Welcome to MatchZoo’s documentation!¶

MatchZoo is a toolkit for text matching. It was developed with a focus on facilitating the designing, comparing and sharing of deep text matching models. There are a number of deep matching methods, such as DRMM, MatchPyramid, MV-LSTM, aNMM, DUET, ARC-I, ARC-II, DSSM, and CDSSM, designed with a unified interface. Potential tasks related to MatchZoo include document retrieval, question answering, conversational response ranking, paraphrase identification, etc. We are always happy to receive any code contributions, suggestions, comments from all our MatchZoo users.

matchzoo¶

matchzoo package¶

Subpackages¶

matchzoo.auto package¶

Subpackages¶

matchzoo.auto.preparer package¶

Submodules¶

matchzoo.auto.preparer.prepare module¶

matchzoo.auto.preparer.preparer module¶

Module contents¶

matchzoo.auto.tuner package¶

Subpackages¶

matchzoo.auto.tuner.callbacks package¶

Submodules¶

matchzoo.auto.tuner.callbacks.callback module¶

matchzoo.auto.tuner.callbacks.lambda_callback module¶

matchzoo.auto.tuner.callbacks.load_embedding_matrix module¶

matchzoo.auto.tuner.callbacks.save_model module¶

Module contents¶

Submodules¶

matchzoo.auto.tuner.tune module¶

matchzoo.auto.tuner.tuner module¶

Module contents¶

matchzoo.data_generator package¶

Subpackages¶

matchzoo.data_generator.callbacks package¶

Submodules¶

matchzoo.data_generator.callbacks.callback module¶

matchzoo.data_generator.callbacks.dynamic_pooling module¶

matchzoo.data_generator.callbacks.histogram module¶

matchzoo.data_generator.callbacks.lambda_callback module¶

Module contents¶

Submodules¶

matchzoo.data_generator.data_generator module¶

matchzoo.data_generator.data_generator_builder module¶

Module contents¶

matchzoo.data_pack package¶

Submodules¶

matchzoo.data_pack.data_pack module¶

Matchzoo DataPack, pair-wise tuple (feature) and context as input.

class matchzoo.data_pack.data_pack.DataPack(relation, left, right)¶

Bases: object

Matchzoo DataPack data structure, store dataframe and context.

DataPack is a MatchZoo native data structure that most MatchZoo data handling processes build upon. A DataPack consists of three parts: left, right and relation, each one of is a pandas.DataFrame.

Parameters

relation (DataFrame) – Store the relation between left document and right document use ids.
left (DataFrame) – Store the content or features for id_left.
right (DataFrame) – Store the content or features for id_right.

Example

>>> left = [
...     ['qid1', 'query 1'],
...     ['qid2', 'query 2']
... ]
>>> right = [
...     ['did1', 'document 1'],
...     ['did2', 'document 2']
... ]
>>> relation = [['qid1', 'did1', 1], ['qid2', 'did2', 1]]
>>> relation_df = pd.DataFrame(relation)
>>> left = pd.DataFrame(left)
>>> right = pd.DataFrame(right)
>>> dp = DataPack(
...     relation=relation_df,
...     left=left,
...     right=right,
... )
>>> len(dp)
2

DATA_FILENAME = 'data.dill'¶

class FrameView(data_pack)¶

Bases: object

FrameView.

append_text_length(verbose=1)¶

Append length_left and length_right columns.

Parameters

inplace – True to modify inplace, False to return a modified copy. (default: False)
verbose – Verbosity.

Example

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> 'length_left' in data_pack.frame[0].columns
False
>>> new_data_pack = data_pack.append_text_length(verbose=0)
>>> 'length_left' in new_data_pack.frame[0].columns
True
>>> 'length_left' in data_pack.frame[0].columns
False
>>> data_pack.append_text_length(inplace=True, verbose=0)
>>> 'length_left' in data_pack.frame[0].columns
True

apply_on_text(func, mode='both', rename=None, verbose=1)¶

Apply func to text columns based on mode.

Parameters

func (Callable) – The function to apply.
mode (str) – One of “both”, “left” and “right”.
rename (Optional[str]) – If set, use new names for results instead of replacing the original columns. To set rename in “both” mode, use a tuple of str, e.g. (“text_left_new_name”, “text_right_new_name”).
inplace – True to modify inplace, False to return a modified copy. (default: False)
verbose (int) – Verbosity.

Examples::

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> frame = data_pack.frame

To apply len on the left text and add the result as ‘length_left’:

>>> data_pack.apply_on_text(len, mode='left',
...                         rename='length_left',
...                         inplace=True,
...                         verbose=0)
>>> list(frame[0].columns) # noqa: E501
['id_left', 'text_left', 'length_left', 'id_right', 'text_right', 'label']

To do the same to the right text:

>>> data_pack.apply_on_text(len, mode='right',
...                         rename='length_right',
...                         inplace=True,
...                         verbose=0)
>>> list(frame[0].columns) # noqa: E501
['id_left', 'text_left', 'length_left', 'id_right', 'text_right', 'length_right', 'label']

To do the same to the both texts at the same time:

>>> data_pack.apply_on_text(len, mode='both',
...                         rename=('extra_left', 'extra_right'),
...                         inplace=True,
...                         verbose=0)
>>> list(frame[0].columns) # noqa: E501
['id_left', 'text_left', 'length_left', 'extra_left', 'id_right', 'text_right', 'length_right', 'extra_right', 'label']

To suppress outputs:

>>> data_pack.apply_on_text(len, mode='both', verbose=0,
...                         inplace=True)

copy()¶

Return type: DataPack
Returns: A deep copy.

drop_invalid()¶

Remove rows from the data pack where the length is zero.

Parameters: inplace – True to modify inplace, False to return a modified copy. (default: False)

Example

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> data_pack.append_text_length(inplace=True, verbose=0)
>>> data_pack.drop_invalid(inplace=True)

drop_label()¶

Remove label column from the data pack.

Parameters: inplace – True to modify inplace, False to return a modified copy. (default: False)

Example

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> data_pack.has_label
True
>>> data_pack.drop_label(inplace=True)
>>> data_pack.has_label
False

property frame: matchzoo.data_pack.data_pack.DataPack.FrameView¶

View the data pack as a pandas.DataFrame.

Returned data frame is created by merging the left data frame, the right dataframe and the relation data frame. Use [] to access an item or a slice of items.

Return type: FrameView
Returns: A matchzoo.DataPack.FrameView instance.

Example

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> type(data_pack.frame)
<class 'matchzoo.data_pack.data_pack.DataPack.FrameView'>
>>> frame_slice = data_pack.frame[0:5]
>>> type(frame_slice)
<class 'pandas.core.frame.DataFrame'>
>>> list(frame_slice.columns)
['id_left', 'text_left', 'id_right', 'text_right', 'label']
>>> full_frame = data_pack.frame()
>>> len(full_frame) == len(data_pack)
True

property has_label: bool¶

True if label column exists, False other wise.

Type: return
Return type: bool

property left: pandas.core.frame.DataFrame¶

Get left() of DataPack.

Return type: DataFrame

one_hot_encode_label(num_classes=2)¶

One-hot encode label column of relation.

Parameters

num_classes – Number of classes.
inplace – True to modify inplace, False to return a modified copy. (default: False)

Returns

property relation¶: relation getter.

property right: pandas.core.frame.DataFrame¶

Get right() of DataPack.

Return type: DataFrame

save(dirpath)¶

Save the DataPack object.

A saved DataPack is represented as a directory with a DataPack object (transformed user input as features and context), it will be saved by pickle.

Parameters: dirpath (Union[str, Path]) – directory path of the saved DataPack.

shuffle()¶

Shuffle the data pack by shuffling the relation column.

Parameters: inplace – True to modify inplace, False to return a modified copy. (default: False)

Example

>>> import matchzoo as mz
>>> import numpy.random
>>> numpy.random.seed(0)
>>> data_pack = mz.datasets.toy.load_data()
>>> orig_ids = data_pack.relation['id_left']
>>> shuffled = data_pack.shuffle()
>>> (shuffled.relation['id_left'] != orig_ids).any()
True

unpack()¶

Unpack the data for training.

The return value can be directly feed to model.fit or model.fit_generator.

Return type: Tuple[Dict[str, array], Optional[array]]
Returns: A tuple of (X, y). y is None if self has no label.

Example

>>> import matchzoo as mz
>>> data_pack = mz.datasets.toy.load_data()
>>> X, y = data_pack.unpack()
>>> type(X)
<class 'dict'>
>>> sorted(X.keys())
['id_left', 'id_right', 'text_left', 'text_right']
>>> type(y)
<class 'numpy.ndarray'>
>>> X, y = data_pack.drop_label().unpack()
>>> type(y)
<class 'NoneType'>

matchzoo.data_pack.data_pack.load_data_pack(dirpath)¶

Load a DataPack. The reverse function of save().

Parameters: dirpath (Union[str, Path]) – directory path of the saved model.
Return type: DataPack
Returns: a DataPack instance.

matchzoo.data_pack.pack module¶

Convert list of input into class:DataPack expected format.

matchzoo.data_pack.pack.pack(df)¶

Pack a DataPack using df.

The df must have text_left and text_right columns. Optionally, the df can have id_left, id_right to index text_left and text_right respectively. id_left, id_right will be automatically generated if not specified.

Parameters: df (DataFrame) – Input pandas.DataFrame to use.

Examples::

>>> import matchzoo as mz
>>> import pandas as pd
>>> df = pd.DataFrame(data={'text_left': list('AABC'),
...                         'text_right': list('abbc'),
...                         'label': [0, 1, 1, 0]})
>>> mz.pack(df).frame()
  id_left text_left id_right text_right  label
0     L-0         A      R-0          a      0
1     L-0         A      R-1          b      1
2     L-1         B      R-1          b      1
3     L-2         C      R-2          c      0

Return type: DataPack

Module contents¶

matchzoo.datasets package¶

Subpackages¶

matchzoo.datasets.embeddings package¶

Submodules¶

matchzoo.datasets.embeddings.load_glove_embedding module¶

Module contents¶

matchzoo.datasets.quora_qp package¶

Submodules¶

matchzoo.datasets.quora_qp.load_data module¶

Module contents¶

matchzoo.datasets.snli package¶

Submodules¶

matchzoo.datasets.snli.load_data module¶

Module contents¶

matchzoo.datasets.toy package¶

Module contents¶

matchzoo.datasets.wiki_qa package¶

Submodules¶

matchzoo.datasets.wiki_qa.load_data module¶

Module contents¶

matchzoo.embedding package¶

Submodules¶

matchzoo.embedding.embedding module¶

Module contents¶

matchzoo.engine package¶

Submodules¶

matchzoo.engine.base_metric module¶

Metric base class and some related utilities.

class matchzoo.engine.base_metric.BaseMetric¶

Bases: abc.ABC

Metric base class.

ALIAS = 'base_metric'¶

matchzoo.engine.base_metric.sort_and_couple(labels, scores)¶

Zip the labels with scores into a single list.

Return type: array

matchzoo.engine.base_model module¶

matchzoo.engine.base_preprocessor module¶

matchzoo.engine.base_task module¶

Base task.

class matchzoo.engine.base_task.BaseTask(loss=None, metrics=None)¶

Bases: abc.ABC

Base Task, shouldn’t be used directly.

abstract classmethod list_available_losses()¶

Return type: list
Returns: a list of available losses.

abstract classmethod list_available_metrics()¶

Return type: list
Returns: a list of available metrics.

property loss¶

Loss used in the task.

Type: return

property metrics¶

Metrics used in the task.

Type: return

abstract property output_dtype¶

output data type for specific task.

Type: return

abstract property output_shape: tuple¶

output shape of a single sample of the task.

Type: return
Return type: tuple

matchzoo.engine.callbacks module¶

matchzoo.engine.hyper_spaces module¶

Hyper parameter search spaces wrapping hyperopt.

class matchzoo.engine.hyper_spaces.HyperoptProxy(hyperopt_func, **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(name)¶

Attach name as hyperopt.hp’s label.

Parameters: name (str) –
Return type: Apply
Returns: a hyperopt ready search space

class matchzoo.engine.hyper_spaces.choice(options)¶

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.choice() proxy.

class matchzoo.engine.hyper_spaces.quniform(low, high, q=1)¶

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.quniform() proxy.

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.Naive.get_default_params().hyper_space
>>> mz.hyper_spaces.sample(space)  
{'optimizer': ...}

class matchzoo.engine.hyper_spaces.uniform(low, high)¶

Bases: matchzoo.engine.hyper_spaces.HyperoptProxy

hyperopt.hp.uniform() proxy.

matchzoo.engine.param module¶

Parameter class.

class matchzoo.engine.param.Param(name, value=None, hyper_space=None, validator=None, desc=None)¶

Bases: object

Parameter class.

Basic usages with a name and value:

>>> param = Param('my_param', 10)
>>> param.name
'my_param'
>>> param.value
10

Use with a validator to make sure the parameter always keeps a valid value.

>>> param = Param(
...     name='my_param',
...     value=5,
...     validator=lambda x: 0 < x < 20
... )
>>> param.validator  
<function <lambda> at 0x...>
>>> param.value
5
>>> param.value = 10
>>> param.value
10
>>> param.value = -1
Traceback (most recent call last):
    ...
ValueError: Validator not satifised.
The validator's definition is as follows:
validator=lambda x: 0 < x < 20

Use with a hyper space. Setting up a hyper space for a parameter makes the parameter tunable in a matchzoo.engine.Tuner.

>>> from matchzoo.engine.hyper_spaces import quniform
>>> param = Param(
...     name='positive_num',
...     value=1,
...     hyper_space=quniform(low=1, high=5)
... )
>>> param.hyper_space  
<matchzoo.engine.hyper_spaces.quniform object at ...>
>>> from hyperopt.pyll.stochastic import sample
>>> hyperopt_space = param.hyper_space.convert(param.name)
>>> samples = [sample(hyperopt_space) for _ in range(64)]
>>> set(samples) == {1, 2, 3, 4, 5}
True

The boolean value of a Param instance is only True when the value is not None. This is because some default falsy values like zero or an empty list are valid parameter values. In other words, the boolean value means to be “if the parameter value is filled”.

>>> param = Param('dropout')
>>> if param:
...     print('OK')
>>> param = Param('dropout', 0)
>>> if param:
...     print('OK')
OK

A _pre_assignment_hook is initialized as a data type convertor if the value is set as a number to keep data type consistency of the parameter. This conversion supports python built-in numbers, numpy numbers, and any number that inherits numbers.Number.

>>> param = Param('float_param', 0.5)
>>> param.value = 10
>>> param.value
10.0
>>> type(param.value)
<class 'float'>

property desc: str¶

Parameter description.

Type: return
Return type: str

property hyper_space: Union[hyperopt.pyll.base.Apply, matchzoo.engine.hyper_spaces.HyperoptProxy]¶

Hyper space of the parameter.

Type: return
Return type: Union[Apply, HyperoptProxy]

property name: str¶

Name of the parameter.

Type: return
Return type: str

reset()¶

Set the parameter’s value to None, which means “not set”.

This method bypasses validator.

Example

>>> import matchzoo as mz
>>> param = mz.Param(
...     name='str', validator=lambda x: isinstance(x, str))
>>> param.value = 'hello'
>>> param.value = None
Traceback (most recent call last):
    ...
ValueError: Validator not satifised.
The validator's definition is as follows:
name='str', validator=lambda x: isinstance(x, str))
>>> param.reset()
>>> param.value is None
True

set_default(val, verbose=1)¶

Set default value, has no effect if already has a value.

Parameters

val – Default value to set.
verbose – Verbosity.

property validator: Callable[Any, bool]¶

Validator of the parameter.

Type: return
Return type: Callable[[Any], bool]

property value: Any¶

Value of the parameter.

Type: return
Return type: Any

matchzoo.engine.param_table module¶

Parameters table class.

class matchzoo.engine.param_table.ParamTable¶

Bases: object

Parameter table class.

Example

>>> params = ParamTable()
>>> params.add(Param('ham', 'Parma Ham'))
>>> params.add(Param('egg', 'Over Easy'))
>>> params['ham']
'Parma Ham'
>>> params['egg']
'Over Easy'
>>> print(params)
ham                           Parma Ham
egg                           Over Easy
>>> params.add(Param('egg', 'Sunny side Up'))
Traceback (most recent call last):
    ...
ValueError: Parameter named egg already exists.
To re-assign parameter egg value, use `params["egg"] = value` instead.

add(param)¶

Parameters: param (Param) – parameter to add.

completed()¶

Return type: bool
Returns: True if all params are filled, False otherwise.

Example

>>> import matchzoo
>>> model = matchzoo.models.Naive()
>>> model.params.completed()
False
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.params.completed()
True

get(key)¶

Return type: Param
Returns: The parameter in the table named key.

property hyper_space: dict¶

Hyper space of the table, a valid hyperopt graph.

Type: return
Return type: dict

keys()¶

Return type: KeysView
Returns: Parameter table keys.

set(key, param)¶: Set key to parameter param.

to_frame()¶

Convert the parameter table into a pandas data frame.

Return type: DataFrame
Returns: A pandas.DataFrame.

Example

>>> import matchzoo as mz
>>> table = mz.ParamTable()
>>> table.add(mz.Param(name='x', value=10, desc='my x'))
>>> table.add(mz.Param(name='y', value=20, desc='my y'))
>>> table.to_frame()
  Name Description  Value Hyper-Space
0    x        my x     10        None
1    y        my y     20        None

update(other)¶

Update self.

Update self with the key/value pairs from other, overwriting existing keys. Notice that this does not add new keys to self.

This method is usually used by models to obtain useful information from a preprocessor’s context.

Parameters: other (dict) – The dictionary used update.

Example

>>> import matchzoo as mz
>>> model = mz.models.DenseBaseline()
>>> model.params['input_shapes'] is None
True
>>> prpr = model.get_default_preprocessor()
>>> _ = prpr.fit(mz.datasets.toy.load_data(), verbose=0)
>>> model.params.update(prpr.context)
>>> model.params['input_shapes']
[(30,), (30,)]

matchzoo.engine.parse_metric module¶

matchzoo.engine.parse_metric.parse_metric(metric, task=None)¶

Parse input metric in any form into a BaseMetric instance.

Parameters

metric (Union[str, Type[BaseMetric], BaseMetric]) – Input metric in any form.
task (Optional[BaseTask]) – Task type for determining specific metric.

Return type

Union[BaseMetric, str]

Returns

A BaseMetric instance

Examples::

>>> from matchzoo import metrics
>>> from matchzoo.engine.parse_metric import parse_metric

Use str as keras native metrics:

>>> parse_metric('mse')
'mse'

Use str as MatchZoo metrics:

>>> mz_metric = parse_metric('map')
>>> type(mz_metric)
<class 'matchzoo.metrics.mean_average_precision.MeanAveragePrecision'>

Use matchzoo.engine.BaseMetric subclasses as MatchZoo metrics:

>>> type(parse_metric(metrics.AveragePrecision))
<class 'matchzoo.metrics.average_precision.AveragePrecision'>

Use matchzoo.engine.BaseMetric instances as MatchZoo metrics:

>>> type(parse_metric(metrics.AveragePrecision()))
<class 'matchzoo.metrics.average_precision.AveragePrecision'>

Module contents¶

matchzoo.layers package¶

Submodules¶

matchzoo.layers.dynamic_pooling_layer module¶

matchzoo.layers.matching_layer module¶

Module contents¶

matchzoo.losses package¶

Submodules¶

matchzoo.losses.rank_cross_entropy_loss module¶

matchzoo.losses.rank_hinge_loss module¶

Module contents¶

matchzoo.metrics package¶

Submodules¶

matchzoo.metrics.average_precision module¶

Average precision metric for ranking.

class matchzoo.metrics.average_precision.AveragePrecision(threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Average precision metric.

ALIAS = ['average_precision', 'ap']¶

matchzoo.metrics.discounted_cumulative_gain module¶

Discounted cumulative gain metric for ranking.

class matchzoo.metrics.discounted_cumulative_gain.DiscountedCumulativeGain(k=1, threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Disconunted cumulative gain metric.

ALIAS = ['discounted_cumulative_gain', 'dcg']¶

matchzoo.metrics.mean_average_precision module¶

Mean average precision metric for ranking.

class matchzoo.metrics.mean_average_precision.MeanAveragePrecision(threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Mean average precision metric.

ALIAS = ['mean_average_precision', 'map']¶

matchzoo.metrics.mean_reciprocal_rank module¶

Mean reciprocal ranking metric.

class matchzoo.metrics.mean_reciprocal_rank.MeanReciprocalRank(threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Mean reciprocal rank metric.

ALIAS = ['mean_reciprocal_rank', 'mrr']¶

matchzoo.metrics.normalized_discounted_cumulative_gain module¶

Normalized discounted cumulative gain metric for ranking.

class matchzoo.metrics.normalized_discounted_cumulative_gain.NormalizedDiscountedCumulativeGain(k=1, threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Normalized discounted cumulative gain metric.

ALIAS = ['normalized_discounted_cumulative_gain', 'ndcg']¶

matchzoo.metrics.precision module¶

Precision for ranking.

class matchzoo.metrics.precision.Precision(k=1, threshold=0.0)¶

Bases: matchzoo.engine.base_metric.BaseMetric

Precision metric.

ALIAS = 'precision'¶

Module contents¶

matchzoo.metrics.list_available()¶

Return type: list

matchzoo.models package¶

Submodules¶

matchzoo.models.anmm module¶

matchzoo.models.arci module¶

matchzoo.models.arcii module¶

matchzoo.models.cdssm module¶

matchzoo.models.conv_knrm module¶

matchzoo.models.dense_baseline module¶

matchzoo.models.drmm module¶

matchzoo.models.drmmtks module¶

matchzoo.models.dssm module¶

matchzoo.models.duet module¶

matchzoo.models.knrm module¶

matchzoo.models.match_pyramid module¶

matchzoo.models.mvlstm module¶

matchzoo.models.naive module¶

matchzoo.models.parameter_readme_generator module¶

Module contents¶

matchzoo.preprocessors package¶

Subpackages¶

matchzoo.preprocessors.units package¶

Submodules¶

matchzoo.preprocessors.units.digit_removal module¶

class matchzoo.preprocessors.units.digit_removal.DigitRemoval¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit to remove digits.

transform(input_)¶

Remove digits from list of tokens.

Parameters: input – list of tokens to be filtered.
Return tokens: tokens of tokens without digits.
Return type: list

matchzoo.preprocessors.units.fixed_length module¶

class matchzoo.preprocessors.units.fixed_length.FixedLength(text_length, pad_value=0, pad_mode='pre', truncate_mode='pre')¶

Bases: matchzoo.preprocessors.units.unit.Unit

FixedLengthUnit Class.

Process unit to get the fixed length text.

Examples

>>> from matchzoo.preprocessors.units import FixedLength
>>> fixedlen = FixedLength(3)
>>> fixedlen.transform(list(range(1, 6))) == [3, 4, 5]
True
>>> fixedlen.transform(list(range(1, 3))) == [0, 1, 2]
True

transform(input_)¶

Transform list of tokenized tokens into the fixed length text.

Parameters: input – list of tokenized tokens.
Return tokens: list of tokenized tokens in fixed length.
Return type: list

matchzoo.preprocessors.units.frequency_filter module¶

class matchzoo.preprocessors.units.frequency_filter.FrequencyFilter(low=0, high=inf, mode='df')¶

Bases: matchzoo.preprocessors.units.stateful_unit.StatefulUnit

Frequency filter unit.

Parameters

low (float) – Lower bound, inclusive.
high (float) – Upper bound, exclusive.
mode (str) – One of tf (term frequency), df (document frequency), and idf (inverse document frequency).

Examples::

>>> import matchzoo as mz

To filter based on term frequency (tf):

>>> tf_filter = mz.preprocessors.units.FrequencyFilter(
...     low=2, mode='tf')
>>> tf_filter.fit([['A', 'B', 'B'], ['C', 'C', 'C']])
>>> tf_filter.transform(['A', 'B', 'C'])
['B', 'C']

To filter based on document frequency (df):

>>> tf_filter = mz.preprocessors.units.FrequencyFilter(
...     low=2, mode='df')
>>> tf_filter.fit([['A', 'B'], ['B', 'C']])
>>> tf_filter.transform(['A', 'B', 'C'])
['B']

To filter based on inverse document frequency (idf):

>>> idf_filter = mz.preprocessors.units.FrequencyFilter(
...     low=1.2, mode='idf')
>>> idf_filter.fit([['A', 'B'], ['B', 'C', 'D']])
>>> idf_filter.transform(['A', 'B', 'C'])
['A', 'C']

fit(list_of_tokens)¶: Fit list_of_tokens by calculating mode states.

transform(input_)¶

Transform a list of tokens by filtering out unwanted words.

Return type: list

matchzoo.preprocessors.units.lemmatization module¶

class matchzoo.preprocessors.units.lemmatization.Lemmatization¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit for token lemmatization.

transform(input_)¶

Lemmatization a sequence of tokens.

Parameters: input – list of tokens to be lemmatized.
Return tokens: list of lemmatizd tokens.
Return type: list

matchzoo.preprocessors.units.lowercase module¶

class matchzoo.preprocessors.units.lowercase.Lowercase¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit for text lower case.

transform(input_)¶

Convert list of tokens to lower case.

Parameters: input – list of tokens.
Return tokens: lower-cased list of tokens.
Return type: list

matchzoo.preprocessors.units.matching_histogram module¶

class matchzoo.preprocessors.units.matching_histogram.MatchingHistogram(bin_size=30, embedding_matrix=None, normalize=True, mode='LCH')¶

Bases: matchzoo.preprocessors.units.unit.Unit

MatchingHistogramUnit Class.

Parameters

bin_size (int) – The number of bins of the matching histogram.
embedding_matrix – The word embedding matrix applied to calculate the matching histogram.
normalize – Boolean, normalize the embedding or not.
mode (str) – The type of the historgram, it should be one of ‘CH’, ‘NG’, or ‘LCH’.

Examples

>>> embedding_matrix = np.array([[1.0, -1.0], [1.0, 2.0], [1.0, 3.0]])
>>> text_left = [0, 1]
>>> text_right = [1, 2]
>>> histogram = MatchingHistogram(3, embedding_matrix, True, 'CH')
>>> histogram.transform([text_left, text_right])
[[3.0, 1.0, 1.0], [1.0, 2.0, 2.0]]

transform(input_)¶

Transform the input text.

Return type: list

matchzoo.preprocessors.units.ngram_letter module¶

class matchzoo.preprocessors.units.ngram_letter.NgramLetter(ngram=3, reduce_dim=True)¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit for n-letter generation.

Triletter is used in DSSMModel. This processor is expected to execute before Vocab has been created.

Examples

>>> triletter = NgramLetter()
>>> rv = triletter.transform(['hello', 'word'])
>>> len(rv)
9
>>> rv
['#he', 'hel', 'ell', 'llo', 'lo#', '#wo', 'wor', 'ord', 'rd#']
>>> triletter = NgramLetter(reduce_dim=False)
>>> rv = triletter.transform(['hello', 'word'])
>>> len(rv)
2
>>> rv
[['#he', 'hel', 'ell', 'llo', 'lo#'], ['#wo', 'wor', 'ord', 'rd#']]

transform(input_)¶

Transform token into tri-letter.

For example, word should be represented as #wo, wor, ord and rd#.

Parameters: input – list of tokens to be transformed.
Return n_letters: generated n_letters.
Return type: list

matchzoo.preprocessors.units.punc_removal module¶

class matchzoo.preprocessors.units.punc_removal.PuncRemoval¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit for remove punctuations.

transform(input_)¶

Remove punctuations from list of tokens.

Parameters: input – list of toekns.
Return rv: tokens without punctuation.
Return type: list

matchzoo.preprocessors.units.stateful_unit module¶

class matchzoo.preprocessors.units.stateful_unit.StatefulUnit¶

Bases: matchzoo.preprocessors.units.unit.Unit

Unit with inner state.

Usually need to be fit before transforming. All information gathered in the fit phrase will be stored into its context.

property context¶: Get current context. Same as unit.state.

abstract fit(input_)¶: Abstract base method, need to be implemented in subclass.

property state¶

Get current context. Same as unit.context.

Deprecated since v2.2.0, and will be removed in the future. Used unit.context instead.

matchzoo.preprocessors.units.stemming module¶

class matchzoo.preprocessors.units.stemming.Stemming(stemmer='porter')¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit for token stemming.

Parameters: stemmer – stemmer to use, porter or lancaster.

transform(input_)¶

Reducing inflected words to their word stem, base or root form.

Parameters: input – list of string to be stemmed.
Return type: list

matchzoo.preprocessors.units.stop_removal module¶

class matchzoo.preprocessors.units.stop_removal.StopRemoval(lang='english')¶

Bases: matchzoo.preprocessors.units.unit.Unit

Process unit to remove stop words.

Example

>>> unit = StopRemoval()
>>> unit.transform(['a', 'the', 'test'])
['test']
>>> type(unit.stopwords)
<class 'list'>

property stopwords: list¶

Get stopwords based on language.

Params lang: language code.
Return type: list
Returns: list of stop words.

transform(input_)¶

Remove stopwords from list of tokenized tokens.

Parameters

input – list of tokenized tokens.
lang – language code for stopwords.

Return tokens

list of tokenized tokens without stopwords.

Return type

list

matchzoo.preprocessors.units.tokenize module¶

matchzoo.preprocessors.units.unit module¶

class matchzoo.preprocessors.units.unit.Unit¶

Bases: object

Process unit do not persive state (i.e. do not need fit).

abstract transform(input_)¶: Abstract base method, need to be implemented in subclass.

matchzoo.preprocessors.units.vocabulary module¶

matchzoo.preprocessors.units.word_hashing module¶

Module contents¶

Submodules¶

matchzoo.preprocessors.basic_preprocessor module¶

matchzoo.preprocessors.build_unit_from_data_pack module¶

matchzoo.preprocessors.build_vocab_unit module¶

matchzoo.preprocessors.cdssm_preprocessor module¶

matchzoo.preprocessors.chain_transform module¶

matchzoo.preprocessors.dssm_preprocessor module¶

matchzoo.preprocessors.naive_preprocessor module¶

Module contents¶

matchzoo.tasks package¶

Submodules¶

matchzoo.tasks.classification module¶

Classification task.

class matchzoo.tasks.classification.Classification(num_classes=2, **kwargs)¶

Bases: matchzoo.engine.base_task.BaseTask

Classification task.

Examples

>>> classification_task = Classification(num_classes=2)
>>> classification_task.metrics = ['precision']
>>> classification_task.num_classes
2
>>> classification_task.output_shape
(2,)
>>> classification_task.output_dtype
<class 'int'>
>>> print(classification_task)
Classification Task with 2 classes

classmethod list_available_losses()¶

Return type: list
Returns: a list of available losses.

classmethod list_available_metrics()¶

Return type: list
Returns: a list of available metrics.

property num_classes: int¶

number of classes to classify.

Type: return
Return type: int

property output_dtype¶

target data type, expect int as output.

Type: return

property output_shape: tuple¶

output shape of a single sample of the task.

Type: return
Return type: tuple

matchzoo.tasks.ranking module¶

Ranking task.

class matchzoo.tasks.ranking.Ranking(loss=None, metrics=None)¶

Bases: matchzoo.engine.base_task.BaseTask

Ranking Task.

Examples

>>> ranking_task = Ranking()
>>> ranking_task.metrics = ['map', 'ndcg']
>>> ranking_task.output_shape
(1,)
>>> ranking_task.output_dtype
<class 'float'>
>>> print(ranking_task)
Ranking Task

classmethod list_available_losses()¶

Return type: list
Returns: a list of available losses.

classmethod list_available_metrics()¶

Return type: list
Returns: a list of available metrics.

property output_dtype¶

target data type, expect float as output.

Type: return

property output_shape: tuple¶

output shape of a single sample of the task.

Type: return
Return type: tuple

Module contents¶

matchzoo.utils package¶

Submodules¶

matchzoo.utils.list_recursive_subclasses module¶

matchzoo.utils.list_recursive_subclasses.list_recursive_concrete_subclasses(base)¶: List all concrete subclasses of base recursively.

matchzoo.utils.make_keras_optimizer_picklable module¶

matchzoo.utils.one_hot module¶

One hot vectors.

matchzoo.utils.one_hot.one_hot(indices, num_classes)¶

Return type: ndarray
Returns: A one-hot encoded vector.

matchzoo.utils.tensor_type module¶

Define Keras tensor type.

Module contents¶

Submodules¶

matchzoo.version module¶

Module contents¶

MatchZoo Model Reference¶

Naive¶

Model Documentation¶

Naive model with a simplest structure for testing purposes.

Bare minimum functioning model. The best choice to get things rolling. The worst choice to fit and evaluate performance.

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.naive.Naive’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam	choice in [‘adam’, ‘adagrad’, ‘rmsprop’]

DSSM¶

Model Documentation¶

Deep structured semantic model.

Examples:

>>> model = DSSM()
>>> model.params['mlp_num_layers'] = 3
>>> model.params['mlp_num_units'] = 300
>>> model.params['mlp_num_fan_out'] = 128
>>> model.params['mlp_activation_func'] = 'relu'
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.dssm.DSSM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
5	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
6	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
7	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
8	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu

CDSSM¶

Model Documentation¶

CDSSM Model implementation.

Learning Semantic Representations Using Convolutional Neural Networks for Web Search. (2014a) A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval. (2014b)

Examples:

>>> model = CDSSM()
>>> model.params['optimizer'] = 'adam'
>>> model.params['filters'] =  32
>>> model.params['kernel_size'] = 3
>>> model.params['conv_activation_func'] = 'relu'
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.cdssm.CDSSM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
5	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
6	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
7	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
8	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu
9	filters	Number of filters in the 1D convolution layer.	32
10	kernel_size	Number of kernel size in the 1D convolution layer.	3
11	strides	Strides in the 1D convolution layer.	1
12	padding	The padding mode in the convolution layer. It should be one of same, valid, and causal.	same
13	conv_activation_func	Activation function in the convolution layer.	relu
14	w_initializer		glorot_normal
15	b_initializer		zeros
16	dropout_rate	The dropout rate.	0.3

DenseBaseline¶

Model Documentation¶

A simple densely connected baseline model.

Examples:

>>> model = DenseBaseline()
>>> model.params['mlp_num_layers'] = 2
>>> model.params['mlp_num_units'] = 300
>>> model.params['mlp_num_fan_out'] = 128
>>> model.params['mlp_activation_func'] = 'relu'
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()
>>> model.compile()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.dense_baseline.DenseBaseline’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
5	mlp_num_units	Number of units in first mlp_num_layers layers.	256	quantitative uniform distribution in [16, 512), with a step size of 1
6	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 5), with a step size of 1
7	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
8	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu

ArcI¶

Model Documentation¶

ArcI Model.

Examples:

>>> model = ArcI()
>>> model.params['num_blocks'] = 1
>>> model.params['left_filters'] = [32]
>>> model.params['right_filters'] = [32]
>>> model.params['left_kernel_sizes'] = [3]
>>> model.params['right_kernel_sizes'] = [3]
>>> model.params['left_pool_sizes'] = [2]
>>> model.params['right_pool_sizes'] = [4]
>>> model.params['conv_activation_func'] = 'relu'
>>> model.params['mlp_num_layers'] = 1
>>> model.params['mlp_num_units'] = 64
>>> model.params['mlp_num_fan_out'] = 32
>>> model.params['mlp_activation_func'] = 'relu'
>>> model.params['dropout_rate'] = 0.5
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.arci.ArcI’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
9	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
10	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
11	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
12	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu
13	num_blocks	Number of convolution blocks.	1
14	left_filters	The filter size of each convolution blocks for the left input.	[32]
15	left_kernel_sizes	The kernel size of each convolution blocks for the left input.	[3]
16	right_filters	The filter size of each convolution blocks for the right input.	[32]
17	right_kernel_sizes	The kernel size of each convolution blocks for the right input.	[3]
18	conv_activation_func	The activation function in the convolution layer.	relu
19	left_pool_sizes	The pooling size of each convolution blocks for the left input.	[2]
20	right_pool_sizes	The pooling size of each convolution blocks for the right input.	[2]
21	padding	The padding mode in the convolution layer. It should be oneof same, valid, and causal.	same	choice in [‘same’, ‘valid’, ‘causal’]
22	dropout_rate	The dropout rate.	0.0	quantitative uniform distribution in [0.0, 0.8), with a step size of 0.01

ArcII¶

Model Documentation¶

ArcII Model.

Examples:

>>> model = ArcII()
>>> model.params['embedding_output_dim'] = 300
>>> model.params['num_blocks'] = 2
>>> model.params['kernel_1d_count'] = 32
>>> model.params['kernel_1d_size'] = 3
>>> model.params['kernel_2d_count'] = [16, 32]
>>> model.params['kernel_2d_size'] = [[3, 3], [3, 3]]
>>> model.params['pool_2d_size'] = [[2, 2], [2, 2]]
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.arcii.ArcII’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam	choice in [‘adam’, ‘rmsprop’, ‘adagrad’]
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	num_blocks	Number of 2D convolution blocks.	1
9	kernel_1d_count	Kernel count of 1D convolution layer.	32
10	kernel_1d_size	Kernel size of 1D convolution layer.	3
11	kernel_2d_count	Kernel count of 2D convolution layer ineach block	[32]
12	kernel_2d_size	Kernel size of 2D convolution layer in each block.	[[3, 3]]
13	activation	Activation function.	relu
14	pool_2d_size	Size of pooling layer in each block.	[[2, 2]]
15	padding	The padding mode in the convolution layer. It should be oneof same, valid.	same	choice in [‘same’, ‘valid’]
16	dropout_rate	The dropout rate.	0.0	quantitative uniform distribution in [0.0, 0.8), with a step size of 0.01

MatchPyramid¶

Model Documentation¶

MatchPyramid Model.

Examples:

>>> model = MatchPyramid()
>>> model.params['embedding_output_dim'] = 300
>>> model.params['num_blocks'] = 2
>>> model.params['kernel_count'] = [16, 32]
>>> model.params['kernel_size'] = [[3, 3], [3, 3]]
>>> model.params['dpool_size'] = [3, 10]
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.match_pyramid.MatchPyramid’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	num_blocks	Number of convolution blocks.	1
9	kernel_count	The kernel count of the 2D convolution of each block.	[32]
10	kernel_size	The kernel size of the 2D convolution of each block.	[[3, 3]]
11	activation	The activation function.	relu
12	dpool_size	The max-pooling size of each block.	[3, 10]
13	padding	The padding mode in the convolution layer.	same
14	dropout_rate	The dropout rate.	0.0	quantitative uniform distribution in [0.0, 0.8), with a step size of 0.01

KNRM¶

Model Documentation¶

KNRM model.

Examples:

>>> model = KNRM()
>>> model.params['embedding_input_dim'] =  10000
>>> model.params['embedding_output_dim'] =  10
>>> model.params['embedding_trainable'] = True
>>> model.params['kernel_num'] = 11
>>> model.params['sigma'] = 0.1
>>> model.params['exact_sigma'] = 0.001
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.knrm.KNRM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	kernel_num	The number of RBF kernels.	11	quantitative uniform distribution in [5, 20), with a step size of 1
9	sigma	The sigma defines the kernel width.	0.1	quantitative uniform distribution in [0.01, 0.2), with a step size of 0.01
10	exact_sigma	The exact_sigma denotes the sigma for exact match.	0.001

DUET¶

Model Documentation¶

DUET Model.

Examples:

>>> model = DUET()
>>> model.params['embedding_input_dim'] = 1000
>>> model.params['embedding_output_dim'] = 300
>>> model.params['lm_filters'] = 32
>>> model.params['lm_hidden_sizes'] = [64, 32]
>>> model.params['dropout_rate'] = 0.5
>>> model.params['dm_filters'] = 32
>>> model.params['dm_kernel_size'] = 3
>>> model.params['dm_d_mpool'] = 4
>>> model.params['dm_hidden_sizes'] = [64, 32]
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.duet.DUET’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	lm_filters	Filter size of 1D convolution layer in the local model.	32
9	lm_hidden_sizes	A list of hidden size of the MLP layer in the local model.	[32]
10	dm_filters	Filter size of 1D convolution layer in the distributed model.	32
11	dm_kernel_size	Kernel size of 1D convolution layer in the distributed model.	3
12	dm_q_hidden_size	Hidden size of the MLP layer for the left text in the distributed model.	32
13	dm_d_mpool	Max pooling size for the right text in the distributed model.	3
14	dm_hidden_sizes	A list of hidden size of the MLP layer in the distributed model.	[32]
15	padding	The padding mode in the convolution layer. It should be one of same, valid, and causal.	same
16	activation_func	Activation function in the convolution layer.	relu
17	dropout_rate	The dropout rate.	0.5	quantitative uniform distribution in [0.0, 0.8), with a step size of 0.02

DRMMTKS¶

Model Documentation¶

DRMMTKS Model.

Examples:

>>> model = DRMMTKS()
>>> model.params['embedding_input_dim'] = 10000
>>> model.params['embedding_output_dim'] = 100
>>> model.params['top_k'] = 20
>>> model.params['mlp_num_layers'] = 1
>>> model.params['mlp_num_units'] = 5
>>> model.params['mlp_num_fan_out'] = 1
>>> model.params['mlp_activation_func'] = 'tanh'
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.drmmtks.DRMMTKS’>
1	input_shapes	Dependent on the model and data. Should be set manually.	[(5,), (300,)]
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
9	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
10	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
11	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
12	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu
13	mask_value	The value to be masked from inputs.	-1
14	top_k	Size of top-k pooling layer.	10	quantitative uniform distribution in [2, 100), with a step size of 1

DRMM¶

Model Documentation¶

DRMM Model.

Examples:

>>> model = DRMM()
>>> model.params['mlp_num_layers'] = 1
>>> model.params['mlp_num_units'] = 5
>>> model.params['mlp_num_fan_out'] = 1
>>> model.params['mlp_activation_func'] = 'tanh'
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()
>>> model.compile()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.drmm.DRMM’>
1	input_shapes	Dependent on the model and data. Should be set manually.	[(5,), (5, 30)]
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
9	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
10	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
11	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
12	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu
13	mask_value	The value to be masked from inputs.	-1

ANMM¶

Model Documentation¶

ANMM Model.

Examples:

>>> model = ANMM()
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.anmm.ANMM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	dropout_rate	The dropout rate.	0.1	quantitative uniform distribution in [0, 1), with a step size of 0.05
9	num_layers	Number of hidden layers in the MLP layer.	2
10	hidden_sizes	Number of hidden size for each hidden layer	[30, 30]

MVLSTM¶

Model Documentation¶

MVLSTM Model.

Examples:

>>> model = MVLSTM()
>>> model.params['lstm_units'] = 32
>>> model.params['top_k'] = 50
>>> model.params['mlp_num_layers'] = 2
>>> model.params['mlp_num_units'] = 20
>>> model.params['mlp_num_fan_out'] = 10
>>> model.params['mlp_activation_func'] = 'relu'
>>> model.params['dropout_rate'] = 0.5
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.mvlstm.MVLSTM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	with_multi_layer_perceptron	A flag of whether a multiple layer perceptron is used. Shouldn’t be changed.	True
9	mlp_num_units	Number of units in first mlp_num_layers layers.	128	quantitative uniform distribution in [8, 256), with a step size of 8
10	mlp_num_layers	Number of layers of the multiple layer percetron.	3	quantitative uniform distribution in [1, 6), with a step size of 1
11	mlp_num_fan_out	Number of units of the layer that connects the multiple layer percetron and the output.	64	quantitative uniform distribution in [4, 128), with a step size of 4
12	mlp_activation_func	Activation function used in the multiple layer perceptron.	relu
13	lstm_units	Integer, the hidden size in the bi-directional LSTM layer.	32
14	dropout_rate	Float, the dropout rate.	0.0
15	top_k	Integer, the size of top-k pooling layer.	10	quantitative uniform distribution in [2, 100), with a step size of 1

MatchLSTM¶

Model Documentation¶

Match LSTM model.

Examples:

>>> model = MatchLSTM()
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.params['embedding_input_dim'] = 10000
>>> model.params['embedding_output_dim'] = 100
>>> model.params['embedding_trainable'] = True
>>> model.params['fc_num_units'] = 200
>>> model.params['lstm_num_units'] = 256
>>> model.params['dropout_rate'] = 0.5
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.contrib.models.match_lstm.MatchLSTM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	lstm_num_units	The hidden size in the LSTM layer.	256	quantitative uniform distribution in [128, 384), with a step size of 32
9	fc_num_units	The hidden size in the full connection layer.	200	quantitative uniform distribution in [100, 300), with a step size of 20
10	dropout_rate	The dropout rate.	0.0	quantitative uniform distribution in [0.0, 0.9), with a step size of 0.01

ConvKNRM¶

Model Documentation¶

ConvKNRM model.

Examples:

>>> model = ConvKNRM()
>>> model.params['embedding_input_dim'] = 10000
>>> model.params['embedding_output_dim'] = 300
>>> model.params['embedding_trainable'] = True
>>> model.params['filters'] = 128
>>> model.params['conv_activation_func'] = 'tanh'
>>> model.params['max_ngram'] = 3
>>> model.params['use_crossmatch'] = True
>>> model.params['kernel_num'] = 11
>>> model.params['sigma'] = 0.1
>>> model.params['exact_sigma'] = 0.001
>>> model.guess_and_fill_missing_params(verbose=0)
>>> model.build()

Model Hyper Parameters¶

	Name	Description	Default Value	Default Hyper-Space
0	model_class	Model class. Used internally for save/load. Changing this may cause unexpected behaviors.	<class ‘matchzoo.models.conv_knrm.ConvKNRM’>
1	input_shapes	Dependent on the model and data. Should be set manually.
2	task	Decides model output shape, loss, and metrics.
3	optimizer		adam
4	with_embedding	A flag used help auto module. Shouldn’t be changed.	True
5	embedding_input_dim	Usually equals vocab size + 1. Should be set manually.
6	embedding_output_dim	Should be set manually.
7	embedding_trainable	True to enable embedding layer training, False to freeze embedding parameters.	True
8	kernel_num	The number of RBF kernels.	11	quantitative uniform distribution in [5, 20), with a step size of 1
9	sigma	The sigma defines the kernel width.	0.1	quantitative uniform distribution in [0.01, 0.2), with a step size of 0.01
10	exact_sigma	The exact_sigma denotes the sigma for exact match.	0.001
11	filters	The filter size in the convolution layer.	128
12	conv_activation_func	The activation function in the convolution layer.	relu
13	max_ngram	The maximum length of n-grams for the convolution layer.	3
14	use_crossmatch	Whether to match left n-grams and right n-grams of different lengths	True