def test_plot_incremental_transactions(self):
"""Test plotting incremental transactions with CDNOW example."""
transactions = load_dataset('CDNOW_sample.txt', header=None, sep='\s+')
transactions.columns = [
'id_total', 'id_sample', 'date', 'num_cd_purc', 'total_value'
]
t = 39
freq = 'W'
transactions_summary = utils.summary_data_from_transaction_data(
transactions,
'id_sample',
'date',
datetime_format='%Y%m%d',
observation_period_end='19970930',
freq=freq)
bgf = BetaGeoFitter(penalizer_coef=0.01)
bgf.fit(transactions_summary['frequency'],
transactions_summary['recency'], transactions_summary['T'])
plt.figure()
plotting.plot_incremental_transactions(bgf,
transactions,
'date',
'id_sample',
2 * t,
t,
freq=freq,
xlabel='week',
datetime_format='%Y%m%d')
return plt.gcf()
def test_plot_incremental_transactions(self, cdnow_transactions, bgf_transactions):
"""Test plotting incremental transactions with CDNOW example."""
t = 39
freq = 'W'
plt.figure()
plotting.plot_incremental_transactions(
bgf_transactions, cdnow_transactions, 'date', 'id_sample', 2 * t, t, freq=freq,
xlabel='week', datetime_format='%Y%m%d')
return plt.gcf()
def evaluation_plots(plot_type):
"""
Evaluation Plots:
- Tracking Cumulative Transactions
- Tracking Daily Transactions
- Frequency of Repeated Transactions
- Calibration vs Holdout.
Parameters
----------
plot_type: str.
"tracking" - Tracking Cumulative and Tracking Daily Transactions.
"repeated" - Frequency of Repeated Transactions.
"calibration_holdout" - Calibration vs Holdout Purchases.
"""
# Loading Calibration Model.
cal_bg_nbd = BetaGeoFitter(penalizer_coef=0.0)
cal_bg_nbd.load_model(path="models/calibration_model.pkl")
# Loading summary_cal_holdout dataset.
summary_cal_holdout = pd.read_csv("datasets/summary_cal_holdout.csv")
# Loading Transactions.
transactions = pd.read_csv("datasets/transactions.csv")
if plot_type == "tracking":
fig = plt.figure(figsize=(20, 4))
plot_cumulative_transactions(model=cal_bg_nbd,
transactions=transactions,
datetime_col="order_purchase_timestamp",
customer_id_col="customer_unique_id",
t=604,
t_cal=512,
freq="D",
ax=fig.add_subplot(121))
plot_incremental_transactions(model=cal_bg_nbd,
transactions=transactions,
datetime_col="order_purchase_timestamp",
customer_id_col="customer_unique_id",
t=604,
t_cal=512,
freq="D",
ax=fig.add_subplot(122))
elif plot_type == "repeated":
plot_period_transactions(model=cal_bg_nbd)
elif plot_type == "calibration_holdout":
plot_calibration_purchases_vs_holdout_purchases(
model=cal_bg_nbd, calibration_holdout_matrix=summary_cal_holdout)
return
def test_plot_incremental_transactions(self, cdnow_transactions,
bgf_transactions):
"""Test plotting incremental transactions with CDNOW example."""
actual = [
np.nan, 3.0, 14.0, 27.0, 23.0, 55.0, 51.0, 67.0, 73.0, 62.0, 91.0,
89.0, 100.0, 84.0, 86.0, 76.0, 69.0, 63.0, 58.0, 68.0, 58.0, 60.0,
48.0, 42.0, 77.0, 84.0, 56.0, 48.0, 43.0, 66.0, 72.0, 33.0, 48.0,
60.0, 48.0, 49.0, 43.0, 47.0, 54.0, 53.0, 51.0, 45.0, 57.0, 51.0,
71.0, 59.0, 54.0, 49.0, 54.0, 66.0, 55.0, 31.0, 42.0, 50.0, 40.0,
34.0, 42.0, 41.0, 44.0, 42.0, 57.0, 61.0, 56.0, 56.0, 61.0, 36.0,
39.0, 40.0, 29.0, 38.0, 41.0, 30.0, 32.0, 40.0, 45.0, 52.0, 28.0,
34.0
]
predicted = [
np.nan, 10.79, 17.52, 24.76, 32.23, 40.38, 47.16, 54.12, 61.71,
68.88, 75.35, 80.49, 81.0, 79.08, 77.38, 75.85, 74.47, 73.21,
72.06, 71.0, 70.01, 69.09, 68.24, 67.43, 66.68, 65.97, 65.29,
64.66, 64.05, 63.47, 62.92, 62.4, 61.9, 61.41, 60.95, 60.51, 60.08,
59.67, 59.28, 58.9, 58.53, 58.17, 57.82, 57.49, 57.17, 56.85,
56.55, 56.25, 55.96, 55.68, 55.41, 55.15, 54.89, 54.64, 54.39,
54.15, 53.92, 53.69, 53.47, 53.25, 53.04, 52.83, 52.62, 52.42,
52.23, 52.04, 51.85, 51.67, 51.48, 51.31, 51.13, 50.96, 50.8,
50.63, 50.47, 50.31, 50.16, 50.0
]
labels = ['actual', 'predicted']
t = 39
freq = 'W'
ax = plotting.plot_incremental_transactions(bgf_transactions,
cdnow_transactions,
'date',
'id_sample',
2 * t,
t,
freq=freq,
xlabel='week',
datetime_format='%Y%m%d')
lines = ax.lines
legend = ax.legend_
actual_y = lines[0].get_data()[1]
predicted_y = lines[1].get_data()[1]
assert_allclose(actual, actual_y, rtol=0.01)
assert_allclose(predicted, predicted_y, rtol=0.01)
assert_array_equal([e.get_text() for e in legend.get_texts()], labels)
assert_equal(ax.title.get_text(), "Tracking Daily Transactions")
assert_equal(ax.xaxis.get_label().get_text(), "week")
assert_equal(ax.yaxis.get_label().get_text(), "Transactions")
plt.close()