def fit(self, frequency, recency, T, iterative_fitting=1, initial_params=None, verbose=False):
"""
This methods fits the data to the Pareto/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve performances but possibly
hurt estimates.
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, with additional properties and methods like params_ and plot
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
params, self._negative_log_likelihood_ = _fit(self._negative_log_likelihood,
[frequency, recency, T, self.penalizer_coef],
iterative_fitting,
initial_params,
4,
verbose)
self.params_ = OrderedDict(zip(['r', 'alpha', 's', 'beta'], params))
self.data = DataFrame(vconcat[frequency, recency, T], columns=['frequency', 'recency', 'T'])
self.generate_new_data = lambda size=1: pareto_nbd_model(T, *params, size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self, frequency, monetary_value, iterative_fitting=5, initial_params=None, verbose=False):
"""
This methods fits the data to the Gamma/Gamma model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
monetary_value: the monetary value vector of customer's purchases (denoted m in literature).
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve performances but possibly
hurt estimates. This model is not very stable so we suggest >10 for best estimates evaluation.
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, fitted and with parameters estimated
"""
params, self._negative_log_likelihood_ = _fit(self._negative_log_likelihood,
[frequency, monetary_value, self.penalizer_coef],
iterative_fitting,
initial_params,
3,
verbose)
self.data = DataFrame(vconcat[frequency, monetary_value], columns=['frequency', 'monetary_value'])
self.params_ = OrderedDict(zip(['p', 'q', 'v'], params))
return self
def fit(self,
frequency,
monetary_value,
iterative_fitting=5,
initial_params=None,
verbose=False):
"""
This methods fits the data to the Gamma/Gamma model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
monetary_value: the monetary value vector of customer's purchases (denoted m in literature).
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve performances but possibly
hurt estimates. This model is not very stable so we suggest >10 for best estimates evaluation.
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, fitted and with parameters estimated
"""
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
[frequency, monetary_value, self.penalizer_coef],
iterative_fitting, initial_params, 3, verbose)
self.data = DataFrame(vconcat[frequency, monetary_value],
columns=['frequency', 'monetary_value'])
self.params_ = OrderedDict(zip(['p', 'q', 'v'], params))
return self
def fit(self,
frequency,
monetary_value,
iterative_fitting=4,
initial_params=None,
verbose=False,
tol=1e-4):
"""
This methods fits the data to the Gamma/Gamma model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
monetary_value: the monetary value vector of customer's purchases (denoted m in literature).
iterative_fitting: perform iterative_fitting fits over random/warm-started initial params.
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
tol: tolerance for termination of the function minimization process.
Returns:
self, fitted and with parameters estimated
"""
_check_inputs(frequency, monetary_value=monetary_value)
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
[frequency, monetary_value, self.penalizer_coef],
iterative_fitting, initial_params, 3, verbose, tol)
self.data = DataFrame(vconcat[frequency, monetary_value],
columns=['frequency', 'monetary_value'])
self.params_ = OrderedDict(zip(['p', 'q', 'v'], params))
return self
def fit(self, frequency, recency, n, n_custs, verbose=False):
"""
Fit the BG/BB model.
Parameters:
frequency: Total periods with observed transactions
recency: Period of most recent transaction
n: Number of transaction opportunities
n_custs: Number of customers with given frequency/recency/T. Fader and Hardie condense
the individual RFM matrix into all observed combinations of frequency/recency/T. This
parameter represents the count of customers with a given purchase pattern. Instead of
calculating individual loglikelihood, the loglikelihood is calculated for each pattern and
multiplied by the number of customers with that pattern.
Returns: self
"""
frequency = asarray(frequency)
recency = asarray(recency)
n = asarray(n)
n_custs = asarray(n_custs)
_check_inputs(frequency, recency, n)
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
[frequency, recency, n, n_custs, self.penalizer_coef], 0,
np.ones(4), 4, verbose)
self.params_ = OrderedDict(
zip(['alpha', 'beta', 'gamma', 'delta'], params))
self.data = DataFrame(vconcat[frequency, recency, n, n_custs],
columns=['frequency', 'recency', 'n', 'n_custs'])
return self
def fit(self, frequency, recency, n, n_custs, verbose=False):
"""
Fit the BG/BB model.
Parameters:
frequency: Total periods with observed transactions
recency: Period of most recent transaction
n: Number of transaction opportunities
n_custs: Number of customers with given frequency/recency/T. Fader and Hardie condense
the individual RFM matrix into all observed combinations of frequency/recency/T. This
parameter represents the count of customers with a given purchase pattern. Instead of
calculating individual loglikelihood, the loglikelihood is calculated for each pattern and
multiplied by the number of customers with that pattern.
Returns: self
"""
frequency = asarray(frequency)
recency = asarray(recency)
n = asarray(n)
n_custs= asarray(n_custs)
_check_inputs(frequency, recency, n)
params, self._negative_log_likelihood_ = _fit(self._negative_log_likelihood,
[frequency, recency, n, n_custs, self.penalizer_coef],
0,
np.ones(4),
4,
verbose)
self.params_ = OrderedDict(zip(['alpha','beta','gamma','delta'], params))
self.data = DataFrame(vconcat[frequency, recency, n, n_custs],
columns=['frequency','recency','n','n_custs'])
return self
def fit(self, frequency, monetary_value, iterative_fitting=4, initial_params=None, verbose=False, tol=1e-4):
"""
This methods fits the data to the Gamma/Gamma model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
monetary_value: the monetary value vector of customer's purchases (denoted m in literature).
iterative_fitting: perform iterative_fitting fits over random/warm-started initial params.
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
tol: tolerance for termination of the function minimization process.
Returns:
self, fitted and with parameters estimated
"""
_check_inputs(frequency, monetary_value=monetary_value)
params, self._negative_log_likelihood_ = _fit(self._negative_log_likelihood,
[frequency, monetary_value, self.penalizer_coef],
iterative_fitting,
initial_params,
3,
verbose,
tol)
self.data = DataFrame(vconcat[frequency, monetary_value], columns=['frequency', 'monetary_value'])
self.params_ = OrderedDict(zip(['p', 'q', 'v'], params))
return self
def fit(self,
frequency,
recency,
T,
iterative_fitting=1,
initial_params=None,
verbose=False,
tol=1e-4,
index=None):
"""
This methods fits the data to the BG/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform iterative_fitting fits over random/warm-started initial params
initial_params: set the initial parameters for the fitter.
verbose: set to true to print out convergence diagnostics.
index: index for resulted DataFrame which is accessible via self.data
Returns:
self, with additional properties and methods like params_ and predict
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
self._scale = _scale_time(T)
scaled_recency = recency * self._scale
scaled_T = T * self._scale
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
[frequency, scaled_recency, scaled_T, self.penalizer_coef],
iterative_fitting, initial_params, 4, verbose, tol)
self.params_ = OrderedDict(zip(['r', 'alpha', 'a', 'b'], params))
self.params_['alpha'] /= self._scale
self.data = DataFrame(vconcat[frequency, recency, T],
columns=['frequency', 'recency', 'T'])
if index is not None:
self.data.index = index
self.generate_new_data = lambda size=1: beta_geometric_nbd_model(
T, *self._unload_params('r', 'alpha', 'a', 'b'), size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self, frequency, recency, T, iterative_fitting=1, initial_params=None, verbose=False):
"""
This methods fits the data to the BG/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve peformance but possibly
hurt estimates.
initial_params: set the initial parameters for the fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, with additional properties and methods like params_ and predict
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
self._scale = _scale_time(T)
scaled_recency = recency * self._scale
scaled_T = T * self._scale
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
frequency,
scaled_recency,
scaled_T,
iterative_fitting,
self.penalizer_coef,
initial_params,
verbose,
)
self.params_ = OrderedDict(zip(["r", "alpha", "a", "b"], params))
self.params_["alpha"] /= self._scale
self.data = DataFrame(vconcat[frequency, recency, T], columns=["frequency", "recency", "T"])
self.generate_new_data = lambda size=1: beta_geometric_nbd_model(
T, *self._unload_params("r", "alpha", "a", "b"), size=size
)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self,
frequency,
recency,
T,
iterative_fitting=1,
initial_params=None,
verbose=False):
"""
This methods fits the data to the BG/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve peformance but possibly
hurt estimates.
initial_params: set the initial parameters for the fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, with additional properties and methods like params_ and predict
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
self._scale = _scale_time(T)
scaled_recency = recency * self._scale
scaled_T = T * self._scale
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood, frequency, scaled_recency, scaled_T,
iterative_fitting, self.penalizer_coef, initial_params, verbose)
self.params_ = OrderedDict(zip(['r', 'alpha', 'a', 'b'], params))
self.params_['alpha'] /= self._scale
self.data = DataFrame(vconcat[frequency, recency, T],
columns=['frequency', 'recency', 'T'])
self.generate_new_data = lambda size=1: beta_geometric_nbd_model(
T, *self._unload_params('r', 'alpha', 'a', 'b'), size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self, frequency, recency, T, iterative_fitting=1, initial_params=None, verbose=False, tol=1e-4):
"""
This methods fits the data to the BG/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform iterative_fitting fits over random/warm-started initial params
initial_params: set the initial parameters for the fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, with additional properties and methods like params_ and predict
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
self._scale = _scale_time(T)
scaled_recency = recency * self._scale
scaled_T = T * self._scale
params, self._negative_log_likelihood_ = _fit(self._negative_log_likelihood,
[frequency, scaled_recency, scaled_T, self.penalizer_coef],
iterative_fitting,
initial_params,
4,
verbose,
tol)
self.params_ = OrderedDict(zip(['r', 'alpha', 'a', 'b'], params))
self.params_['alpha'] /= self._scale
self.data = DataFrame(vconcat[frequency, recency, T], columns=['frequency', 'recency', 'T'])
self.generate_new_data = lambda size=1: beta_geometric_nbd_model(T, *self._unload_params('r', 'alpha', 'a', 'b'), size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self,
frequency,
recency,
T,
iterative_fitting=1,
initial_params=None,
verbose=False,
tol=1e-4):
"""
This methods fits the data to the Pareto/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform iterative_fitting fits over random/warm-started initial params
initial_params: set initial params for the iterative fitter.
verbose: set to true to print out convergence diagnostics.
Returns:
self, with additional properties and methods like params_ and plot
"""
frequency = asarray(frequency)
recency = asarray(recency)
T = asarray(T)
_check_inputs(frequency, recency, T)
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood,
[frequency, recency, T, self.penalizer_coef], iterative_fitting,
initial_params, 4, verbose, tol)
self.params_ = OrderedDict(zip(['r', 'alpha', 's', 'beta'], params))
self.data = DataFrame(vconcat[frequency, recency, T],
columns=['frequency', 'recency', 'T'])
self.generate_new_data = lambda size=1: pareto_nbd_model(
T, *params, size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self
def fit(self,
frequency,
recency,
T,
iterative_fitting=1,
initial_params=None):
"""
This methods fits the data to the Pareto/NBD model.
Parameters:
frequency: the frequency vector of customers' purchases (denoted x in literature).
recency: the recency vector of customers' purchases (denoted t_x in literature).
T: the vector of customers' age (time since first purchase)
iterative_fitting: perform `iterative_fitting` additional fits to find the best
parameters for the model. Setting to 0 will improve peformance but possibly
hurt estimates.
Returns:
self, with additional properties and methods like params_ and plot
"""
frequency = np.asarray(frequency)
recency = np.asarray(recency)
T = np.asarray(T)
params, self._negative_log_likelihood_ = _fit(
self._negative_log_likelihood, frequency, recency, T,
iterative_fitting, self.penalizer_coef, initial_params)
self.params_ = dict(zip(['r', 'alpha', 's', 'beta'], params))
self.data = pd.DataFrame(np.c_[frequency, recency, T],
columns=['frequency', 'recency', 'T'])
self.generate_new_data = lambda size=1: pareto_nbd_model(
T, *params, size=size)
self.predict = self.conditional_expected_number_of_purchases_up_to_time
return self