FrozenLifetimeRegression

class relife.lifetime_model.FrozenLifetimeRegression(regression, covar, *args)

Frozen lifetime regression.

Parameters:

regressionLifetimeRegression

Any lifetime regression.

covarfloat or np.ndarray

Covariate values to be frozen.

*argsfloat or np.ndarray

Additional arguments needed by the model to be frozen.

Attributes:

unfrozen_modelLifetimeRegression

The unfrozen regression model.

argstuple of float or np.ndarray

All the frozen arguments given and necessary to compute model functions.

nb_assetsint

Number of assets passed in frozen arguments. The data is mainly used to control numpy broadcasting and may not interest an user.

Warning

This class is documented for the purpose of clarity and mainly address contributors or advance users. Actually, the recommanded way to instanciate a FrozenLifetimeRegression is use to freeze factory function.

Methods

cdf	The cumulative density function.
chf	The cumulative hazard function.
dhf	The derivate of the hazard function.
hf	The hazard function.
ichf	Inverse cumulative hazard function.
isf	The inverse survival function.
jac_cdf	The jacobian of the cumulative density function.
jac_chf	The jacobian of the cumulative hazard function.
jac_hf	The jacobian of the hazard function.
jac_pdf	The jacobian of the probability density function.
jac_sf	The jacobian of the survival function.
ls_integrate	Lebesgue-Stieltjes integration.
mean	The mean.
median	The median.
moment	n-th order moment.
mrl	The mean residual life function.
pdf	The probability density function.
ppf	The percent point function.
rvs	Random variable sampling.
sf	The survival function.
unfreeze
var	The variance.

cdf(time)

The cumulative density function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

chf(time)

The cumulative hazard function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

dhf(time)

The derivate of the hazard function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

hf(time)

The hazard function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

ichf(cumulative_hazard_rate)

Inverse cumulative hazard function.

Parameters:

cumulative_hazard_ratefloat or np.ndarray

Cumulative hazard rate value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given probability value(s).

isf(probability)

The inverse survival function.

Parameters:

probabilityfloat or np.ndarray

Probability value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given probability value(s).

jac_cdf(time, asarray=False)

The jacobian of the cumulative density function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

asarraybool, default is False

Returns:

np.float64, np.ndarray or tuple of np.float64 or np.ndarray

The derivatives with respect to each parameter. If asarray is False, the function returns a tuple containing the same number of elements as parameters. If asarray is True, the function returns an ndarray whose first dimension equals the number of parameters. This output is equivalent to applying np.stack on the output tuple when asarray is False.

jac_chf(time, asarray=False)

The jacobian of the cumulative hazard function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

asarraybool, default is False

Returns:

np.float64, np.ndarray or tuple of np.float64 or np.ndarray

The derivatives with respect to each parameter. If asarray is False, the function returns a tuple containing the same number of elements as parameters. If asarray is True, the function returns an ndarray whose first dimension equals the number of parameters. This output is equivalent to applying np.stack on the output tuple when asarray is False.

jac_hf(time, asarray=False)

The jacobian of the hazard function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

asarraybool, default is False

Returns:

np.float64, np.ndarray or tuple of np.float64 or np.ndarray

The derivatives with respect to each parameter. If asarray is False, the function returns a tuple containing the same number of elements as parameters. If asarray is True, the function returns an ndarray whose first dimension equals the number of parameters. This output is equivalent to applying np.stack on the output tuple when asarray is False.

jac_pdf(time, asarray=False)

The jacobian of the probability density function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

asarraybool, default is False

Returns:

np.float64, np.ndarray or tuple of np.float64 or np.ndarray

The derivatives with respect to each parameter. If asarray is False, the function returns a tuple containing the same number of elements as parameters. If asarray is True, the function returns an ndarray whose first dimension equals the number of parameters. This output is equivalent to applying np.stack on the output tuple when asarray is False.

jac_sf(time, asarray=False)

The jacobian of the survival function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

asarraybool, default is False

Returns:

np.float64, np.ndarray or tuple of np.float64 or np.ndarray

The derivatives with respect to each parameter. If asarray is False, the function returns a tuple containing the same number of elements as parameters. If asarray is True, the function returns an ndarray whose first dimension equals the number of parameters. This output is equivalent to applying np.stack on the output tuple when asarray is False.

ls_integrate(func, a, b, deg=10)

Lebesgue-Stieltjes integration.

Parameters:

funccallable (in1 ndarray , out1 ndarray)

The callable must have only one ndarray object as argument and one ndarray object as output

andarray (maximum number of dimension is 2)

Lower bound(s) of integration.

bndarray (maximum number of dimension is 2)

Upper bound(s) of integration. If lower bound(s) is infinite, use np.inf as value.)

degint, default 10

Degree of the polynomials interpolation

Returns:

np.ndarray

Lebesgue-Stieltjes integral of func from a to b.

mean()

The mean.

Returns:

np.float64 or np.ndarray

median()

The median.

Returns:

np.float64 or np.ndarray

moment(n)

n-th order moment.

Parameters:

nint

Order of the moment (at least 1)

Returns:

np.float64 or np.ndarray

mrl(time)

The mean residual life function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

property nb_coef

The number of coefficients

Returns:

int

property nb_params

Number of parameters.

Returns:

int

Number of parameters.

property params

Parameters values.

Returns:

ndarray

Parameters values of the core

Notes

If parameter values are not set, they are encoded as np.nan value.

Parameters can be by manually setting`params` through its setter, fitting the core if fit exists or by specifying all parameters values when the core object is initialized.

property params_names

Parameters names.

Returns:

list of str

Parameters names

Notes

Parameters values can be requested (a.k.a. get) by their name at instance level.

pdf(time)

The probability density function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

ppf(probability)

The percent point function.

Parameters:

probabilityfloat or np.ndarray

Probability value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given probability value(s).

rvs(size, return_event=False, return_entry=False, seed=None)

Random variable sampling.

Parameters:

sizeint, (int,) or (int, int)

Size of the generated sample. If size is n or (n,), n samples are generated. If size is (m,n), a 2d array of samples is generated.

return_eventbool, default is False

If True, returns event indicators along with the sample time values.

return_entrybool, default is False

If True, returns corresponding entry values of the sample time values.

seedoptional int, default is None

Random seed used to fix random sampling.

Returns:

float, ndarray or tuple of float or ndarray

The sample values. If either return_event or return_entry is True, returns a tuple containing the time values followed by event values, entry values or both.

sf(time)

The survival function.

Parameters:

timefloat or np.ndarray

Elapsed time value(s) at which to compute the function. If ndarray, allowed shapes are (), (n,) or (m, n).

Returns:

np.float64 or np.ndarray

Function values at each given time(s).

var()

The variance.

Returns:

np.float64 or np.ndarray