Model

Model(*args, **kwargs)

Attributes

Data Connection

Model.datatree	A source for data for the model.
Model.dataset	Data arrays as loaded for model computation.
Model.n_cases	The number of cases in the attached data.

Choice Definition

Model.choice_ca_var	An idca variable giving the choices as indicator values.
Model.choice_co_vars	A mapping giving idco expressions that evaluate to indicator values.
Model.choice_co_code	An idco variable giving the choices as alternative id's.

Alternative Availability

Model.availability_ca_var	An idca variable or expression indicating if alternatives are available.
Model.availability_co_vars	A mapping giving idco expressions that evaluate to availability indicators.

Utility Definition

Model.utility_ca	The portion of the utility function computed from idca data.
Model.utility_co	The portion of the utility function computed from idco data.
Model.quantity_ca	The portion of the quantity function computed from idca data.

Parameters

Model.pf	A DataFrame of the model parameters.
Model.pvals	An array of the current parameter values.
Model.pnames	An array of the current parameter names.
Model.pholdfast	An array indicating which parameters are marked as holdfast.
Model.pnullvals	An array of the current parameter null values.
Model.pmaximum	An array of the current parameter maximum values.
Model.pminimum	An array of the current parameter minimum values.
Model.pbounds	A copy of the current min-max bounds of the parameters.
Model.pstderr	An array of the current parameter standard errors.
Model.mixtures

Estimation Results

Model.most_recent_estimation_result	A copy of the result dict from most recent likelihood maximization.
Model.possible_overspecification	Possible overspecification of the model.

Methods

Setting Parameters

Model.set_values([values])	Set the parameter values for one or more parameters.
Model.lock_value([name, value])	Set a fixed value for a model parameter.
Model.set_cap([cap])	Set limiting values for one or more parameters.
Model.remove_unused_parameters([verbose])	Remove parameters that are not used in the model.

Parameter Estimation

Model.maximize_loglike(*args, **kwargs)	Maximize the log likelihood.
Model.calculate_parameter_covariance([...])	Calculate the parameter covariance matrix.

Model Fitness

Model.loglike_null([use_cache])

Compute the log likelihood at null values.

Model Analysis

Model.analyze_predictions_co([q, n, ...])	Analyze predictions of the model based on idco attributes.
Model.analyze_predictions_co_figure([q, n, ...])	Create an Altair figure of the model's predictions based on idco attributes.
Model.analyze_elasticity(variable[, altid, ...])	Analyze elasticity of the model.
Model.histogram_on_idca_variable(x, **kwargs)

Reporting

Model.parameter_summary()	Create a tabular summary of parameter values.
Model.estimation_statistics([...])	Create an XHTML summary of estimation statistics.
Model.mixture_summary()	Create a summary of the mixture parameters as a pandas DataFrame.
Model.to_xlsx(filename[, save_now, ...])	Write the estimation results to an Excel file.

Ancillary Computation

Model.bhhh([x, start_case, stop_case, ...])
Model.check_d_loglike([stylize, skip_zeros])	Check that the analytic and finite-difference gradients are approximately equal.
Model.d_loglike([x, start_case, stop_case, ...])
Model.d_loglike_casewise([x, start_case, ...])
Model.loglike([x, start_case, stop_case, ...])	Compute the log likelihood of the model.
Model.loglike_casewise([x, start_case, ...])
Model.logloss([x, start_case, stop_case, ...])
Model.logsums([x, start_case, stop_case, ...])
Model.probability([x, start_case, ...])	Compute values for the probability function embodied by the model.
Model.quantity([x, start_case, stop_case, ...])
Model.total_weight()	Compute the total weight of cases in the loaded data.
Model.utility([x, start_case, stop_case, ...])	Compute values for the utility function contained in the model.

Troubleshooting

Model.doctor(**kwargs)

Run diagnostics, checking for common problems and inconsistencies.