pa.array([1, 2, 3])], names=["ID_For_Students"])
+    df = ctx.create_dataframe([[batch]])
+
+    # Both should work
+    assert df.drop('"ID_For_Students"').schema().names == []
+    assert df.drop('ID_For_Students').schema().names == []
+
+
 def test_select_mixed_expr_string(df):
     df = df.select(column("b"), "a")
 
     # execute and collect the first (and only) batch
     result = df.collect()[0]