diff --git a/tests/__init__.py b/tests/__init__.py
index a8d1e77..36a107b 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -163,6 +163,59 @@ ECOMMERCE_MAPPING = {
 ECOMMERCE_FILE_NAME = ROOT_DIR + "/ecommerce.json.gz"
 ECOMMERCE_DF_FILE_NAME = ROOT_DIR + "/ecommerce_df.json.gz"
 
+MOVIES_INDEX_NAME = "movies"
+MOVIES_FILE_NAME = ROOT_DIR + "/movies.json.gz"
+MOVIES_MAPPING = {
+    "mappings": {
+        "properties": {
+            "type": {"type": "keyword"},
+            "title": {"type": "text"},
+            "year": {"type": "integer"},
+            "rated": {"type": "keyword"},
+            "released": {"type": "date"},
+            "plot": {"type": "text"},
+            "awards": {"type": "text"},
+            "poster": {"type": "keyword"},
+            "id": {"type": "keyword"},
+            "metascore": {"type": "float"},
+            "imdbRating": {"type": "float"},
+            "imdbVotes": {"type": "integer"},
+            "language": {"type": "keyword"},
+            "runtime": {"type": "integer"},
+            "genres": {
+                "type": "text",
+                "fields": {
+                    "keyword": {"type": "keyword"},
+                },
+            },
+            "directors": {
+                "type": "text",
+                "fields": {
+                    "keyword": {"type": "keyword"},
+                },
+            },
+            "writers": {
+                "type": "text",
+                "fields": {
+                    "keyword": {"type": "keyword"},
+                },
+            },
+            "actors": {
+                "type": "text",
+                "fields": {
+                    "keyword": {"type": "keyword"},
+                },
+            },
+            "country": {
+                "type": "text",
+                "fields": {
+                    "keyword": {"type": "keyword"},
+                },
+            },
+        }
+    }
+}
+
 TEST_MAPPING1 = {
     "mappings": {
         "properties": {
diff --git a/tests/movies.json.gz b/tests/movies.json.gz
new file mode 100644
index 0000000..47e6bbb
Binary files /dev/null and b/tests/movies.json.gz differ
diff --git a/tests/setup_tests.py b/tests/setup_tests.py
index 953aeb9..c0c353a 100644
--- a/tests/setup_tests.py
+++ b/tests/setup_tests.py
@@ -30,6 +30,9 @@ from tests import (
     FLIGHTS_MAPPING,
     FLIGHTS_SMALL_FILE_NAME,
     FLIGHTS_SMALL_INDEX_NAME,
+    MOVIES_FILE_NAME,
+    MOVIES_INDEX_NAME,
+    MOVIES_MAPPING,
     TEST_MAPPING1,
     TEST_MAPPING1_INDEX_NAME,
     TEST_NESTED_USER_GROUP_DOCS,
@@ -41,6 +44,7 @@ DATA_LIST = [
     (FLIGHTS_FILE_NAME, FLIGHTS_INDEX_NAME, FLIGHTS_MAPPING),
     (FLIGHTS_SMALL_FILE_NAME, FLIGHTS_SMALL_INDEX_NAME, FLIGHTS_MAPPING),
     (ECOMMERCE_FILE_NAME, ECOMMERCE_INDEX_NAME, ECOMMERCE_MAPPING),
+    (MOVIES_FILE_NAME, MOVIES_INDEX_NAME, MOVIES_MAPPING),
 ]
 
 
@@ -58,18 +62,20 @@ def _setup_data(es):
         es.indices.create(index=index_name, **mapping)
 
         df = pd.read_json(json_file_name, lines=True)
-
         actions = []
         n = 0
 
         print("Adding", df.shape[0], "items to index:", index_name)
         for index, row in df.iterrows():
-            values = row.to_dict()
+            values = row.dropna().to_dict()
             # make timestamp datetime 2018-01-01T12:09:35
             # values['timestamp'] = datetime.strptime(values['timestamp'], '%Y-%m-%dT%H:%M:%S')
 
-            # Use integer as id field for repeatable results
-            action = {"_index": index_name, "_source": values, "_id": str(n)}
+            # Use id field as document id from the row if the fiel exists.
+            # Else, use integer as id field for repeatable results
+            # document_id = values['id'] if 'id' in values else str(n)
+            document_id = values["id"] if "id" in values else str(n)
+            action = {"_index": index_name, "_source": values, "_id": document_id}
 
             actions.append(action)