import numpy.testing as npt
import pytest
import lifetimes.estimation as estimation
import lifetimes.utils as utils
from lifetimes.datasets import load_cdnow, load_summary_data_with_monetary_value, load_donations,\
load_transaction_data
from lifetimes.generate_data import modified_beta_geometric_nbd_model
@pytest.fixture
def cdnow_customers():
return load_cdnow()
cdnow_customers_with_monetary_value = load_summary_data_with_monetary_value()
donations = load_donations()
class TestBaseFitter():
def test_repr(self):
base_fitter = estimation.BaseFitter()
assert repr(base_fitter) == '<lifetimes.BaseFitter>'
base_fitter.params_ = dict(x=12.3, y=42)
base_fitter.data = np.array([1, 2, 3])
assert repr(
base_fitter
) == '<lifetimes.BaseFitter: fitted with 3 subjects, x: 12.30, y: 42.00>'
def test_unload_params(self):
base_fitter = estimation.BaseFitter()
from __future__ import print_function
import numpy as np
import pandas as pd
import numpy.testing as npt
import lifetimes.estimation as estimation
from lifetimes.datasets import load_cdnow, load_summary_data_with_monetary_value
cdnow_customers = load_cdnow()
cdnow_customers_with_monetary_value = load_summary_data_with_monetary_value()
class TestGammaGammaFitter():
def test_params_out_is_close_to_Hardie_paper(self):
ggf = estimation.GammaGammaFitter()
ggf.fit(
cdnow_customers_with_monetary_value['frequency'],
cdnow_customers_with_monetary_value['monetary_value'],
iterative_fitting=3
)
expected = np.array([6.25, 3.74, 15.44])
npt.assert_array_almost_equal(expected, np.array(ggf._unload_params('p', 'q', 'v')), decimal=2)
class TestParetoNBDFitter():
def test_overflow_error(self):
ptf = estimation.ParetoNBDFitter()
params = np.array([10.465, 7.98565181e-03, 3.0516, 2.820])
