def test_predictions_with_additional_regressors(sample_data):
'''
TODO: update
'''
my_chronos = Chronos(n_changepoints=0, max_iter=100)
my_chronos.add_regressors("reg1", "mul")
my_chronos.add_regressors("reg2", "mul")
# Check not including the regressor throws an error
with pytest.raises(KeyError):
my_chronos.fit(sample_data)
# Now check with the regressor
sample_data['reg1'] = [1] * sample_data.shape[0]
sample_data['reg2'] = [1] * sample_data.shape[0]
my_chronos.fit(sample_data)
future_df = my_chronos.make_future_dataframe(include_history=False)
# Check not including the regressor throws an error
with pytest.raises(KeyError):
predictions = my_chronos.predict(future_df)
# Now check with the regressor
future_df['reg1'] = [1] * future_df.shape[0]
future_df['reg2'] = [1] * future_df.shape[0]
predictions = my_chronos.predict(future_df)
predictions.drop('y', axis=1, inplace=True)
assert (predictions.isna().sum().sum() == 0)
def test_error_for_nan_values(sample_data):
'''
Tests that Chronos complains when given
nan values to fit on, but not to predict on
'''
def add_dummy_regressors(data):
z = data.index.values
y = 0.01 * z + np.sin(z / 30)
data['y'] = y
# should be easy since the target is just dummy1 + dummy2
dummy1 = 0.01 * z
dummy2 = np.sin(z / 30)
data['dummy1'] = dummy1
data['dummy2'] = dummy2
return data
sample_data = add_dummy_regressors(sample_data)
my_chronos = Chronos(max_iter=200)
# add dummies
my_chronos.add_regressors("dummy1")
my_chronos.add_regressors("dummy2")
# check nan values fail for all columns
for col in ['ds', 'y', 'dummy1', 'dummy2']:
sample_data_with_nans = sample_data.copy()
sample_data_with_nans.loc[0, col] = np.nan
with pytest.raises(ValueError):
my_chronos.fit(sample_data_with_nans)
# check original data works
my_chronos.fit(sample_data)
future_df = my_chronos.make_future_dataframe()
future_df = add_dummy_regressors(future_df)
# check nan values fail for all columns EXCEPT
# the target column when making predictions
for col in ['ds', 'y', 'dummy1', 'dummy2']:
future_df_with_nans = future_df.copy()
future_df_with_nans.loc[0, col] = np.nan
if (col == 'y'):
predictions = my_chronos.predict(future_df_with_nans)
else:
with pytest.raises(ValueError):
predictions = my_chronos.predict(future_df_with_nans)
def test_prediction_with_easy_extra_regressors(sample_data):
'''
Test that when the size of the data is too small, the
number of changepoints gets adjusted
'''
z = sample_data.index.values
y = 0.01 * z + np.sin(z / 30)
sample_data['y'] = y
# should be easy since the target is just dummy1 + dummy2
dummy1 = 0.01 * z
dummy2 = np.sin(z / 30)
sample_data['dummy1'] = dummy1
sample_data['dummy2'] = dummy2
for distribution in chronos_utils.SUPPORTED_DISTRIBUTIONS:
# Student t distribution has issues with the long tails
if (distribution != chronos_utils.StudentT_dist_code):
my_chronos = Chronos(max_iter=200, distribution=distribution)
# add dummies
my_chronos.add_regressors("dummy1")
my_chronos.add_regressors("dummy2")
my_chronos.fit(sample_data)
future_df = my_chronos.make_future_dataframe()
# Add dummies to future df
z = future_df.index.values
y = 0.01 * z + np.sin(z / 30)
future_df['y'] = y
dummy1 = 0.01 * z
dummy2 = np.sin(z / 30)
future_df['dummy1'] = dummy1
future_df['dummy2'] = dummy2
# Make predictions
predictions = my_chronos.predict(future_df)
# The predictions should be almost the same as the target
assert (np.mean(np.abs(predictions['y'] - predictions['yhat'])) <
0.1)