Force index=False for wr.db.to_sql() with redshift.

Author: igorborgest

awswrangler/db.py

@@ -34,6 +34,10 @@ def to_sql(df: pd.DataFrame, con: sqlalchemy.engine.Engine, **pandas_kwargs) ->
     ----
     Redshift: For large DataFrames (1MM+ rows) consider the function **wr.db.copy_to_redshift()**.
 
+    Note
+    ----
+    Redshift: `index=False` will be forced.
+
     Parameters
     ----------
     df : pandas.DataFrame
@@ -92,6 +96,8 @@ def to_sql(df: pd.DataFrame, con: sqlalchemy.engine.Engine, **pandas_kwargs) ->
     )
     pandas_kwargs["dtype"] = dtypes
     pandas_kwargs["con"] = con
+    if pandas_kwargs["con"].name.lower() == "redshift":  # Redshift does not accept index
+        pandas_kwargs["index"] = False
     max_attempts: int = 3
     for attempt in range(max_attempts):
         try:

testing/test_awswrangler/test_db.py

@@ -89,13 +89,14 @@ def test_sql(parameters, db_type):
     if db_type == "redshift":
         df.drop(["binary"], axis=1, inplace=True)
     engine = wr.catalog.get_engine(connection=f"aws-data-wrangler-{db_type}")
+    index = True if engine.name == "redshift" else False
     wr.db.to_sql(
         df=df,
         con=engine,
         name="test_sql",
         schema=parameters[db_type]["schema"],
         if_exists="replace",
-        index=False,
+        index=index,
         index_label=None,
         chunksize=None,
         method=None,