def test_consistence_over_T():
params = {'r': 1, 'alpha': 10, 's': 0.8, 'beta': 5}
gen_data = gen.generate_pareto_data_for_T_N(60, 100, params)
# compressed_gen_data = comp.compress_data(gen_data)
fitting_window = [(0, 30), (15, 45), (30, 60)]
t = 365 # time horizon
fitted_pars = []
fitted_Ex = []
for fw in fitting_window:
pareto_model = mod.ParetoNBDModel()
filtered_data = comp.filter_data_by_T(gen_data, fw[0], fw[1])
pareto_model.fit(filtered_data['frequency'],
filtered_data['recency'],
filtered_data['T'],
bootstrap_size=10)
fitted_pars.append((pareto_model.params, pareto_model.params_C))
Ex = pareto_model.expected_number_of_purchases_up_to_time(t)
fitted_Ex.append((Ex.n, Ex.s))
ex_0, ex_err_0 = fitted_Ex[0]
for ex, ex_err in fitted_Ex:
assert math.fabs(ex - ex_0) / math.sqrt(ex_err**2 + ex_err_0**2) < 5
def test_Pareto_expected_purchases_before_fitting():
model = models.ParetoNBDModel()
error_generated = False
try:
_, _ = model.expected_number_of_purchases_up_to_time(1)
except ValueError:
error_generated = True
assert error_generated
def test_Pareto_expected_number_of_purchases_with_error():
fitted_model = _fit_and_simulate(models.ParetoNBDModel(), params, t)
e_x, err_e_x = fitted_model.expected_number_of_sessions_up_to_time_with_errors(
t)
assert e_x is not None and err_e_x is not None
assert math.fabs(
err_e_x - EM_expected_number_of_purchases_up_to_time_error(
fitted_model.fitter, t, fitted_model.params_C)) < 10**-6
def test_params_covariance():
model = _fit_and_simulate(models.ParetoNBDModel(), params, t)
covariance_matrix = np.matrix(model.params_C)
# test symmetry
transpose_covariance = covariance_matrix.transpose()
assert np.all(np.fabs(covariance_matrix - transpose_covariance) < 10**-6)
# test_diagonal
for i in range(len(covariance_matrix)):
assert covariance_matrix.item((i, i)) >= 0
def test_models_fitting_and_simulation():
test_models = [
models.ParetoNBDModel(),
models.BetaGeoModel(),
models.ModifiedBetaGeoModel()
]
for model in test_models:
assert model.params is None
assert model.params_C is None
for model in test_models:
fitted_model = _fit_and_simulate(model=model, parameters=params, t=t)
assert fitted_model.params is not None
assert fitted_model.params_C is not None
def generate_pareto_data_for_T_N(T, N, params):
"""
Quick data generator over time
:param T: Max T to generate
:param N: How many users per T
:param params: The pareto params
:type params: dict
:return: Generated data
"""
from lifetimes import models
pareto = models.ParetoNBDModel()
data = pd.DataFrame()
for t in range(T + 1):
new_data = pareto.generateData(t, params, N)
data = pd.concat([data, new_data])
return data