def get_crit_func(
params, options, df, return_scalar=True, return_comparison_plot_data=False
):
"""Get the criterion function.
Return a version of the likelihood functions in respy where all arguments
except the parameter vector are fixed with :func:`functools.partial`. Thus the
function can be directly passed into an optimizer or a function for taking
numerical derivatives.
Parameters
----------
params : pandas.DataFrame
DataFrame containing model parameters.
options : dict
Dictionary containing model options.
df : pandas.DataFrame
The model is fit to this dataset.
return_scalar : bool, default False
Indicator for whether the mean log likelihood should be returned or the log
likelihood contributions.
return_comparison_plot_data : bool, default False
Indicator for whether a :class:`pandas.DataFrame` with various contributions for
the visualization with estimagic should be returned.
Returns
-------
criterion_function : :func:`log_like`
Criterion function where all arguments except the parameter vector are set.
Raises
------
AssertionError
If data has not the expected format.
"""
optim_paras, options = process_params_and_options(params, options)
optim_paras = _adjust_optim_paras_for_estimation(optim_paras, df)
check_estimation_data(df, optim_paras)
solve = get_solve_func(params, options)
state_space = solve.keywords["state_space"]
df, type_covariates = _process_estimation_data(
df, state_space, optim_paras, options
)
base_draws_est = create_base_draws(
(
df.shape[0] * optim_paras["n_types"],
options["estimation_draws"],
len(optim_paras["choices"]),
),
next(options["estimation_seed_startup"]),
options["monte_carlo_sequence"],
)
criterion_function = partial(
log_like,
df=df,
base_draws_est=base_draws_est,
solve=solve,
type_covariates=type_covariates,
options=options,
return_scalar=return_scalar,
return_comparison_plot_data=return_comparison_plot_data,
)
return criterion_function
def get_log_like_func(params, options, df, return_scalar=True):
"""Get the criterion function for maximum likelihood estimation.
Return a version of the likelihood functions in respy where all arguments
except the parameter vector are fixed with :func:`functools.partial`. Thus the
function can be directly passed into an optimizer or a function for taking
numerical derivatives.
Parameters
----------
params : pandas.DataFrame
DataFrame containing model parameters.
options : dict
Dictionary containing model options.
df : pandas.DataFrame
The model is fit to this dataset.
return_scalar : bool, default False
Indicator for whether the mean log likelihood should be returned. If False will
return a dictionary with the following key and value pairs:
- "value": mean log likelihood (float)
- "contributions": log likelihood contributions (numpy.array)
- "comparison_plot_data" : DataFrame with various contributions for
the visualization with estimagic. Data contains the following columns:
- ``identifier`` : Individual identifiers derived from input df.
- ``period`` : Periods derived from input df.
- ``choice`` : Choice that ``value`` is connected to.
- ``value`` : Value of log likelihood contribution.
- ``kind`` : Kind of contribution (e.g choice or wage).
- ``type`` and `log_type_probability``: Will be included in models with
types.
Returns
-------
criterion_function : :func:`log_like`
Criterion function where all arguments except the parameter vector are set.
Raises
------
AssertionError
If data has not the expected format.
Examples
--------
>>> import respy as rp
>>> params, options, data = rp.get_example_model("robinson_crusoe_basic")
At default the function returns the log likelihood as a scalar value.
>>> log_like = rp.get_log_like_func(params=params, options=options, df=data)
>>> scalar = log_like(params)
Alternatively, a dictionary containing the log likelihood, as well as
log likelihood contributions and a :class:`pandas.DataFrame` can be returned.
>>> log_like = rp.get_log_like_func(params=params, options=options, df=data,
... return_scalar=False
... )
>>> outputs = log_like(params)
>>> outputs.keys()
dict_keys(['value', 'contributions', 'comparison_plot_data'])
"""
optim_paras, options = process_params_and_options(params, options)
optim_paras = _update_optim_paras_with_initial_experience_levels(
optim_paras, df)
check_estimation_data(df, optim_paras)
solve = get_solve_func(params, options)
state_space = solve.keywords["state_space"]
df, type_covariates = _process_estimation_data(df, state_space,
optim_paras, options)
# Replace with decorator.
base_draws_est = {}
for dense_key, indices in df.groupby("dense_key").groups.items():
n_choices = sum(state_space.dense_key_to_choice_set[dense_key])
draws = create_base_draws(
(len(indices), options["estimation_draws"], n_choices),
next(options["estimation_seed_startup"]),
options["monte_carlo_sequence"],
)
base_draws_est[dense_key] = draws
criterion_function = partial(
log_like,
df=df,
base_draws_est=base_draws_est,
solve=solve,
type_covariates=type_covariates,
options=options,
return_scalar=return_scalar,
)
return criterion_function
def get_log_like_func(params,
options,
df,
return_scalar=True,
return_comparison_plot_data=False):
"""Get the criterion function for maximum likelihood estimation.
Return a version of the likelihood functions in respy where all arguments
except the parameter vector are fixed with :func:`functools.partial`. Thus the
function can be directly passed into an optimizer or a function for taking
numerical derivatives.
Parameters
----------
params : pandas.DataFrame
DataFrame containing model parameters.
options : dict
Dictionary containing model options.
df : pandas.DataFrame
The model is fit to this dataset.
return_scalar : bool, default False
Indicator for whether the mean log likelihood should be returned or the log
likelihood contributions.
return_comparison_plot_data : bool, default False
Indicator for whether a :class:`pandas.DataFrame` with various contributions for
the visualization with estimagic should be returned.
Returns
-------
criterion_function : :func:`log_like`
Criterion function where all arguments except the parameter vector are set.
Raises
------
AssertionError
If data has not the expected format.
Examples
--------
>>> import respy as rp
>>> params, options, data = rp.get_example_model("robinson_crusoe_basic")
At default the function returns the log likelihood as a scalar value.
>>> log_like = rp.get_log_like_func(params=params, options=options, df=data)
>>> scalar = log_like(params)
Additionally, a :class:`pandas.DataFrame` with data for visualization can be
returned.
>>> log_like = rp.get_log_like_func(params=params, options=options, df=data,
... return_comparison_plot_data=True
... )
>>> scalar, df = log_like(params)
In alternative to the log likelihood, a :class:`numpy.array` of the individual
log likelihood contributions can be returned.
>>> log_like_contribs = rp.get_log_like_func(params=params, options=options,
... df=data, return_scalar=False
... )
>>> array = log_like_contribs(params)
"""
optim_paras, options = process_params_and_options(params, options)
optim_paras = _update_optim_paras_with_initial_experience_levels(
optim_paras, df)
check_estimation_data(df, optim_paras)
solve = get_solve_func(params, options)
state_space = solve.keywords["state_space"]
df, type_covariates = _process_estimation_data(df, state_space,
optim_paras, options)
# Replace with decorator.
base_draws_est = {}
for dense_key, indices in df.groupby("dense_key").groups.items():
n_choices = sum(state_space.dense_key_to_choice_set[dense_key])
draws = create_base_draws(
(len(indices), options["estimation_draws"], n_choices),
next(options["estimation_seed_startup"]),
options["monte_carlo_sequence"],
)
base_draws_est[dense_key] = draws
criterion_function = partial(
log_like,
df=df,
base_draws_est=base_draws_est,
solve=solve,
type_covariates=type_covariates,
options=options,
return_scalar=return_scalar,
return_comparison_plot_data=return_comparison_plot_data,
)
return criterion_function
def get_crit_func(params, options, df, version="log_like"):
"""Get the criterion function.
Return a version of the likelihood functions in respy where all arguments
except the parameter vector are fixed with :func:`functools.partial`. Thus the
function can be directly passed into an optimizer or a function for taking
numerical derivatives.
By default we return :func:`log_like`. Other versions can be requested via the
version argument.
Parameters
----------
params : pandas.DataFrame
DataFrame containing model parameters.
options : dict
Dictionary containing model options.
df : pandas.DataFrame
The model is fit to this dataset.
version : str, default "log_like"
Can take the values "log_like" and "log_like_obs".
Returns
-------
criterion_function : :func:`log_like`
Criterion function where all arguments except the parameter vector are set.
Raises
------
AssertionError
If data has not the expected format.
"""
optim_paras, options = process_params_and_options(params, options)
optim_paras = _adjust_optim_paras_for_estimation(optim_paras, df)
check_estimation_data(df, optim_paras)
state_space = StateSpace(optim_paras, options)
(
choices,
idx_indiv_first_obs,
indices,
log_wages_observed,
type_covariates,
) = _process_estimation_data(df, state_space, optim_paras, options)
base_draws_est = create_base_draws(
(len(choices), options["estimation_draws"], len(
optim_paras["choices"])),
next(options["estimation_seed_startup"]),
options["monte_carlo_sequence"],
)
if version == "log_like":
unpartialed = log_like
elif version == "log_like_obs":
unpartialed = log_like_obs
else:
raise ValueError("version has to be 'log_like' or 'log_like_obs'.")
criterion_function = partial(
unpartialed,
choices=choices,
idx_indiv_first_obs=idx_indiv_first_obs,
indices=indices,
log_wages_observed=log_wages_observed,
base_draws_est=base_draws_est,
state_space=state_space,
type_covariates=type_covariates,
options=options,
)
# this will be relevant for estimagic topography plots
criterion_function.__name__ = version
return criterion_function