def test_error_metrics(self, mock_comparison_dataframe):
accuracy = Accuracy(Mock(), Mock(), Mock(), Mock(), Mock(), Mock(),
Mock())
accuracy.comparison_dataframe = self._mock_comparison_dataframe()
self.assertEqual(accuracy.root_mean_squared_error(), (1.0, 1.0))
self.assertListEqual(accuracy.root_squared_error().mean().tolist(),
[1.0, 1.0])
self.assertListEqual(accuracy.absolute_pct_error().mean().tolist(),
[2.0, 0.66666666666666663])
def test_error_report(self, mock_comparison_datframe, mock_from_data_dir):
accuracy = Accuracy(Mock(), Mock(), Mock(), Mock(), Mock(), Mock(),
Mock())
accuracy.comparison_dataframe = self._mock_comparison_dataframe()
accuracy.from_data_dir.return_value = accuracy
state_puma = dict()
state_puma['20'] = ['00500', '00602', '00604']
state_puma['29'] = ['00901', '00902']
expected_columns = ['marginal-pums', 'marginal-doppelganger']
df_puma, df_variable, df_total =\
accuracy.error_report(
state_puma, 'fake_dir',
marginal_variables=['num_people', 'num_vehicles', 'age'],
statistic=ErrorStat.ABSOLUTE_PCT_ERROR
)
# Test df_total
df_total_expected = pd.Series([2.00000, 0.666667],
index=expected_columns)
self.assertTrue(all((df_total - df_total_expected) < 1))
# Test df_puma
expected_puma_data = np.reshape([2.0, 2 / 3.0] * 5, (5, 2))
df_expected_puma = pd.DataFrame(data=expected_puma_data,
index=self._mock_state_puma(),
columns=expected_columns)
self.assertTrue((df_expected_puma == df_puma).all().all())
# Test df_variable
expected_variable_data = np.reshape([2.0, 2 / 3.0] * 12, (12, 2))
df_expected_variable = pd.DataFrame(data=expected_variable_data,
index=self._mock_variable_bins(),
columns=expected_columns)
self.assertTrue((df_expected_variable == df_variable).all().all())
# Test unimplemented statistic name
try:
self.assertRaises(
Exception,
Accuracy.error_report(
state_puma,
'fake_dir',
marginal_variables=['num_people', 'num_vehicles', 'age'],
statistic='wrong-statistic-name'))
except Exception:
pass