Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[get_df] Fix datetime conversion #5274

Merged
merged 1 commit into from
Jun 27, 2018
Merged

[get_df] Fix datetime conversion #5274

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 3 additions & 5 deletions superset/viz.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,13 +197,11 @@ def get_df(self, query_obj=None):
# be considered as the default ISO date format
# If the datetime format is unix, the parse will use the corresponding
# parsing logic.
if df is None or df.empty:
return pd.DataFrame()
else:
if not df.empty:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You removed the check for df is None does that mean df won't be None? Will we still be passing an empty data frame if there's no data?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The check was only there because we were mocking the pandas.DataFrame. The data is obtained from pandas.read_sql_query which returns a pandas.DataFrame object.

if DTTM_ALIAS in df.columns:
if timestamp_format in ('epoch_s', 'epoch_ms'):
df[DTTM_ALIAS] = pd.to_datetime(
df[DTTM_ALIAS], utc=False, unit=timestamp_format[6:])
# Column has already been formatted as a timestamp.
df[DTTM_ALIAS] = df[DTTM_ALIAS].apply(pd.Timestamp)
else:
df[DTTM_ALIAS] = pd.to_datetime(
df[DTTM_ALIAS], utc=False, format=timestamp_format)
Expand Down
81 changes: 37 additions & 44 deletions tests/viz_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,73 +38,66 @@ def test_get_fillna_returns_default_on_null_columns(self):
def test_get_df_returns_empty_df(self):
datasource = Mock()
datasource.type = 'table'
mock_dttm_col = Mock()
mock_dttm_col.python_date_format = Mock()
datasource.get_col = Mock(return_value=mock_dttm_col)
form_data = {'dummy': 123}
query_obj = {'granularity': 'day'}
results = Mock()
results.query = Mock()
results.status = Mock()
results.error_message = None
results.df = Mock()
results.df.empty = True
results.df = pd.DataFrame()
datasource.query = Mock(return_value=results)
test_viz = viz.BaseViz(datasource, form_data)
result = test_viz.get_df(query_obj)
self.assertEqual(type(result), pd.DataFrame)
self.assertTrue(result.empty)

def test_get_df_handles_dttm_col(self):
datasource = Mock()
datasource.type = 'table'
datasource.offset = 1
mock_dttm_col = Mock()
mock_dttm_col.python_date_format = 'epoch_ms'
datasource.get_col = Mock(return_value=mock_dttm_col)
form_data = {'dummy': 123}
query_obj = {'granularity': 'day'}
results = Mock()
results.query = Mock()
results.status = Mock()
results.error_message = Mock()
df = Mock()
df.columns = [DTTM_ALIAS]
f_datetime = datetime(1960, 1, 1, 5, 0)
df.__getitem__ = Mock(return_value=pd.Series([f_datetime]))
df.__setitem__ = Mock()
df.replace = Mock()
df.fillna = Mock()
results.df = df
results.df.empty = False
datasource = Mock()
datasource.type = 'table'
datasource.query = Mock(return_value=results)
mock_dttm_col = Mock()
datasource.get_col = Mock(return_value=mock_dttm_col)
test_viz = viz.BaseViz(datasource, form_data)

test_viz.df_metrics_to_num = Mock()
test_viz.get_fillna_for_columns = Mock(return_value=0)
test_viz.get_df(query_obj)
mock_call = df.__setitem__.mock_calls[0]
self.assertEqual(mock_call[1][0], DTTM_ALIAS)
self.assertFalse(mock_call[1][1].empty)
self.assertEqual(mock_call[1][1][0], f_datetime)
mock_call = df.__setitem__.mock_calls[1]
self.assertEqual(mock_call[1][0], DTTM_ALIAS)
self.assertEqual(mock_call[1][1][0].hour, 6)
self.assertEqual(mock_call[1][1].dtype, 'datetime64[ns]')
mock_dttm_col.python_date_format = 'utc'
test_viz.get_df(query_obj)
mock_call = df.__setitem__.mock_calls[2]
self.assertEqual(mock_call[1][0], DTTM_ALIAS)
self.assertFalse(mock_call[1][1].empty)
self.assertEqual(mock_call[1][1][0].hour, 7)
mock_call = df.__setitem__.mock_calls[3]
self.assertEqual(mock_call[1][0], DTTM_ALIAS)
self.assertEqual(mock_call[1][1][0].hour, 6)
self.assertEqual(mock_call[1][1].dtype, 'datetime64[ns]')
mock_call = df.__setitem__.mock_calls[4]
self.assertEqual(mock_call[1][0], DTTM_ALIAS)
self.assertEqual(mock_call[1][1][0].hour, 7)
self.assertEqual(mock_call[1][1].dtype, 'datetime64[ns]')

results.df = pd.DataFrame(data={DTTM_ALIAS: ['1960-01-01 05:00:00']})
datasource.offset = 0
mock_dttm_col.python_date_format = 'epoch_ms'
result = test_viz.get_df(query_obj)
pd.testing.assert_series_equal(
result[DTTM_ALIAS],
pd.Series([datetime(1960, 1, 1, 5, 0)], name=DTTM_ALIAS),
)

mock_dttm_col.python_date_format = None
result = test_viz.get_df(query_obj)
pd.testing.assert_series_equal(
result[DTTM_ALIAS],
pd.Series([datetime(1960, 1, 1, 5, 0)], name=DTTM_ALIAS),
)

datasource.offset = 1
result = test_viz.get_df(query_obj)
pd.testing.assert_series_equal(
result[DTTM_ALIAS],
pd.Series([datetime(1960, 1, 1, 6, 0)], name=DTTM_ALIAS),
)

datasource.offset = 0
results.df = pd.DataFrame(data={DTTM_ALIAS: ['1960-01-01']})
mock_dttm_col.python_date_format = '%Y-%m-%d'
result = test_viz.get_df(query_obj)
pd.testing.assert_series_equal(
result[DTTM_ALIAS],
pd.Series([datetime(1960, 1, 1, 0, 0)], name=DTTM_ALIAS),
)

def test_cache_timeout(self):
datasource = Mock()
Expand Down