matchzoo.engine.hyper_spaces

Hyper parameter search spaces wrapping hyperopt.

Module Contents

Classes

HyperoptProxy

Hyperopt proxy class.

choice

hyperopt.hp.choice() proxy.

quniform

hyperopt.hp.quniform() proxy.

uniform

hyperopt.hp.uniform() proxy.

Functions

_wrap_as_composite_func(self, other, func)

sample(space)

Take a sample in the hyper space.
class matchzoo.engine.hyper_spaces.HyperoptProxy(hyperopt_func: typing.Callable[…, hyperopt.pyll.Apply], **kwargs)

Bases: object

Hyperopt proxy class.

See hyperopt’s documentation for more details: https://github.com/hyperopt/hyperopt/wiki/FMin

Reason of these wrappers:

A hyper space in hyperopt requires a label to instantiate. This label is used later as a reference to original hyper space that is sampled. In matchzoo, hyper spaces are used in matchzoo.engine.Param. Only if a hyper space’s label matches its parent matchzoo.engine.Param’s name, matchzoo can correctly back-refrenced the parameter got sampled. This can be done by asking the user always use the same name for a parameter and its hyper space, but typos can occur. As a result, these wrappers are created to hide hyper spaces’ label, and always correctly bind them with its parameter’s name.

Examples::
>>> import matchzoo as mz
>>> from hyperopt.pyll.stochastic import sample
Basic Usage:
>>> model = mz.models.DenseBaseline()
>>> sample(model.params.hyper_space)  
 {'mlp_num_layers': 1.0, 'mlp_num_units': 274.0}
Arithmetic Operations:
>>> new_space = 2 ** mz.hyper_spaces.quniform(2, 6)
>>> model.params.get('mlp_num_layers').hyper_space = new_space
>>> sample(model.params.hyper_space)  
{'mlp_num_layers': 8.0, 'mlp_num_units': 292.0}
convert(self, name: str) → hyperopt.pyll.Apply

Attach name as hyperopt.hp’s label.

Parameters

name –

Returns

a hyperopt ready search space

__add__(self, other)

__add__.

__radd__(self, other)

__radd__.

__sub__(self, other)

__sub__.

__rsub__(self, other)

__rsub__.

__mul__(self, other)

__mul__.

__rmul__(self, other)

__rmul__.

__truediv__(self, other)

__truediv__.

__rtruediv__(self, other)

__rtruediv__.

__floordiv__(self, other)

__floordiv__.

__rfloordiv__(self, other)

__rfloordiv__.

__pow__(self, other)

__pow__.

__rpow__(self, other)

__rpow__.

__neg__(self)

__neg__.

matchzoo.engine.hyper_spaces._wrap_as_composite_func(self, other, func)
class matchzoo.engine.hyper_spaces.choice(options: list)

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.choice() proxy.

__str__(self)
Returns

str representation of the hyper space.

class matchzoo.engine.hyper_spaces.quniform(low: numbers.Number, high: numbers.Number, q: numbers.Number = 1)

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.quniform() proxy.

__str__(self)
Returns

str representation of the hyper space.

class matchzoo.engine.hyper_spaces.uniform(low: numbers.Number, high: numbers.Number)

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.uniform() proxy.

__str__(self)
Returns

str representation of the hyper space.

matchzoo.engine.hyper_spaces.sample(space)

Take a sample in the hyper space.

This method is stateless, so the distribution of the samples is different from that of tune call. This function just gives a general idea of what a sample from the space looks like.

Example

>>> import matchzoo as mz
>>> space = mz.models.DenseBaseline.get_default_params().hyper_space
>>> mz.hyper_spaces.sample(space)  
{'mlp_num_fan_out': ...}