diff --git a/etl/__init__.py b/etl/__init__.py
new file mode 100644
index 00000000..a9f46b58
--- /dev/null
+++ b/etl/__init__.py
@@ -0,0 +1 @@
+from .filter_mastermap import filter_mastermap
\ No newline at end of file
diff --git a/etl/filter_mastermap.py b/etl/filter_mastermap.py
index 76c1d559..be68f756 100644
--- a/etl/filter_mastermap.py
+++ b/etl/filter_mastermap.py
@@ -14,20 +14,19 @@ csv.field_size_limit(sys.maxsize)
 def main(mastermap_path):
     mm_paths = sorted(glob.glob(os.path.join(mastermap_path, "*.gml.csv")))
     for mm_path in mm_paths:
-        filter(mm_path)
+        filter_mastermap(mm_path)
 
 
-def filter(mm_path)
+def filter_mastermap(mm_path)
     output_path =  "{}.filtered.csv".format(str(mm_path).replace(".gml.csv", ""))
     output_fieldnames = ('WKT', 'fid', 'descriptiveGroup')
     # Open the input csv with all polygons, buildings and others
     with open(mm_path, 'r') as fh:
         r = csv.DictReader(fh)
-        # Open a new buildings csv
+        # Open a new output csv that will contain just buildings
         with open(output_path, 'w') as output_fh:
             w = csv.DictWriter(output_fh, fieldnames=output_fieldnames)
-            w.writeheader()    
-            # Then write to the output csv buildings only
+            w.writeheader()
             for line in r:
                 if 'Building' in line['descriptiveGroup']:
                     w.writerow(line)
diff --git a/tests/test_filter.py b/tests/test_filter.py
new file mode 100644
index 00000000..cf2a2083
--- /dev/null
+++ b/tests/test_filter.py
@@ -0,0 +1,8 @@
+import pytest
+from etl import filter_mastermap
+
+def test_filter_mastermap():
+    """Test that MasterMap CSV can be correctly filtered to include only buildings."""
+    input_file = ""
+    expected_output = ""
+    assert filter_mastermap(input_file) == expected_output
\ No newline at end of file