def test_lgt_fixed_sm_input(synthetic_data, level_sm_input,
seasonality_sm_input, slope_sm_input):
train_df, test_df, coef = synthetic_data
lgt = LGTMAP(
response_col='response',
date_col='week',
regressor_col=train_df.columns.tolist()[2:],
level_sm_input=level_sm_input,
seasonality_sm_input=seasonality_sm_input,
slope_sm_input=slope_sm_input,
seasonality=52,
verbose=False,
)
lgt.fit(train_df)
predict_df = lgt.predict(test_df, n_bootstrap_draw=100)
regression_out = lgt.get_regression_coefs()
num_regressors = regression_out.shape[0]
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (51, len(expected_columns))
expected_regression_shape = (6, 3)
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert regression_out.shape == expected_regression_shape
assert num_regressors == len(train_df.columns.tolist()[2:])
def test_lgt_map_fit(synthetic_data, seasonality, estimator_type):
train_df, test_df, coef = synthetic_data
lgt = LGTMAP(response_col='response',
date_col='week',
seasonality=seasonality,
verbose=False,
estimator_type=estimator_type)
lgt.fit(train_df)
init_call = lgt.get_init_values()
if seasonality:
assert isinstance(init_call, LGTInitializer)
assert init_call.s == 52
init_values = init_call()
assert init_values['init_sea'].shape == (51, )
else:
assert not init_call
predict_df = lgt.predict(test_df)
expected_num_parameters = 10
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
if seasonality == 52:
expected_num_parameters += 2
expected_shape = (51, len(expected_columns))
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(lgt._posterior_samples) == expected_num_parameters
def test_lgt_mixed_signs_and_order(iclaims_training_data, regressor_signs):
df = iclaims_training_data
df['claims'] = np.log(df['claims'])
raw_regressor_col = ['trend.unemploy', 'trend.filling', 'trend.job']
new_regressor_col = [raw_regressor_col[idx] for idx in [2, 1, 0]]
new_regressor_signs = [regressor_signs[idx] for idx in [2, 1, 0]]
# mixiing ordering of cols in df of prediction
new_df = df[['claims', 'week'] + new_regressor_col]
lgt = LGTMAP(
response_col='claims',
date_col='week',
regressor_col=raw_regressor_col,
regressor_sign=regressor_signs,
seasonality=52,
seed=8888,
)
lgt.fit(df)
predicted_df_v1 = lgt.predict(df)
predicted_df_v2 = lgt.predict(new_df)
# mixing ordering of signs
lgt_new = LGTMAP(
response_col='claims',
date_col='week',
regressor_col=new_regressor_col,
regressor_sign=new_regressor_signs,
seasonality=52,
seed=8888,
)
lgt_new.fit(df)
predicted_df_v3 = lgt_new.predict(df)
predicted_df_v4 = lgt_new.predict(new_df)
pred_v1 = predicted_df_v1['prediction'].values
pred_v2 = predicted_df_v2['prediction'].values
pred_v3 = predicted_df_v3['prediction'].values
pred_v4 = predicted_df_v4['prediction'].values
# they should be all identical; ordering of signs or columns in prediction show not matter
assert np.allclose(pred_v1, pred_v2, atol=1e-3)
assert np.allclose(pred_v1, pred_v3, atol=1e-3)
assert np.allclose(pred_v1, pred_v4, atol=1e-3)
def test_lgt_map_reproducibility(synthetic_data, seasonality):
train_df, test_df, coef = synthetic_data
lgt1 = LGTMAP(
response_col='response',
date_col='week',
prediction_percentiles=[5, 95],
seasonality=seasonality,
)
# first fit and predict
lgt1.fit(train_df)
posteriors1 = copy(lgt1._aggregate_posteriors['map'])
prediction1 = lgt1.predict(test_df)
# second fit and predict
# note a new instance must be created to reset the seed
# note both fit and predict contain random generation processes
lgt2 = LGTMAP(
response_col='response',
date_col='week',
prediction_percentiles=[5, 95],
seasonality=seasonality,
)
lgt2.fit(train_df)
posteriors2 = copy(lgt2._aggregate_posteriors['map'])
prediction2 = lgt2.predict(test_df)
# assert same posterior keys
assert set(posteriors1.keys()) == set(posteriors2.keys())
# assert posterior draws are reproducible
for k, v in posteriors1.items():
assert np.allclose(posteriors1[k], posteriors2[k])
# assert prediction is reproducible
assert np.allclose(prediction1['prediction'].values,
prediction2['prediction'].values)
def test_lgt_predict_all_positive_reg(iclaims_training_data):
df = iclaims_training_data
lgt = LGTMAP(
response_col='claims',
date_col='week',
regressor_col=['trend.unemploy', 'trend.filling', 'trend.job'],
regressor_sign=['+', '+', '+'],
seasonality=52,
seed=8888,
)
lgt.fit(df)
predicted_df = lgt.predict(df, decompose=True)
assert any(predicted_df['regression'].values)
def test_lgt_map_univariate(synthetic_data, estimator_type):
train_df, test_df, coef = synthetic_data
lgt = LGTMAP(response_col='response',
date_col='week',
seasonality=52,
verbose=False,
estimator_type=estimator_type)
lgt.fit(train_df)
predict_df = lgt.predict(test_df)
expected_columns = ['week', 'prediction']
expected_shape = (51, len(expected_columns))
expected_num_parameters = 12 # no `lp__` parameter in optimizing()
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(lgt._posterior_samples) == expected_num_parameters
def test_lgt_map_single_regressor(iclaims_training_data):
df = iclaims_training_data
df['claims'] = np.log(df['claims'])
regressor_col = ['trend.unemploy']
lgt = LGTMAP(
response_col='claims',
date_col='week',
regressor_col=regressor_col,
seasonality=52,
seed=8888,
)
lgt.fit(df)
predicted_df = lgt.predict(df)
expected_num_parameters = 13
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
assert predicted_df.shape[0] == df.shape[0]
assert predicted_df.columns.tolist() == expected_columns
assert len(lgt._posterior_samples) == expected_num_parameters
def test_lgt_map_fit(synthetic_data, seasonality, estimator_type):
train_df, test_df, coef = synthetic_data
lgt = LGTMAP(
response_col='response',
date_col='week',
seasonality=seasonality,
verbose=False,
estimator_type=estimator_type
)
lgt.fit(train_df)
predict_df = lgt.predict(test_df)
expected_num_parameters = 10
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
if seasonality == 52:
expected_num_parameters += 2
expected_shape = (51, len(expected_columns))
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(lgt._posterior_samples) == expected_num_parameters