def test__get_missing_valid_rows_excess_rows(self):
"""If more rows than required are passed, the result is cut to num_rows."""
# Setup
data_navigator = MagicMock(spec=DataNavigator)
modeler = MagicMock(spec=Modeler)
sampler = Sampler(data_navigator, modeler)
synthesized = pd.DataFrame(columns=list('AB'), index=range(3, 7))
drop_indices = pd.Series(False, index=range(3, 7))
valid_rows = pd.DataFrame(columns=list('AB'), index=range(2))
num_rows = 5
# Run
result = sampler._get_missing_valid_rows(synthesized, drop_indices,
valid_rows, num_rows)
missing_rows, valid_rows = result
# Check
assert missing_rows == 0
assert valid_rows.equals(
pd.DataFrame(columns=list('AB'), index=range(5)))
data_navigator.assert_not_called()
assert data_navigator.method_calls == []
modeler.assert_not_called()
assert modeler.method_calls == []
def test__get_missing_valid_rows(self):
"""get_missing_valid_rows return an a dataframe and an integer.
The dataframe contains valid_rows concatenated to synthesized and their index reset.
The integer is the diference between num_rows and the returned dataframe rows.
"""
# Setup
data_navigator = MagicMock(spec=DataNavigator)
modeler = MagicMock(spec=Modeler)
sampler = Sampler(data_navigator, modeler)
synthesized = pd.DataFrame(columns=list('AB'), index=range(3, 5))
drop_indices = pd.Series(False, index=range(3, 5))
valid_rows = pd.DataFrame(columns=list('AB'), index=range(2))
num_rows = 5
# Run
result = sampler._get_missing_valid_rows(synthesized, drop_indices,
valid_rows, num_rows)
missing_rows, valid_rows = result
# Check
assert missing_rows == 1
assert valid_rows.equals(
pd.DataFrame(columns=list('AB'), index=[0, 1, 2, 3]))
data_navigator.assert_not_called()
assert data_navigator.method_calls == []
modeler.assert_not_called()
assert modeler.method_calls == []