def test_expected_cumulative_transactions_dedups_inside_a_time_period(
fitted_bg, example_transaction_data):
by_week = utils.expected_cumulative_transactions(fitted_bg,
example_transaction_data,
'date',
'id',
10,
freq='W')
by_day = utils.expected_cumulative_transactions(fitted_bg,
example_transaction_data,
'date',
'id',
10,
freq='D')
assert (by_week['actual'] >= by_day['actual']).all()
def test_expected_cumulative_transactions_dedups_inside_a_time_period(
fitted_bg, example_transaction_data):
by_week = utils.expected_cumulative_transactions(fitted_bg,
example_transaction_data,
"date",
"id",
10,
freq="W")
by_day = utils.expected_cumulative_transactions(fitted_bg,
example_transaction_data,
"date",
"id",
10,
freq="D")
assert (by_week["actual"] >= by_day["actual"]).all()
def df_cum_transactions(cdnow_transactions):
datetime_col = 'date'
customer_id_col = 'id_sample'
t = 25 * 7
datetime_format = '%Y%m%d'
freq = 'D'
observation_period_end = '19970930'
freq_multiplier = 7
transactions_summary = utils.summary_data_from_transaction_data(
cdnow_transactions, customer_id_col, datetime_col,
datetime_format=datetime_format, freq=freq, freq_multiplier=freq_multiplier,
observation_period_end=observation_period_end)
transactions_summary = transactions_summary.reset_index()
model = ParetoNBDFitter()
model.fit(transactions_summary['frequency'],
transactions_summary['recency'],
transactions_summary['T'])
df_cum = utils.expected_cumulative_transactions(
model, cdnow_transactions, datetime_col, customer_id_col, t,
datetime_format, freq, set_index_date=False, freq_multiplier=freq_multiplier)
return df_cum
def plot_incremental_transactions(model,
transactions,
datetime_col,
customer_id_col,
t,
t_cal,
datetime_format=None,
freq='D',
set_index_date=False,
title='Tracking Daily Transactions',
xlabel='day',
ylabel='Transactions',
**kwargs):
"""
Plot a figure of the predicted and actual cumulative transactions of users
Parameters:
model: A fitted lifetimes model
transactions: a Pandas DataFrame containing the transactions history of the customer_id
datetime_col: the column in transactions that denotes the datetime the purchase was made.
customer_id_col: the column in transactions that denotes the customer_id
t: the number of time units since the begining of
data for which we want to calculate cumulative transactions
datetime_format: a string that represents the timestamp format. Useful if Pandas can't understand
the provided format.
freq: Default 'D' for days, 'W' for weeks, 'M' for months... etc. Full list here:
http://pandas.pydata.org/pandas-docs/stable/timeseries.html#dateoffset-objects
set_index_date: when True set date as Pandas DataFrame index, default False - number of time units
title: figure title
xlabel: figure xlabel, if set_index_date is True will be overwrited to date
ylabel: figure ylabel
kwargs: passed into the pandas.DataFrame.plot command.
"""
from matplotlib import pyplot as plt
ax = kwargs.pop('ax', None) or plt.subplot(111)
df_cum_transactions = expected_cumulative_transactions(
model,
transactions,
datetime_col,
customer_id_col,
t,
datetime_format=datetime_format,
freq=freq,
set_index_date=set_index_date)
# get incremental from cumulative transactions
df_cum_transactions = df_cum_transactions.apply(lambda x: x - x.shift(1))
ax = df_cum_transactions.plot(ax=ax, title=title, **kwargs)
if set_index_date:
x_vline = df_cum_transactions.index[int(t_cal)]
xlabel = 'date'
else:
x_vline = t_cal
ax.axvline(x=x_vline, color='r', linestyle='--')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
return ax
def test_expected_cumulative_transactions_date_index(cdnow_transactions):
"""
Test set_index as date for cumulative transactions and bgf fitter.
Get first 14 cdnow transactions dates and validate that date index,
freq_multiplier = 1 working and compare with tested data for last 4 records.
dates = ['1997-01-11', '1997-01-12', '1997-01-13', '1997-01-14']
actual_trans = [11, 12, 15, 19]
expected_trans = [10.67, 12.67, 14.87, 17.24]
"""
datetime_col = "date"
customer_id_col = "id_sample"
t = 14
datetime_format = "%Y%m%d"
freq = "D"
observation_period_end = "19970930"
freq_multiplier = 1
transactions_summary = utils.summary_data_from_transaction_data(
cdnow_transactions,
customer_id_col,
datetime_col,
datetime_format=datetime_format,
freq=freq,
freq_multiplier=freq_multiplier,
observation_period_end=observation_period_end,
)
transactions_summary = transactions_summary.reset_index()
model = BetaGeoFitter()
model.fit(transactions_summary["frequency"],
transactions_summary["recency"], transactions_summary["T"])
df_cum = utils.expected_cumulative_transactions(
model,
cdnow_transactions,
datetime_col,
customer_id_col,
t,
datetime_format,
freq,
set_index_date=True,
freq_multiplier=freq_multiplier,
)
dates = ["1997-01-11", "1997-01-12", "1997-01-13", "1997-01-14"]
actual_trans = [11, 12, 15, 19]
expected_trans = [10.67, 12.67, 14.87, 17.24]
date_index = df_cum.iloc[-4:].index.to_timestamp().astype(str)
actual = df_cum["actual"].iloc[-4:].values
predicted = df_cum["predicted"].iloc[-4:].values.round(2)
assert all(dates == date_index)
assert_allclose(actual, actual_trans)
assert_allclose(predicted, expected_trans, atol=1e-2)
def df_cum_transactions(cdnow_transactions):
datetime_col = "date"
customer_id_col = "id_sample"
t = 25 * 7
datetime_format = "%Y%m%d"
freq = "D"
observation_period_end = "19970930"
freq_multiplier = 7
transactions_summary = utils.summary_data_from_transaction_data(
cdnow_transactions,
customer_id_col,
datetime_col,
datetime_format=datetime_format,
freq=freq,
freq_multiplier=freq_multiplier,
observation_period_end=observation_period_end,
)
transactions_summary = transactions_summary.reset_index()
model = ParetoNBDFitter()
model.fit(transactions_summary["frequency"],
transactions_summary["recency"], transactions_summary["T"])
df_cum = utils.expected_cumulative_transactions(
model,
cdnow_transactions,
datetime_col,
customer_id_col,
t,
datetime_format,
freq,
set_index_date=False,
freq_multiplier=freq_multiplier,
)
return df_cum
def plot_cumulative_transactions(model, transactions, datetime_col, customer_id_col, t, t_cal,
datetime_format=None, freq='D', set_index_date=False,
title='Tracking Cumulative Transactions',
xlabel='day', ylabel='Cumulative Transactions',
ax=None, **kwargs):
"""
Plot a figure of the predicted and actual cumulative transactions of users.
Parameters
----------
model: lifetimes model
A fitted lifetimes model
transactions: pandas DataFrame
DataFrame containing the transactions history of the customer_id
datetime_col: str
The column in transactions that denotes the datetime the purchase was made.
customer_id_col: str
The column in transactions that denotes the customer_id
t: float
The number of time units since the begining of
data for which we want to calculate cumulative transactions
datetime_format: str, optional
A string that represents the timestamp format. Useful if Pandas
can't understand the provided format.
freq: str, optional
Default 'D' for days, 'W' for weeks, 'M' for months... etc.
Full list here:
http://pandas.pydata.org/pandas-docs/stable/timeseries.html#dateoffset-objects
set_index_date: bool, optional
When True set date as Pandas DataFrame index, default False - number of time units
title: str, optional
Figure title
xlabel: str, optional
Figure xlabel
ylabel: str, optional
Figure ylabel
ax: matplotlib.AxesSubplot, optional
Using user axes
kwargs
Passed into the pandas.DataFrame.plot command.
Returns
-------
axes: matplotlib.AxesSubplot
"""
from matplotlib import pyplot as plt
if ax is None:
ax = plt.subplot(111)
df_cum_transactions = expected_cumulative_transactions(model, transactions, datetime_col,
customer_id_col, t,
datetime_format=datetime_format, freq=freq,
set_index_date=set_index_date)
ax = df_cum_transactions.plot(ax=ax, title=title, **kwargs)
if set_index_date:
x_vline = df_cum_transactions.index[int(t_cal)]
xlabel = 'date'
else:
x_vline = t_cal
ax.axvline(x=x_vline, color='r', linestyle='--')
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
return ax
