def loads(data,
fix_imports=True,
encoding="ASCII",
errors="strict",
buffers=None):
"""Robust pickle loading
We first try to unpickle the object with pd.read_pickle. This makes no
difference for non-pandas objects but makes the de-serialization
of pandas objects more robust across pandas versions. If that fails, we use
cloudpickle. If that fails, we return None but do not raise an error.
See: https://github.com/pandas-dev/pandas/issues/16474
"""
try:
res = pd.read_pickle(io.BytesIO(data), compression=None)
except (KeyboardInterrupt, SystemExit):
raise
except Exception:
try:
res = cloudpickle.loads(data)
except (KeyboardInterrupt, SystemExit):
raise
except Exception:
res = None
tb = get_traceback()
warnings.warn(
f"Unable to read PickleType column from database:\n{tb}\n "
"The entry was replaced by None.")
return res
def wrapper_catch(*args, **kwargs):
try:
res = func(*args, **kwargs)
except exclude:
raise
except exception as e:
if onerror is not None:
onerror(e)
if reraise:
raise e
tb = get_traceback()
if warn:
msg = f"The following exception was caught:\n\n{tb}"
warnings.warn(msg)
if default == "__traceback__":
res = tb
elif callable(default):
res = default(*args, **kwargs)
else:
res = default
return res
def internal_criterion_and_derivative_template(
x,
*,
task,
direction,
criterion,
params,
reparametrize_from_internal,
convert_derivative,
algorithm_info,
derivative,
criterion_and_derivative,
numdiff_options,
logging,
db_kwargs,
error_handling,
error_penalty,
first_criterion_evaluation,
cache,
cache_size,
fixed_log_data,
):
"""Template for the internal criterion and derivative function.
The internal criterion and derivative function only has the arguments x and task
and algorithm_info. The other arguments will be partialed in by estimagic at some
point. Algorithm_info and possibly even task will be partialed in by the algorithm.
That is the reason why this function is called a template.
Args:
x (np.ndarray): 1d numpy array with internal parameters.
task (str): One of "criterion", "derivative" and "criterion_and_derivative".
direction (str): One of "maximize" or "minimize"
criterion (callable): (partialed) user provided criterion function that takes a
parameter dataframe as only argument and returns a scalar, an array like
object or a dictionary. See :ref:`criterion`.
params (pd.DataFrame): see :ref:`params`
reparametrize_from_internal (callable): Function that takes x and returns a
numpy array with the values of the external parameters.
convert_derivative (callable): Function that takes the derivative of criterion
at the external version of x and x and returns the derivative
of the internal criterion.
algorithm_info (dict): Dict with the following entries:
"primary_criterion_entry": One of "value", "contributions" and
"root_contributions" or "dict".
"parallelizes": Bool that indicates if the algorithm calls the internal
criterion function in parallel. If so, caching is disabled.
"needs_scaling": bool
"name": string
derivative (callable, optional): (partialed) user provided function that
calculates the first derivative of criterion. For most algorithm, this is
the gradient of the scalar output (or "value" entry of the dict). However
some algorithms (e.g. bhhh) require the jacobian of the "contributions"
entry of the dict. You will get an error if you provide the wrong type of
derivative.
criterion_and_derivative (callable): Function that returns criterion
and derivative as a tuple. This can be used to exploit synergies in the
evaluation of both functions. The fist element of the tuple has to be
exactly the same as the output of criterion. The second has to be exactly
the same as the output of derivative.
numdiff_options (dict): Keyword arguments for the calculation of numerical
derivatives. See :ref:`first_derivative` for details. Note that the default
method is changed to "forward" for speed reasons.
logging (bool): Wether logging is used.
db_kwargs (dict): Dictionary with entries "database", "path" and "fast_logging".
error_handling (str): Either "raise" or "continue". Note that "continue" does
not absolutely guarantee that no error is raised but we try to handle as
many errors as possible in that case without aborting the optimization.
error_penalty (dict): Dict with the entries "constant" (float) and "slope"
(float). If the criterion or derivative raise an error and error_handling is
"continue", return ``constant + slope * norm(params - start_params)`` where
``norm`` is the euclidean distance as criterion value and adjust the
derivative accordingly. This is meant to guide the optimizer back into a
valid region of parameter space (in direction of the start parameters).
Note that the constant has to be high enough to ensure that the penalty is
actually a bad function value. The default constant is 2 times the criterion
value at the start parameters. The default slope is 0.1.
first_criterion_evaluation (dict): Dictionary with entries "internal_params",
"external_params", "output".
cache (dict): Dictionary used as cache for criterion and derivative evaluations.
cache_size (int): Number of evaluations that are kept in cache. Default 10.
fixed_log_data (dict): Dictionary with fixed data to be saved in the database.
Has the entries "stage" (str) and "substage" (int).
Returns:
float, np.ndarray or tuple: If task=="criterion" it returns the output of
criterion which can be a float or 1d numpy array. If task=="derivative" it
returns the first derivative of criterion, which is a numpy array.
If task=="criterion_and_derivative" it returns both as a tuple.
"""
if algorithm_info["primary_criterion_entry"] == "root_contributions":
if direction == "maximize":
msg = (
"Optimizers that exploit a least squares structure like {} can only be "
"used for minimization.")
raise ValueError(msg.format(algorithm_info["name"]))
x_hash = hash_array(x)
cache_entry = cache.get(x_hash, {})
to_dos = _determine_to_dos(task, cache_entry, derivative,
criterion_and_derivative)
caught_exceptions = []
new_criterion, new_derivative, new_external_derivative = None, None, None
current_params = params.copy()
external_x = reparametrize_from_internal(x)
current_params["value"] = external_x
if to_dos == []:
pass
elif "numerical_criterion_and_derivative" in to_dos:
def func(x):
external_x = reparametrize_from_internal(x)
p = params.copy()
p["value"] = external_x
return criterion(p)
options = numdiff_options.copy()
options["key"] = algorithm_info["primary_criterion_entry"]
options["f0"] = cache_entry.get("criterion", None)
options["return_func_value"] = True
try:
derivative_dict = first_derivative(func, x, **options)
new_derivative = {
algorithm_info["primary_criterion_entry"]:
derivative_dict["derivative"]
}
new_criterion = derivative_dict["func_value"]
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
caught_exceptions.append(get_traceback())
if "criterion" in cache_entry:
raise Exception(DERIVATIVE_ERROR_MESSAGE) from e
elif "criterion_and_derivative" in to_dos:
try:
new_criterion, new_external_derivative = criterion_and_derivative(
current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
caught_exceptions.append(get_traceback())
if "criterion" in cache_entry:
raise Exception(DERIVATIVE_ERROR_MESSAGE) from e
else:
if "criterion" in to_dos:
try:
new_criterion = criterion(current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
caught_exceptions.append(get_traceback())
if "derivative" in cache_entry:
raise Exception(CRITERION_ERROR_MESSAGE) from e
if "derivative" in to_dos:
try:
new_external_derivative = derivative(current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
caught_exceptions.append(get_traceback())
if "criterion" in cache_entry:
raise Exception(DERIVATIVE_ERROR_MESSAGE) from e
if new_derivative is None and new_external_derivative is not None:
if not isinstance(new_external_derivative, dict):
new_external_derivative = {
algorithm_info["primary_criterion_entry"]:
new_external_derivative
}
new_derivative = {
k: convert_derivative(v, internal_values=x)
for k, v in new_external_derivative.items()
}
if caught_exceptions:
if error_handling == "continue":
new_criterion, new_derivative = _penalty_and_derivative(
x, first_criterion_evaluation, error_penalty, algorithm_info)
warnings.warn("\n\n".join(caught_exceptions))
else:
raise Exception("\n\n".join(caught_exceptions))
if not algorithm_info["parallelizes"] and cache_size >= 1:
_cache_new_evaluations(new_criterion, new_derivative, x_hash, cache,
cache_size)
new_criterion = _check_and_harmonize_criterion_output(
cache_entry.get("criterion", new_criterion), algorithm_info)
new_derivative = _check_and_harmonize_derivative(
cache_entry.get("derivative", new_derivative), algorithm_info)
if (new_criterion is not None or new_derivative is not None) and logging:
_log_new_evaluations(
new_criterion=new_criterion,
new_derivative=new_derivative,
external_x=external_x,
caught_exceptions=caught_exceptions,
db_kwargs=db_kwargs,
fixed_log_data=fixed_log_data,
)
res = _get_output_for_optimizer(new_criterion, new_derivative, task,
algorithm_info, direction)
return res
def internal_criterion_and_derivative_template(
x,
*,
task,
direction,
criterion,
converter,
algo_info,
derivative,
criterion_and_derivative,
numdiff_options,
logging,
db_kwargs,
error_handling,
error_penalty_func,
fixed_log_data,
history_container=None,
return_history_entry=False,
):
"""Template for the internal criterion and derivative function.
This function forms the basis of all functions that define the optimization problem
and are passed to the internal optimizers in estimagic. I.e. the criterion,
derivative and criterion_and_derivative functions.
Most of the arguments of this function will be partialled in before the functions
are passed to internal optimizers.
That is the reason why this function is called a template.
Args:
x (np.ndarray): 1d numpy array with internal parameters.
task (str): One of "criterion", "derivative" and "criterion_and_derivative".
direction (str): One of "maximize" or "minimize"
criterion (callable): (partialed) user provided criterion function that takes a
parameter dataframe as only argument and returns a scalar, an array like
object or a dictionary. See :ref:`criterion`.
params (pd.DataFrame): see :ref:`params`
converter (Converter): NamedTuple with methods to convert between internal
and external derivatives, parameters and criterion outputs.
algo_info (AlgoInfo): NamedTuple with attributes
- primary_criterion_entry
- name
- parallelizes
- needs_scaling
- is_available
derivative (callable, optional): (partialed) user provided function that
calculates the first derivative of criterion. For most algorithm, this is
the gradient of the scalar output (or "value" entry of the dict). However
some algorithms (e.g. bhhh) require the jacobian of the "contributions"
entry of the dict. You will get an error if you provide the wrong type of
derivative.
criterion_and_derivative (callable): Function that returns criterion
and derivative as a tuple. This can be used to exploit synergies in the
evaluation of both functions. The fist element of the tuple has to be
exactly the same as the output of criterion. The second has to be exactly
the same as the output of derivative.
numdiff_options (dict): Keyword arguments for the calculation of numerical
derivatives. See :ref:`first_derivative` for details. Note that the default
method is changed to "forward" for speed reasons.
logging (bool): Whether logging is used.
db_kwargs (dict): Dictionary with entries "database", "path" and "fast_logging".
error_handling (str): Either "raise" or "continue". Note that "continue" does
not absolutely guarantee that no error is raised but we try to handle as
many errors as possible in that case without aborting the optimization.
error_penalty_func (callable): Function that takes ``x`` and ``task`` and
returns a penalized criterion function, its derivative or both (depending)
on task.
fixed_log_data (dict): Dictionary with fixed data to be saved in the database.
Has the entries "stage" (str) and "substage" (int).
history_container (list or None): List to which parameter, criterion and
derivative histories are appended. Should be set to None if an algorithm
parallelizes over criterion or derivative evaluations.
return_history_entry (bool): Whether the history container should be returned.
Returns:
float, np.ndarray or tuple: If task=="criterion" it returns the output of
criterion which can be a float or 1d numpy array. If task=="derivative" it
returns the first derivative of criterion, which is a numpy array.
If task=="criterion_and_derivative" it returns both as a tuple.
"""
now = time.perf_counter()
to_dos = _determine_to_dos(task, derivative, criterion_and_derivative)
caught_exceptions = []
new_criterion, new_external_criterion = None, None
new_derivative, new_external_derivative = None, None
current_params, external_x = converter.params_from_internal(
x,
return_type="tree_and_flat",
)
if to_dos == []:
pass
elif "numerical_criterion_and_derivative" in to_dos:
def func(x):
p = converter.params_from_internal(x, "tree")
crit_full = criterion(p)
crit_relevant = converter.func_to_internal(crit_full)
out = {"full": crit_full, "relevant": crit_relevant}
return out
options = numdiff_options.copy()
options["key"] = "relevant"
options["return_func_value"] = True
try:
derivative_dict = first_derivative(func, x, **options)
new_derivative = derivative_dict["derivative"]
new_criterion = derivative_dict["func_value"]["relevant"]
new_external_criterion = derivative_dict["func_value"]["full"]
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
tb = get_traceback()
caught_exceptions.append(tb)
if error_handling == "raise":
msg = (
"An error occurred when evaluating criterion to calculate a "
"numerical derivative during optimization.")
raise UserFunctionRuntimeError(msg) from e
else:
msg = (
"The following exception was caught when evaluating criterion to "
f"calculate a numerical derivative during optimization:\n\n{tb}"
)
warnings.warn(msg)
elif "criterion_and_derivative" in to_dos:
try:
new_external_criterion, new_external_derivative = criterion_and_derivative(
current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
tb = get_traceback()
caught_exceptions.append(tb)
if error_handling == "raise":
msg = (
"An error ocurred when evaluating criterion_and_derivative "
"during optimization.")
raise UserFunctionRuntimeError(msg) from e
else:
msg = (
"The following exception was caught when evaluating "
f"criterion_and_derivative during optimization:\n\n{tb}")
warnings.warn(msg)
else:
if "criterion" in to_dos:
try:
new_external_criterion = criterion(current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
tb = get_traceback()
caught_exceptions.append(tb)
if error_handling == "raise":
msg = ("An error ocurred when evaluating criterion during "
"optimization.")
raise UserFunctionRuntimeError(msg) from e
else:
msg = (
"The following exception was caught when evaluating "
f"criterion during optimization:\n\n{tb}")
warnings.warn(msg)
if "derivative" in to_dos:
try:
new_external_derivative = derivative(current_params)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
tb = get_traceback()
caught_exceptions.append(tb)
if error_handling == "raise":
msg = (
"An error ocurred when evaluating derivative during "
"optimization")
raise UserFunctionRuntimeError(msg) from e
else:
msg = (
"The following exception was caught when evaluating "
f"derivative during optimization:\n\n{tb}")
warnings.warn(msg)
if new_external_criterion is not None and new_criterion is None:
new_criterion = converter.func_to_internal(new_external_criterion)
if new_external_derivative is not None and new_derivative is None:
new_derivative = converter.derivative_to_internal(
new_external_derivative, x)
if caught_exceptions:
new_criterion, new_derivative = error_penalty_func(
x, task="criterion_and_derivative")
if new_criterion is not None:
scalar_critval = aggregate_func_output_to_value(
f_eval=new_criterion,
primary_key=algo_info.primary_criterion_entry,
)
else:
scalar_critval = None
if (new_criterion is not None or new_derivative is not None) and logging:
_log_new_evaluations(
new_criterion=new_external_criterion,
new_derivative=new_derivative,
external_x=external_x,
caught_exceptions=caught_exceptions,
db_kwargs=db_kwargs,
fixed_log_data=fixed_log_data,
scalar_value=scalar_critval,
now=now,
)
res = _get_output_for_optimizer(
new_criterion=new_criterion,
new_derivative=new_derivative,
task=task,
direction=direction,
)
if new_criterion is not None:
hist_entry = {
"params": current_params,
"criterion": scalar_critval,
"runtime": now,
}
else:
hist_entry = None
if history_container is not None and new_criterion is not None:
history_container.append(hist_entry)
if return_history_entry:
res = (res, hist_entry)
return res
