def evaluate_topic_models(data,
varying_parameters,
constant_parameters=None,
n_max_processes=None,
return_models=False,
metric=None,
**metric_kwargs):
"""
Compute several Topic Models in parallel using the "gensim" package. Calculate the models using a list of varying
parameters `varying_parameters` on a single Document-Term-Matrix `data`. Pass parameters in `constant_parameters`
dict to each model calculation. Use at maximum `n_max_processes` processors or use all available processors if None
is passed.
`data` must be a Document-Term-Matrix (NumPy array/matrix, SciPy sparse matrix).
Will return a list of size `len(varying_parameters)` containing tuples `(parameter_set, eval_results)` where
`parameter_set` is a dict of the used parameters and `eval_results` is a dict of metric names -> metric results.
"""
mp_eval = MultiprocEvaluationRunner(MultiprocEvaluationWorkerGensim,
AVAILABLE_METRICS,
data,
varying_parameters,
constant_parameters,
metric=metric or DEFAULT_METRICS,
metric_options=metric_kwargs,
n_max_processes=n_max_processes,
return_models=return_models)
return mp_eval.run()
def evaluate_topic_models(data,
varying_parameters,
constant_parameters=None,
n_max_processes=None,
return_models=False,
metric=None,
**metric_kwargs):
"""
Compute several Topic Models in parallel using the "gensim" package. Calculate the models using a list of varying
parameters `varying_parameters` on a single Document-Term-Matrix `data`. Pass parameters in `constant_parameters`
dict to each model calculation. Use at maximum `n_max_processes` processors or use all available processors if None
is passed.
`data` must be a Document-Term-Matrix (NumPy array/matrix, SciPy sparse matrix).
Will return a list of size `len(varying_parameters)` containing tuples `(parameter_set, eval_results)` where
`parameter_set` is a dict of the used parameters and `eval_results` is a dict of metric names -> metric results:
.. code-block:: text
[(parameter_set_1, {'<metric_name>': result_1, ...}),
...,
(parameter_set_n, {'<metric_name>': result_n, ...})])
.. seealso:: Results can be simplified using :func:`tmtoolkit.topicmod.evaluate.results_by_parameter`.
:param data: a (sparse) 2D array/matrix
:param varying_parameters: list of dicts with parameters; each parameter set will be used in a separate
evaluation
:param constant_parameters: dict with parameters that are the same for all parallel computations
:param n_max_processes: maximum number of worker processes to spawn
:param return_models: if True, also return the computed models in the evaluation results
:param metric: string or list of strings; if given, use only this metric(s) for evaluation; must be subset of
`available_metrics`
:param metric_kwargs: dict of options for metric used metric(s)
:return: list of evaluation results for each varying parameter set as described above
"""
mp_eval = MultiprocEvaluationRunner(MultiprocEvaluationWorkerGensim,
AVAILABLE_METRICS,
data,
varying_parameters,
constant_parameters,
metric=metric or DEFAULT_METRICS,
metric_options=metric_kwargs,
n_max_processes=n_max_processes,
return_models=return_models)
return mp_eval.run()