doc(bigquery): add more data types to load dataframe sample

googleapis · Dec 30, 2019 · e10f755 · e10f755
1 parent 154c8ec
commit e10f755
Show file tree

Hide file tree

Showing 2 changed files with 58 additions and 8 deletions.
diff --git a/bigquery/samples/load_table_dataframe.py b/bigquery/samples/load_table_dataframe.py
@@ -16,9 +16,11 @@
 def load_table_dataframe(client, table_id):
 
     # [START bigquery_load_table_dataframe]
-    from google.cloud import bigquery
+    import datetime
 
+    from google.cloud import bigquery
     import pandas
+    import pytz
 
     # TODO(developer): Construct a BigQuery client object.
     # client = bigquery.Client()
@@ -27,16 +29,54 @@ def load_table_dataframe(client, table_id):
     # table_id = "your-project.your_dataset.your_table_name"
 
     records = [
-        {"title": u"The Meaning of Life", "release_year": 1983},
-        {"title": u"Monty Python and the Holy Grail", "release_year": 1975},
-        {"title": u"Life of Brian", "release_year": 1979},
-        {"title": u"And Now for Something Completely Different", "release_year": 1971},
+        {
+            "title": u"The Meaning of Life",
+            "release_year": 1983,
+            "length_minutes": 112.5,
+            "release_date": datetime.datetime(
+                1983, 5, 9, 13, 0, 0, tzinfo=pytz.timezone("Europe/Paris")
+            ),
+            "dvd_release": datetime.datetime(2002, 1, 22, 7, 0, 0),
+        },
+        {
+            "title": u"Monty Python and the Holy Grail",
+            "release_year": 1975,
+            "length_minutes": 91.5,
+            "release_date": datetime.datetime(
+                1975, 4, 9, 23, 59, 2, tzinfo=pytz.timezone("Europe/London")
+            ),
+            "dvd_release": datetime.datetime(2002, 7, 16, 9, 0, 0),
+        },
+        {
+            "title": u"Life of Brian",
+            "release_year": 1979,
+            "length_minutes": 94.25,
+            "release_date": datetime.datetime(
+                1979, 8, 17, 23, 59, 5, tzinfo=pytz.timezone("America/New_York")
+            ),
+            "dvd_release": datetime.datetime(2008, 1, 14, 8, 0, 0),
+        },
+        {
+            "title": u"And Now for Something Completely Different",
+            "release_year": 1971,
+            "length_minutes": 88.0,
+            "release_date": datetime.datetime(
+                1971, 9, 28, 23, 59, 7, tzinfo=pytz.timezone("Europe/London")
+            ),
+            "dvd_release": datetime.datetime(2003, 10, 22, 10, 0, 0),
+        },
     ]
     dataframe = pandas.DataFrame(
         records,
         # In the loaded table, the column order reflects the order of the
         # columns in the DataFrame.
-        columns=["title", "release_year"],
+        columns=[
+            "title",
+            "release_year",
+            "length_minutes",
+            "release_date",
+            "dvd_release",
+        ],
         # Optionally, set a named index, which can also be written to the
         # BigQuery table.
         index=pandas.Index(

diff --git a/bigquery/samples/tests/test_load_table_dataframe.py b/bigquery/samples/tests/test_load_table_dataframe.py
@@ -25,7 +25,17 @@ def test_load_table_dataframe(capsys, client, random_table_id):
 
     table = load_table_dataframe.load_table_dataframe(client, random_table_id)
     out, _ = capsys.readouterr()
-    assert "Loaded 4 rows and 3 columns" in out
+    assert "Loaded 4 rows and 6 columns" in out
 
     column_names = [field.name for field in table.schema]
-    assert column_names == ["wikidata_id", "title", "release_year"]
+    assert column_names == [
+        "wikidata_id",
+        "title",
+        "release_year",
+        "length_minutes",
+        "release_date",
+        "dvd_release",
+    ]
+
+    df = client.list_rows(table).to_dataframe()
+    # TODO: sort and check values