def test_stash_local_dataframe_multiindex_err():
arrays = [
np.array(['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux']),
np.array(['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two'])
]
df = pd.DataFrame(np.random.randn(8, 4), index=arrays)
with pytest.raises(TypeError):
_model._stash_local_dataframe(df)
def test_stash_local_data_from_dataframe(mock_file):
df = pd.DataFrame({'a': [1], 'b': [2]})
assert _model._stash_local_dataframe(df) == -11
mock_file.assert_called_once_with(mock.ANY,
name='modelpipeline_data.csv',
client=mock.ANY)
assert isinstance(mock_file.call_args[0][0], BytesIO)
def test_stash_local_dataframe_format_select_csv(mock_csv, mock_feather):
# Always store data as a CSV for CivisML versions <= 2.0.
_model._stash_local_dataframe('df', 9969)
assert mock_feather.call_count == 0
assert mock_csv.call_count == 1
def test_stash_local_dataframe_format_select_feather(mock_csv, mock_feather):
# Try to store data as Feather for CivisML versions > 2.0.
_model._stash_local_dataframe('df', 10050)
assert mock_feather.call_count == 1
assert mock_csv.call_count == 0
def test_stash_local_data_from_dataframe_feather(mock_file):
df = pd.DataFrame({'a': [1], 'b': [2]})
assert _model._stash_local_dataframe(df, 10000) == -11
mock_file.assert_called_once_with(mock.ANY,
name='modelpipeline_data.feather',
client=mock.ANY)