def plot_history_alive_min_thresholds(model, summary, transaction_data,
threshold):
"""Plotting function for threshold plot of min customer alive probability
vs pct cumulative customers with probability.
Parameters
----------
model : bgf model, fit to all data
summary : summary set of data, output from summary_data_from_transaction_data function
Returns
-------
saved figure
"""
from lifetimes.utils import coalesce, calculate_alive_path
#make a summary frame with customers with more than one purchase
summary_multiple = summary[summary['frequency'] > 0]
#find all purchase paths for customers, save in a list and then append to paths list
paths = []
for customer in summary_multiple.index:
individual = summary.loc[[customer]]
sp_trans = transaction_data.ix[transaction_data['CustomerNo'] ==
individual.index[0]]
path = calculate_alive_path(model, sp_trans, 'OrderDate',
int(individual['T']), '1D')
paths.append(path)
#find the min path prob for each individual
min_paths = [path.min() for path in paths]
#sort them, then plot the cumulative totals for each threshold (max = 0.7673)
#make a threshold
y = np.arange(0, len(min_paths)) / len(min_paths)
ax = plt.scatter(sorted(min_paths), y)
plt.xlabel('min probability active')
plt.ylabel('cumulative fraction of customers')
plt.title('Fraction of customers with Min Probablity Active')
return ax
def test_calculate_alive_path(example_transaction_data, example_summary_data,
fitted_bg):
user_data = example_transaction_data[example_transaction_data['id'] == 33]
frequency, recency, T = example_summary_data.loc[33]
alive_path = utils.calculate_alive_path(fitted_bg, user_data, 'date', 205)
assert alive_path[0] == 1
assert alive_path[T] == fitted_bg.conditional_probability_alive(
frequency, recency, T)
def get_customer_journey(transactions, bgf, id):
id = int(id)
days_since_birth = 30
sp_trans = transactions.loc[transactions['user_id'] == id]
sp_trans_list = sp_trans.drop('user_id', axis=1).values
path = calculate_alive_path(bgf, sp_trans, 'event_time', days_since_birth, freq="D")
path_dates = pd.date_range(start=min(sp_trans['event_time']), periods=len(path), freq="D")
return create_palive_figure(path, path_dates, sp_trans), sp_trans_list
def plot_history_alive(model,
t,
transactions,
datetime_col,
freq='D',
**kwargs):
"""
Draw a graph showing the probablility of being alive for a customer in time.
Parameters:
model: A fitted lifetimes model
t: the number of time units since the birth we want to draw the p_alive
transactions: a Pandas DataFrame containing the transactions history of the customer_id
datetime_col: the column in the transactions that denotes the datetime the purchase was made
freq: Default 'D' for days. Other examples= 'W' for weekly
"""
from matplotlib import pyplot as plt
start_date = kwargs.pop('start_date', min(transactions[datetime_col]))
ax = kwargs.pop('ax', None) or plt.subplot(111)
# Get purchasing history of user
customer_history = transactions[[datetime_col]].copy()
customer_history.index = pd.DatetimeIndex(customer_history[datetime_col])
# Add transactions column
customer_history['transactions'] = 1
customer_history = customer_history.resample(freq).sum()
# plot alive_path
path = calculate_alive_path(model, transactions, datetime_col, t, freq)
path_dates = pd.date_range(start=min(transactions[datetime_col]),
periods=len(path),
freq=freq)
plt.plot(path_dates, path, '-', label='P_alive')
# plot buying dates
payment_dates = customer_history[
customer_history['transactions'] >= 1].index
plt.vlines(payment_dates.values,
ymin=0,
ymax=1,
colors='r',
linestyles='dashed',
label='purchases')
plt.ylim(0, 1.0)
plt.yticks(np.arange(0, 1.1, 0.1))
plt.xlim(start_date, path_dates[-1])
plt.legend(loc=3)
plt.ylabel('P_alive')
plt.title('History of P_alive')
return ax
def plot_history_alive(model, t, transactions, datetime_col, freq='D', **kwargs):
"""
Draws a graph showing the probablility of being alive for a customer in time
:param model: A fitted lifetimes model
:param t: the number of time units since the birth we want to draw the p_alive
:param transactions: a Pandas DataFrame containing the transactions history of the customer_id
:param datetime_col: the column in the transactions that denotes the datetime the purchase was made
:param freq: Default 'D' for days. Other examples= 'W' for weekly
"""
from matplotlib import pyplot as plt
start_date = kwargs.pop('start_date', min(transactions[datetime_col]))
ax = kwargs.pop('ax', None) or plt.subplot(111)
# Get purchasing history of user
customer_history = transactions[[datetime_col]].copy()
customer_history.index = pd.DatetimeIndex(customer_history[datetime_col])
# Add transactions column
customer_history['transactions'] = 1
customer_history = customer_history.resample(freq, how='sum').reset_index()
# plot alive_path
path = calculate_alive_path(model, transactions, datetime_col, t, freq)
path_dates = pd.date_range(start=min(transactions[datetime_col]), periods=len(path), freq=freq)
plt.plot(path_dates, path, '-', label='P_alive')
# plot buying dates
payment_dates = customer_history[customer_history['transactions'] >= 1]['index']
plt.vlines(payment_dates.values, ymin=0, ymax=1, colors='r', linestyles='dashed', label='purchases')
plt.ylim(0, 1.0)
plt.yticks(np.arange(0, 1.1, 0.1))
plt.xlim(start_date, path_dates[-1])
plt.legend(loc=3)
plt.ylabel('P_alive')
plt.title('History of P_alive')
return ax
def test_calculate_alive_path(example_transaction_data, example_summary_data, fitted_bg):
user_data = example_transaction_data[example_transaction_data['id'] == 33]
frequency, recency, T = example_summary_data.loc[33]
alive_path = utils.calculate_alive_path(fitted_bg, user_data, 'date', 205)
assert alive_path[0] == 1
assert alive_path[T] == fitted_bg.conditional_probability_alive(frequency, recency, T)
def plot_history_alive(model, t, transactions, datetime_col, freq='D',
start_date=None, ax=None, **kwargs):
"""
Draw a graph showing the probablility of being alive for a customer in time.
Parameters
----------
model: lifetimes model
A fitted lifetimes model.
t: int
the number of time units since the birth we want to draw the p_alive
transactions: pandas DataFrame
DataFrame containing the transactions history of the customer_id
datetime_col: str
The column in the transactions that denotes the datetime the purchase was made
freq: str, optional
Default 'D' for days. Other examples= 'W' for weekly
start_date: datetime, optional
Limit xaxis to start date
ax: matplotlib.AxesSubplot, optional
Using user axes
kwargs
Passed into the matplotlib.pyplot.plot command.
Returns
-------
axes: matplotlib.AxesSubplot
"""
from matplotlib import pyplot as plt
if start_date is None:
start_date = min(transactions[datetime_col])
if ax is None:
ax = plt.subplot(111)
# Get purchasing history of user
customer_history = transactions[[datetime_col]].copy()
customer_history.index = pd.DatetimeIndex(customer_history[datetime_col])
# Add transactions column
customer_history['transactions'] = 1
customer_history = customer_history.resample(freq).sum()
# plot alive_path
path = calculate_alive_path(model, transactions, datetime_col, t, freq)
path_dates = pd.date_range(start=min(transactions[datetime_col]), periods=len(path), freq=freq)
plt.plot(path_dates, path, '-', label='P_alive')
# plot buying dates
payment_dates = customer_history[customer_history['transactions'] >= 1].index
plt.vlines(payment_dates.values, ymin=0, ymax=1, colors='r', linestyles='dashed', label='purchases')
plt.ylim(0, 1.0)
plt.yticks(np.arange(0, 1.1, 0.1))
plt.xlim(start_date, path_dates[-1])
plt.legend(loc=3)
plt.ylabel('P_alive')
plt.title('History of P_alive')
return ax
def plot_history_alive(model, t, transactions, datetime_col, freq='D',
start_date=None, end_date=None, ax=None,
title='Evolution of survival probability', **kwargs):
"""
Draw a graph showing the probablility of being alive for a customer in time.
Parameters
----------
model: lifetimes model
A fitted lifetimes model.
t: int
the number of time units since the birth we want to draw the p_alive
transactions: pandas DataFrame
DataFrame containing the transactions history of the customer_id
datetime_col: str
The column in the transactions that denotes the datetime the purchase
was made
freq: str, optional
Default 'D' for days. Other examples= 'W' for weekly
start_date: datetime, optional
Limit xaxis to start date
ax: matplotlib.AxesSubplot, optional
Using user axes
title: str, optional
Title of the plot.
kwargs
Passed into the matplotlib.pyplot.plot command.
Returns
-------
axes: matplotlib.AxesSubplot
"""
from matplotlib import pyplot as plt
first_transaction_date = transactions[datetime_col].min()
if start_date is None:
start_date = dt.datetime.strptime(first_transaction_date,"%Y-%m-%d") - \
dt.timedelta(days=7)
if ax is None:
ax = plt.subplot(111)
# Get purchasing history of user
customer_history = transactions[[datetime_col]].copy()
customer_history.index = pd.DatetimeIndex(customer_history[datetime_col])
# Add transactions column
customer_history['transactions'] = 1
customer_history = customer_history.resample(freq).sum()
current_date = dt.datetime.strftime(dt.datetime.now(),"%Y-%m-%d")
refresh_date = dt.datetime.strftime(
dt.datetime.strptime(first_transaction_date,"%Y-%m-%d") + dt.timedelta(days=t),
"%Y-%m-%d")
periods_to_plot = (dt.datetime.strptime(end_date,"%Y-%m-%d") \
- start_date
).days
if freq == 'W':
periods_to_plot = int(periods_to_plot/7.)
# plot alive_path
path = pd.concat(
[pd.Series([None]*7),
calculate_alive_path(model, transactions, datetime_col, periods_to_plot, freq)*100.])
path_dates = pd.date_range(start=start_date, periods=len(path), freq=freq)
past_dates_path = path_dates[path_dates<=refresh_date]
past_path = path[path_dates<=refresh_date]
future_dates_path = path_dates[path_dates>=refresh_date]
future_path = path[path_dates>=refresh_date]
plt.plot(past_dates_path, past_path, color=glovo_gray, ls='-', label='P_alive')
plt.plot(future_dates_path, future_path, color=glovo_gray, ls='--')
# plot buying dates
payment_dates = customer_history[customer_history['transactions'] >= 1].index
plt.vlines(payment_dates.values, ymin=0, ymax=100,
colors=glovo_green, linestyles='dashed', label='Orders')
plt.vlines(refresh_date, ymin=0, ymax=100,
colors=glovo_yellow, linestyles='solid', label='Last refresh')
plt.vlines(current_date, ymin=0, ymax=100,
colors='red', linestyles='solid', label='Today')
plt.ylim(0, 105)
plt.yticks(np.arange(0, 110, 10))
plt.xticks(rotation=-20.)
plt.xlim(start_date, path_dates[-1])
plt.legend(loc=3)
plt.ylabel('P_alive (%)')
plt.title(title)
return ax