pyemma.msm.ChapmanKolmogorovValidator

class pyemma.msm.ChapmanKolmogorovValidator(model, estimator, memberships, mlags=None, conf=0.95, err_est=False, n_jobs=1, show_progress=True)
__init__(model, estimator, memberships, mlags=None, conf=0.95, err_est=False, n_jobs=1, show_progress=True)
Parameters:memberships (ndarray(n, m)) – Set memberships to calculate set probabilities. n must be equal to the number of active states in model. m is the number of sets. memberships must be a row-stochastic matrix (the rows must sum up to 1).

Methods

__init__(model, estimator, memberships[, ...])
param memberships:
 Set memberships to calculate set probabilities. n must be equal to
estimate(X, **params) Estimates the model given the data X
fit(X) Estimates parameters - for compatibility with sklearn.
get_params([deep]) Get parameters for this estimator.
register_progress_callback(call_back[, stage]) Registers the progress reporter.
set_params(**params) Set the parameters of this estimator.

Attributes

estimates Returns estimates at different lagtimes
estimates_conf Returns the confidence intervals of the estimates at different lagtimes (if available).
lagtimes
logger The logger for this class instance
model The model estimated by this Estimator
name The name of this instance
predictions Returns tested model predictions at different lagtimes
predictions_conf Returns the confidence intervals of the estimates at different
show_progress whether to show the progress of heavy calculations on this object.
estimate(X, **params)

Estimates the model given the data X

Parameters:
  • X (object) – A reference to the data from which the model will be estimated
  • params (dict) – New estimation parameter values. The parameters must that have been announced in the __init__ method of this estimator. The present settings will overwrite the settings of parameters given in the __init__ method, i.e. the parameter values after this call will be those that have been used for this estimation. Use this option if only one or a few parameters change with respect to the __init__ settings for this run, and if you don’t need to remember the original settings of these changed parameters.
Returns:

estimator – The estimated estimator with the model being available.

Return type:

object

estimates

Returns estimates at different lagtimes

Returns:Y – each row contains the n observables computed at one of the T lag t imes.
Return type:ndarray(T, n)
estimates_conf

Returns the confidence intervals of the estimates at different lagtimes (if available).

If not available, returns None.

Returns:
  • L (ndarray(T, n)) – each row contains the lower confidence bound of n observables computed at one of the T lag times.
  • R (ndarray(T, n)) – each row contains the upper confidence bound of n observables computed at one of the T lag times.
fit(X)

Estimates parameters - for compatibility with sklearn.

Parameters:X (object) – A reference to the data from which the model will be estimated
Returns:estimator – The estimator (self) with estimated model.
Return type:object
get_params(deep=True)

Get parameters for this estimator.

Parameters:deep (boolean, optional) – If True, will return the parameters for this estimator and contained subobjects that are estimators.
Returns:params – Parameter names mapped to their values.
Return type:mapping of string to any
logger

The logger for this class instance

model

The model estimated by this Estimator

name

The name of this instance

predictions

Returns tested model predictions at different lagtimes

Returns:Y – each row contains the n observables predicted at one of the T lag times by the tested model.
Return type:ndarray(T, n)
predictions_conf

Returns the confidence intervals of the estimates at different lagtimes (if available)

If not available, returns None.

Returns:
  • L (ndarray(T, n)) – each row contains the lower confidence bound of n observables computed at one of the T lag times.
  • R (ndarray(T, n)) – each row contains the upper confidence bound of n observables computed at one of the T lag times.
register_progress_callback(call_back, stage=0)

Registers the progress reporter.

Parameters:
  • call_back (function) –

    This function will be called with the following arguments:

    1. stage (int)
    2. instance of pyemma.utils.progressbar.ProgressBar
    3. optional *args and named keywords (**kw), for future changes
  • stage (int, optional, default=0) – The stage you want the given call back function to be fired.
set_params(**params)

Set the parameters of this estimator. The method works on simple estimators as well as on nested objects (such as pipelines). The former have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object. :returns: :rtype: self

show_progress

whether to show the progress of heavy calculations on this object.