diff --git a/data_check.py b/data_check.py
new file mode 100644
index 0000000..09b2c77
--- /dev/null
+++ b/data_check.py
@@ -0,0 +1,17 @@
+import polars as pl
+
+df = pl.read_parquet('data/warehouse/transactions.parquet')
+print("Data loaded from Parquet file:")
+print(df)
+
+relevant_data = df.sql('''
+    SELECT 
+        date,
+        sum(transaction_amount) as total
+    FROM self
+    GROUP BY date
+    ORDER BY date DESC
+    '''
+)
+print("Data after SQL query:")
+print(relevant_data)
\ No newline at end of file
diff --git a/pipeline/raw_to_base.py b/pipeline/raw_to_base.py
index 1e2072a..255a8ad 100644
--- a/pipeline/raw_to_base.py
+++ b/pipeline/raw_to_base.py
@@ -20,6 +20,7 @@ class RawToBase:
 
     def process_entities(self):
         for entity in self.entities:
+            logging.info(f"Processing entity: {entity}")
             # check the file is in the raw data path, if not skip the entity
             folder_path = os.path.join(self.raw_data_path, entity)
             folder_contents = os.listdir(folder_path)
@@ -40,6 +41,7 @@ class RawToBase:
             if not self._move_raw_to_processed(entity):
                 logging.error(f"entity: {entity} has been processed, but we could not move the file out of the raw folder, please clear the raw folder for {entity}.")
                 sys.exit(ec.MOVE_FILE_ERROR)
+            logging.info(f"Successfully processed entity: {entity}")
     
     def _load_raw_data(self, entity):
         entity_path = os.path.join(self.raw_data_path, entity)