def cdnow_customers():
return load_cdnow()
import os
import pandas as pd
import pytest
import matplotlib
matplotlib.use('AGG') # use a non-interactive backend
from matplotlib import pyplot as plt
from lifetimes import plotting
from lifetimes import BetaGeoFitter, ParetoNBDFitter, ModifiedBetaGeoFitter
from lifetimes.datasets import load_cdnow, load_transaction_data
from lifetimes import utils
bgf = BetaGeoFitter()
cd_data = load_cdnow()
bgf.fit(cd_data['frequency'],
cd_data['recency'],
cd_data['T'],
iterative_fitting=1)
@pytest.mark.plottest
class TestPlotting():
@pytest.mark.mpl_image_compare(tolerance=30)
def test_plot_period_transactions(self):
plt.figure()
plotting.plot_period_transactions(bgf)
return plt.gcf()
@pytest.mark.mpl_image_compare(tolerance=30)
def test_plot_period_transactions_parento(self):
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])
import os
import pandas as pd
import pytest
import matplotlib
matplotlib.use('AGG') # use a non-interactive backend
from matplotlib import pyplot as plt
from lifetimes import plotting
from lifetimes import BetaGeoFitter, ParetoNBDFitter, ModifiedBetaGeoFitter
from lifetimes.datasets import load_cdnow, load_transaction_data
from lifetimes import utils
bgf = BetaGeoFitter()
cd_data = load_cdnow()
bgf.fit(cd_data['frequency'], cd_data['recency'], cd_data['T'], iterative_fitting=1)
@pytest.mark.plottest
class TestPlotting():
@pytest.mark.mpl_image_compare(tolerance=30)
def test_plot_period_transactions(self):
plt.figure()
plotting.plot_period_transactions(bgf)
return plt.gcf()
@pytest.mark.mpl_image_compare(tolerance=30)
def test_plot_period_transactions_parento(self):
pnbd = ParetoNBDFitter()
pnbd.fit(cd_data['frequency'], cd_data['recency'], cd_data['T'], iterative_fitting=1)
from __future__ import print_function
import numpy as np
import pandas as pd
import numpy.testing as npt
import lifetimes.estimation as estimation
import lifetimes.utils as utils
from lifetimes.datasets import load_cdnow, load_summary_data_with_monetary_value, load_donations
cdnow_customers = load_cdnow()
cdnow_customers_with_monetary_value = load_summary_data_with_monetary_value()
donations = load_donations()
class TestBetaGeoBetaBinomFitter():
def test_params_out_is_close_to_Hardie_paper(self):
bbtf = estimation.BetaGeoBetaBinomFitter()
bbtf.fit(
donations['frequency'],
donations['recency'],
donations['n'],
donations['n_custs'],
)
expected = np.array([1.204, 0.750, 0.657, 2.783])
npt.assert_array_almost_equal(expected, np.array(bbtf._unload_params('alpha','beta','gamma','delta')),
decimal=2)
def test_prob_alive_is_close_to_Hardie_paper_table_6(self):
"""Table 6: P(Alive in 2002) as a Function of Recency and Frequency"""
''' Created on 22 oct. 2015 @author: mrousseau - toto ''' from lifetimes.datasets import load_cdnow from lifetimes.estimation import BetaGeoFitter, GammaGammaFitter, ParetoNBDFitter data = load_cdnow(index_col=[0]) print data.head() print type(data) from scikits.recommenders.knn import UserBasedRecommender bgf = ParetoNBDFitter(penalizer_coef=0.0) bgf.fit(data['frequency'], data['recency'], data['T']) print bgf print bgf.conditional_expected_number_of_purchases_up_to_time(1,2,45,90) print bgf.conditional_probability_alive(2,45,90) from lifetimes.plotting import plot_frequency_recency_matrix plot_frequency_recency_matrix(bgf) #from matplotlib import pyplot as plt #plt.show() #from lifetimes.plotting import plot_probability_alive_matrix #plot_probability_alive_matrix(bgf) #plt.show() t = 1
def cdnow_customers():
return load_cdnow()
