def test_dlt_non_seasonal_fit(synthetic_data, estimator_type):
train_df, test_df, coef = synthetic_data
dlt = DLTFull(response_col='response',
date_col='week',
estimator_type=estimator_type)
dlt.fit(train_df)
predict_df = dlt.predict(test_df)
expected_columns = ['week', 'prediction']
expected_shape = (51, len(expected_columns))
expected_num_parameters = 11
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(dlt._posterior_samples) == expected_num_parameters
def test_dlt_full_univariate(synthetic_data, estimator_type):
train_df, test_df, coef = synthetic_data
dlt = DLTFull(response_col='response',
date_col='week',
prediction_percentiles=[5, 95],
seasonality=52,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
dlt.fit(train_df)
predict_df = dlt.predict(test_df)
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (51, len(expected_columns))
expected_num_parameters = 13
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(dlt._posterior_samples) == expected_num_parameters
def test_dlt_full_with_regression(synthetic_data, estimator_type,
regressor_signs):
train_df, test_df, coef = synthetic_data
dlt = DLTFull(response_col='response',
date_col='week',
regressor_col=train_df.columns.tolist()[2:],
regressor_sign=regressor_signs,
prediction_percentiles=[5, 95],
seasonality=52,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
dlt.fit(train_df)
predict_df = dlt.predict(test_df)
regression_out = dlt.get_regression_coefs()
num_regressors = regression_out.shape[0]
expected_columns = [
'week', 'prediction_lower', 'prediction', 'prediction_upper'
]
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_dlt_full_univariate(synthetic_data, estimator_type):
train_df, test_df, coef = synthetic_data
dlt = DLTFull(response_col='response',
date_col='week',
prediction_percentiles=[5, 95],
seasonality=52,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
dlt.fit(train_df)
init_call = dlt.get_init_values()
assert isinstance(init_call, DLTInitializer)
assert init_call.s == 52
init_values = init_call()
assert init_values['init_sea'].shape == (51, )
predict_df = dlt.predict(test_df)
expected_columns = ['week', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (51, len(expected_columns))
expected_num_parameters = 12
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(dlt._posterior_samples) == expected_num_parameters
def test_dlt_full_with_regression(synthetic_data, estimator_type,
regressor_signs):
train_df, test_df, coef = synthetic_data
dlt = DLTFull(response_col='response',
date_col='week',
regressor_col=train_df.columns.tolist()[2:],
regressor_sign=regressor_signs,
prediction_percentiles=[5, 95],
seasonality=52,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
dlt.fit(train_df)
init_call = dlt.get_init_values()
assert isinstance(init_call, DLTInitializer)
init_values = init_call()
assert init_values['init_sea'].shape == (51, )
if regressor_signs.count('+') > 0:
assert init_values['pr_beta'].shape == (regressor_signs.count('+'), )
if regressor_signs.count('-') > 0:
assert init_values['nr_beta'].shape == (regressor_signs.count('-'), )
if regressor_signs.count('=') > 0:
assert init_values['rr_beta'].shape == (regressor_signs.count('='), )
predict_df = dlt.predict(test_df)
regression_out = dlt.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:])
assert np.sum(regression_out['coefficient'].values >= 0) <= \
regressor_signs.count('+') + regressor_signs.count('=')
assert np.sum(regression_out['coefficient'].values <= 0) <= \
regressor_signs.count('-') + regressor_signs.count('=')
def test_dlt_full_reproducibility(synthetic_data, estimator_type,
regressor_signs, seasonality):
train_df, test_df, coef = synthetic_data
dlt_first = DLTFull(response_col='response',
date_col='week',
regressor_col=train_df.columns.tolist()[2:],
regressor_sign=regressor_signs,
prediction_percentiles=[5, 95],
seasonality=seasonality,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
# first fit and predict
dlt_first.fit(train_df)
posteriors_first = copy(dlt_first._posterior_samples)
predict_df_first = dlt_first.predict(test_df)
regression_out_first = dlt_first.get_regression_coefs()
# second fit and predict
# note a new instance must be created to reset the seed
# note both fit and predict contain random generation processes
dlt_second = DLTFull(response_col='response',
date_col='week',
regressor_col=train_df.columns.tolist()[2:],
regressor_sign=regressor_signs,
prediction_percentiles=[5, 95],
seasonality=seasonality,
num_warmup=50,
verbose=False,
estimator_type=estimator_type)
dlt_second.fit(train_df)
posteriors_second = copy(dlt_second._posterior_samples)
predict_df_second = dlt_second.predict(test_df)
regression_out_second = dlt_second.get_regression_coefs()
# assert same posterior keys
assert set(posteriors_first.keys()) == set(posteriors_second.keys())
# assert posterior draws are reproducible
for k, v in posteriors_first.items():
assert np.allclose(posteriors_first[k], posteriors_second[k])
# assert identical regression columns
# this is also checked in posterior samples, but an extra layer just in case
# since this one very commonly retrieved by end users
assert regression_out_first.equals(regression_out_second)
# assert prediction is reproducible
assert predict_df_first.equals(predict_df_second)
msk = (credit_agg_short.loc[:, 'pct_chg_in_sales_from_prev_mnth'].isna())
credit_agg_short.loc[msk, 'pct_chg_in_sales_from_prev_mnth'] = 0
test_size = 14
train_df = credit_agg_short[:-test_size]
test_df = credit_agg_short[-test_size:]
regressors = ['panel_sales', 'transaction_count']
dlt = DLTFull(
response_col='pct_chg_in_sales_from_prev_mnth',
regressor_col=regressors,
date_col='date',
seasonality=1,
seed=2020,
level_sm_input=0.3, # recommend for higher frequency data
regressor_sigma_prior=[0.5] * len(regressors),
regression_penalty='lasso',
period=365,
prediction_percentiles=[5, 95])
dlt.fit(df=train_df)
pystan.check_hmc_diagnostics(dlt)
density_plot = plot_posterior_params(dlt,
kind='density',
incl_trend_params=True,
incl_smooth_params=True)