chainladder.Development#
- class chainladder.Development(n_periods=-1, average='volume', sigma_interpolation='log-linear', drop=None, drop_high=None, drop_low=None, preserve=1, drop_valuation=None, drop_above=inf, drop_below=0.0, fillna=None, groupby=None)#
A Transformer that allows for basic loss development pattern selection.
- Parameters:
- n_periods: integer, optional (default = -1)
number of origin periods to be used in the ldf average calculation. For all origin periods, set n_periods = -1
- average: string or float, optional (default = ‘volume’)
type of averaging to use for ldf average calculation. Options include ‘volume’, ‘simple’, and ‘regression’. If numeric values are supplied, then (2-average) in the style of Zehnwirth & Barnett is used for the exponent of the regression weights.
- sigma_interpolation: string optional (default = ‘log-linear’)
Options include ‘log-linear’ and ‘mack’
- drop: tuple or list of tuples
Drops specific origin/development combination(s)
- drop_high: bool, int, list of bools, or list of ints (default = None)
Drops highest (by rank) link ratio(s) from LDF calculation If a boolean variable is passed, drop_high is set to 1, dropping only the highest value Note that drop_high is performed after consideration of n_periods (if used)
- drop_low: bool, int, list of bools, or list of ints (default = None)
Drops lowest (by rank) link ratio(s) from LDF calculation If a boolean variable is passed, drop_low is set to 1, dropping only the lowest value Note that drop_low is performed after consideration of n_periods (if used)
- drop_above: float or list of floats (default = numpy.inf)
Drops all link ratio(s) above the given parameter from the LDF calculation
- drop_below: float or list of floats (default = 0.00)
Drops all link ratio(s) below the given parameter from the LDF calculation
- preserve: int (default = 1)
The minimum number of link ratio(s) required for LDF calculation
- drop_valuation: str or list of str (default = None)
Drops specific valuation periods. str must be date convertible.
- fillna: float, (default = None)
Used to fill in zero or nan values of an triangle with some non-zero amount. When an link-ratio has zero as its denominator, it is automatically excluded from the
ldf_
calculation. For the specific case of ‘volume’ averaging in a deterministic method, this may be reasonable. For all other averages and stochastic methods, this assumption should be avoided.- groupby:
An option to group levels of the triangle index together for the purposes of estimating patterns. If omitted, each level of the triangle index will receive its own patterns.
- Attributes:
- ldf_: Triangle
The estimated loss development patterns
- cdf_: Triangle
The estimated cumulative development patterns
- sigma_: Triangle
Sigma of the ldf regression
- std_err_: Triangle
Std_err of the ldf regression
- std_residuals_: Triangle
A Triangle representing the weighted standardized residuals of the estimator as described in Barnett and Zehnwirth.
Methods
fit
(X[, y, sample_weight])Fit the model with X.
fit_transform
(X[, y])Fit to data, then transform it.
get_metadata_routing
()Get metadata routing of this object.
get_params
([deep])Get parameters for this estimator.
set_backend
(backend[, inplace, deep])Converts triangle array_backend.
set_fit_request
(*[, sample_weight])Request metadata passed to the
fit
method.set_output
(*[, transform])Set output container.
set_params
(**params)Set the parameters of this estimator.
to_json
()Serializes triangle object to json format
to_pickle
(path[, protocol])Serializes triangle object to pickle.
transform
(X)If X and self are of different shapes, align self to X, else return self.
pipe