diff --git a/Databricks/clean data with spark/clean data with spark SQL.dbc b/Databricks/clean data with spark/clean data with spark SQL.dbc
new file mode 100644
index 0000000..23e543a
Binary files /dev/null and b/Databricks/clean data with spark/clean data with spark SQL.dbc differ
diff --git a/Databricks/clean data with spark/clean data with spark python.dbc b/Databricks/clean data with spark/clean data with spark python.dbc
new file mode 100644
index 0000000..1b0212c
Binary files /dev/null and b/Databricks/clean data with spark/clean data with spark python.dbc differ
diff --git a/Databricks/clean data with spark/orders_raw.csv b/Databricks/clean data with spark/orders_raw.csv
new file mode 100644
index 0000000..7d59dc2
--- /dev/null
+++ b/Databricks/clean data with spark/orders_raw.csv	
@@ -0,0 +1,12 @@
+order_id,order_date,customer_id,amount
+1,27/09/2024,101,10
+2,,101,11
+3,29/09/2024,201,12
+4,30/09/2024,101,13
+4,30/09/2024,101,13
+5,01/10/2024,301,
+6,02/10/2024,401,15
+7,03/10/2024,,16
+8,32/10/2024,501,17
+9,05/10/2024,301,AAA
+10,06/10/2024,401,19