Labeling Models¶
Table of Contents
Bidirectional LSTM Model¶
-
class
kashgari.tasks.labeling.
BiLSTM_Model
(embedding=None, sequence_length=None, hyper_parameters=None)[source]¶ Bases:
kashgari.tasks.labeling.abc_model.ABCLabelingModel
-
__init__
(embedding=None, sequence_length=None, hyper_parameters=None)¶
-
build_model
(x_data, y_data)¶ Build Model with x_data and y_data
- This function will setup a
CorpusGenerator
, then call
ABCClassificationModel.build_model_gen()
for preparing processor and model
Returns:
- This function will setup a
-
build_model_generator
(generators)¶ - Parameters
generators (List[kashgari.generators.CorpusGenerator]) –
- Return type
-
compile_model
(loss=None, optimizer=None, metrics=None, **kwargs)¶ Configures the model for training. call
tf.keras.Model.predict()
to compile model with custom loss, optimizer and metricsExamples
>>> model = BiLSTM_Model() # Build model with corpus >>> model.build_model(train_x, train_y) # Compile model with custom loss, optimizer and metrics >>> model.compile(loss='categorical_crossentropy', optimizer='rsm', metrics = ['accuracy'])
- Parameters
loss (Any) – name of objective function, objective function or
tf.keras.losses.Loss
instance.optimizer (Any) – name of optimizer or optimizer instance.
metrics (object) – List of metrics to be evaluated by the model during training and testing.
kwargs (Any) – additional params passed to
tf.keras.Model.predict`()
.
- Return type
-
classmethod
default_hyper_parameters
()[source]¶ The default hyper parameters of the model dict, all models must implement this function.
You could easily change model’s hyper-parameters.
For example, change the LSTM unit in BiLSTM_Model from 128 to 32.
>>> from kashgari.tasks.classification import BiLSTM_Model >>> hyper = BiLSTM_Model.default_hyper_parameters() >>> print(hyper) {'layer_bi_lstm': {'units': 128, 'return_sequences': False}, 'layer_output': {}} >>> hyper['layer_bi_lstm']['units'] = 32 >>> model = BiLSTM_Model(hyper_parameters=hyper)
-
evaluate
(x_data, y_data, batch_size=32, digits=4, truncating=False)¶ Build a text report showing the main labeling metrics.
- Parameters
- Returns
A report dict
- Return type
Dict
Example
>>> from kashgari.tasks.labeling import BiGRU_Model >>> model = BiGRU_Model() >>> model.fit(train_x, train_y, valid_x, valid_y) >>> report = model.evaluate(test_x, test_y) precision recall f1-score support ORG 0.0665 0.1108 0.0831 984 LOC 0.1870 0.2086 0.1972 1951 PER 0.1685 0.0882 0.1158 884 micro avg 0.1384 0.1555 0.1465 3819 macro avg 0.1516 0.1555 0.1490 3819 >>> print(report) { 'f1-score': 0.14895159934887792, 'precision': 0.1516294012813676, 'recall': 0.15553809897879026, 'support': 3819, 'detail': {'LOC': {'f1-score': 0.19718992248062014, 'precision': 0.18695452457510336, 'recall': 0.20861096873398258, 'support': 1951}, 'ORG': {'f1-score': 0.08307926829268293, 'precision': 0.06646341463414634, 'recall': 0.11077235772357724, 'support': 984}, 'PER': {'f1-score': 0.11581291759465479, 'precision': 0.16846652267818574, 'recall': 0.08823529411764706, 'support': 884}}, }
-
fit
(x_train, y_train, x_validate=None, y_validate=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data set list.
- Parameters
x_train (List[List[str]]) – Array of train feature data (if the model has a single input), or tuple of train feature data array (if the model has multiple inputs)
y_train (List[List[str]]) – Array of train label data
x_validate (List[List[str]]) – Array of validation feature data (if the model has a single input), or tuple of validation feature data array (if the model has multiple inputs)
y_validate (List[List[str]]) – Array of validation label data
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tensorflow.python.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See
tf.keras.callbacks
.fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
fit_generator
(train_sample_gen, valid_sample_gen=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data generator.
Data generator must be the subclass of CorpusGenerator
- Parameters
train_sample_gen (kashgari.generators.CorpusGenerator) – train data generator.
valid_sample_gen (kashgari.generators.CorpusGenerator) – valid data generator.
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tf.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks.
fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
classmethod
load_model
(model_path, custom_objects=None, encoding='utf-8')¶
-
predict
(x_data, *, batch_size=32, truncating=False, predict_kwargs=None)¶ Generates output predictions for the input samples.
Computation is done in batches.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
array(s) of predictions.
- Return type
List[List[str]]
-
predict_entities
(x_data, batch_size=32, join_chunk=' ', truncating=False, predict_kwargs=None)¶ Gets entities from sequence.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
join_chunk (str) – str or False,
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
list of entity.
- Return type
-
Bidirectional GRU Model¶
-
class
kashgari.tasks.labeling.
BiGRU_Model
(embedding=None, sequence_length=None, hyper_parameters=None)[source]¶ Bases:
kashgari.tasks.labeling.abc_model.ABCLabelingModel
-
__init__
(embedding=None, sequence_length=None, hyper_parameters=None)¶
-
build_model
(x_data, y_data)¶ Build Model with x_data and y_data
- This function will setup a
CorpusGenerator
, then call
ABCClassificationModel.build_model_gen()
for preparing processor and model
Returns:
- This function will setup a
-
build_model_generator
(generators)¶ - Parameters
generators (List[kashgari.generators.CorpusGenerator]) –
- Return type
-
compile_model
(loss=None, optimizer=None, metrics=None, **kwargs)¶ Configures the model for training. call
tf.keras.Model.predict()
to compile model with custom loss, optimizer and metricsExamples
>>> model = BiLSTM_Model() # Build model with corpus >>> model.build_model(train_x, train_y) # Compile model with custom loss, optimizer and metrics >>> model.compile(loss='categorical_crossentropy', optimizer='rsm', metrics = ['accuracy'])
- Parameters
loss (Any) – name of objective function, objective function or
tf.keras.losses.Loss
instance.optimizer (Any) – name of optimizer or optimizer instance.
metrics (object) – List of metrics to be evaluated by the model during training and testing.
kwargs (Any) – additional params passed to
tf.keras.Model.predict`()
.
- Return type
-
classmethod
default_hyper_parameters
()[source]¶ The default hyper parameters of the model dict, all models must implement this function.
You could easily change model’s hyper-parameters.
For example, change the LSTM unit in BiLSTM_Model from 128 to 32.
>>> from kashgari.tasks.classification import BiLSTM_Model >>> hyper = BiLSTM_Model.default_hyper_parameters() >>> print(hyper) {'layer_bi_lstm': {'units': 128, 'return_sequences': False}, 'layer_output': {}} >>> hyper['layer_bi_lstm']['units'] = 32 >>> model = BiLSTM_Model(hyper_parameters=hyper)
-
evaluate
(x_data, y_data, batch_size=32, digits=4, truncating=False)¶ Build a text report showing the main labeling metrics.
- Parameters
- Returns
A report dict
- Return type
Dict
Example
>>> from kashgari.tasks.labeling import BiGRU_Model >>> model = BiGRU_Model() >>> model.fit(train_x, train_y, valid_x, valid_y) >>> report = model.evaluate(test_x, test_y) precision recall f1-score support ORG 0.0665 0.1108 0.0831 984 LOC 0.1870 0.2086 0.1972 1951 PER 0.1685 0.0882 0.1158 884 micro avg 0.1384 0.1555 0.1465 3819 macro avg 0.1516 0.1555 0.1490 3819 >>> print(report) { 'f1-score': 0.14895159934887792, 'precision': 0.1516294012813676, 'recall': 0.15553809897879026, 'support': 3819, 'detail': {'LOC': {'f1-score': 0.19718992248062014, 'precision': 0.18695452457510336, 'recall': 0.20861096873398258, 'support': 1951}, 'ORG': {'f1-score': 0.08307926829268293, 'precision': 0.06646341463414634, 'recall': 0.11077235772357724, 'support': 984}, 'PER': {'f1-score': 0.11581291759465479, 'precision': 0.16846652267818574, 'recall': 0.08823529411764706, 'support': 884}}, }
-
fit
(x_train, y_train, x_validate=None, y_validate=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data set list.
- Parameters
x_train (List[List[str]]) – Array of train feature data (if the model has a single input), or tuple of train feature data array (if the model has multiple inputs)
y_train (List[List[str]]) – Array of train label data
x_validate (List[List[str]]) – Array of validation feature data (if the model has a single input), or tuple of validation feature data array (if the model has multiple inputs)
y_validate (List[List[str]]) – Array of validation label data
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tensorflow.python.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See
tf.keras.callbacks
.fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
fit_generator
(train_sample_gen, valid_sample_gen=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data generator.
Data generator must be the subclass of CorpusGenerator
- Parameters
train_sample_gen (kashgari.generators.CorpusGenerator) – train data generator.
valid_sample_gen (kashgari.generators.CorpusGenerator) – valid data generator.
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tf.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks.
fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
classmethod
load_model
(model_path, custom_objects=None, encoding='utf-8')¶
-
predict
(x_data, *, batch_size=32, truncating=False, predict_kwargs=None)¶ Generates output predictions for the input samples.
Computation is done in batches.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
array(s) of predictions.
- Return type
List[List[str]]
-
predict_entities
(x_data, batch_size=32, join_chunk=' ', truncating=False, predict_kwargs=None)¶ Gets entities from sequence.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
join_chunk (str) – str or False,
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
list of entity.
- Return type
-
Bidirectional LSTM CRF Model¶
-
class
kashgari.tasks.labeling.
BiLSTM_CRF_Model
(embedding=None, sequence_length=None, hyper_parameters=None)[source]¶ Bases:
kashgari.tasks.labeling.abc_model.ABCLabelingModel
-
__init__
(embedding=None, sequence_length=None, hyper_parameters=None)¶
-
build_model
(x_data, y_data)¶ Build Model with x_data and y_data
- This function will setup a
CorpusGenerator
, then call
ABCClassificationModel.build_model_gen()
for preparing processor and model
Returns:
- This function will setup a
-
build_model_generator
(generators)¶ - Parameters
generators (List[kashgari.generators.CorpusGenerator]) –
- Return type
-
compile_model
(loss=None, optimizer=None, metrics=None, **kwargs)[source]¶ Configures the model for training. call
tf.keras.Model.predict()
to compile model with custom loss, optimizer and metricsExamples
>>> model = BiLSTM_Model() # Build model with corpus >>> model.build_model(train_x, train_y) # Compile model with custom loss, optimizer and metrics >>> model.compile(loss='categorical_crossentropy', optimizer='rsm', metrics = ['accuracy'])
- Parameters
loss (Any) – name of objective function, objective function or
tf.keras.losses.Loss
instance.optimizer (Any) – name of optimizer or optimizer instance.
metrics (object) – List of metrics to be evaluated by the model during training and testing.
kwargs (Any) – additional params passed to
tf.keras.Model.predict`()
.
- Return type
-
classmethod
default_hyper_parameters
()[source]¶ The default hyper parameters of the model dict, all models must implement this function.
You could easily change model’s hyper-parameters.
For example, change the LSTM unit in BiLSTM_Model from 128 to 32.
>>> from kashgari.tasks.classification import BiLSTM_Model >>> hyper = BiLSTM_Model.default_hyper_parameters() >>> print(hyper) {'layer_bi_lstm': {'units': 128, 'return_sequences': False}, 'layer_output': {}} >>> hyper['layer_bi_lstm']['units'] = 32 >>> model = BiLSTM_Model(hyper_parameters=hyper)
-
evaluate
(x_data, y_data, batch_size=32, digits=4, truncating=False)¶ Build a text report showing the main labeling metrics.
- Parameters
- Returns
A report dict
- Return type
Dict
Example
>>> from kashgari.tasks.labeling import BiGRU_Model >>> model = BiGRU_Model() >>> model.fit(train_x, train_y, valid_x, valid_y) >>> report = model.evaluate(test_x, test_y) precision recall f1-score support ORG 0.0665 0.1108 0.0831 984 LOC 0.1870 0.2086 0.1972 1951 PER 0.1685 0.0882 0.1158 884 micro avg 0.1384 0.1555 0.1465 3819 macro avg 0.1516 0.1555 0.1490 3819 >>> print(report) { 'f1-score': 0.14895159934887792, 'precision': 0.1516294012813676, 'recall': 0.15553809897879026, 'support': 3819, 'detail': {'LOC': {'f1-score': 0.19718992248062014, 'precision': 0.18695452457510336, 'recall': 0.20861096873398258, 'support': 1951}, 'ORG': {'f1-score': 0.08307926829268293, 'precision': 0.06646341463414634, 'recall': 0.11077235772357724, 'support': 984}, 'PER': {'f1-score': 0.11581291759465479, 'precision': 0.16846652267818574, 'recall': 0.08823529411764706, 'support': 884}}, }
-
fit
(x_train, y_train, x_validate=None, y_validate=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data set list.
- Parameters
x_train (List[List[str]]) – Array of train feature data (if the model has a single input), or tuple of train feature data array (if the model has multiple inputs)
y_train (List[List[str]]) – Array of train label data
x_validate (List[List[str]]) – Array of validation feature data (if the model has a single input), or tuple of validation feature data array (if the model has multiple inputs)
y_validate (List[List[str]]) – Array of validation label data
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tensorflow.python.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See
tf.keras.callbacks
.fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
fit_generator
(train_sample_gen, valid_sample_gen=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data generator.
Data generator must be the subclass of CorpusGenerator
- Parameters
train_sample_gen (kashgari.generators.CorpusGenerator) – train data generator.
valid_sample_gen (kashgari.generators.CorpusGenerator) – valid data generator.
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tf.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks.
fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
classmethod
load_model
(model_path, custom_objects=None, encoding='utf-8')¶
-
predict
(x_data, *, batch_size=32, truncating=False, predict_kwargs=None)¶ Generates output predictions for the input samples.
Computation is done in batches.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
array(s) of predictions.
- Return type
List[List[str]]
-
predict_entities
(x_data, batch_size=32, join_chunk=' ', truncating=False, predict_kwargs=None)¶ Gets entities from sequence.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
join_chunk (str) – str or False,
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
list of entity.
- Return type
-
Bidirectional GRU CRF Model¶
-
class
kashgari.tasks.labeling.
BiGRU_CRF_Model
(embedding=None, sequence_length=None, hyper_parameters=None)[source]¶ Bases:
kashgari.tasks.labeling.abc_model.ABCLabelingModel
-
__init__
(embedding=None, sequence_length=None, hyper_parameters=None)¶
-
build_model
(x_data, y_data)¶ Build Model with x_data and y_data
- This function will setup a
CorpusGenerator
, then call
ABCClassificationModel.build_model_gen()
for preparing processor and model
Returns:
- This function will setup a
-
build_model_generator
(generators)¶ - Parameters
generators (List[kashgari.generators.CorpusGenerator]) –
- Return type
-
compile_model
(loss=None, optimizer=None, metrics=None, **kwargs)[source]¶ Configures the model for training. call
tf.keras.Model.predict()
to compile model with custom loss, optimizer and metricsExamples
>>> model = BiLSTM_Model() # Build model with corpus >>> model.build_model(train_x, train_y) # Compile model with custom loss, optimizer and metrics >>> model.compile(loss='categorical_crossentropy', optimizer='rsm', metrics = ['accuracy'])
- Parameters
loss (Any) – name of objective function, objective function or
tf.keras.losses.Loss
instance.optimizer (Any) – name of optimizer or optimizer instance.
metrics (object) – List of metrics to be evaluated by the model during training and testing.
kwargs (Any) – additional params passed to
tf.keras.Model.predict`()
.
- Return type
-
classmethod
default_hyper_parameters
()[source]¶ The default hyper parameters of the model dict, all models must implement this function.
You could easily change model’s hyper-parameters.
For example, change the LSTM unit in BiLSTM_Model from 128 to 32.
>>> from kashgari.tasks.classification import BiLSTM_Model >>> hyper = BiLSTM_Model.default_hyper_parameters() >>> print(hyper) {'layer_bi_lstm': {'units': 128, 'return_sequences': False}, 'layer_output': {}} >>> hyper['layer_bi_lstm']['units'] = 32 >>> model = BiLSTM_Model(hyper_parameters=hyper)
-
evaluate
(x_data, y_data, batch_size=32, digits=4, truncating=False)¶ Build a text report showing the main labeling metrics.
- Parameters
- Returns
A report dict
- Return type
Dict
Example
>>> from kashgari.tasks.labeling import BiGRU_Model >>> model = BiGRU_Model() >>> model.fit(train_x, train_y, valid_x, valid_y) >>> report = model.evaluate(test_x, test_y) precision recall f1-score support ORG 0.0665 0.1108 0.0831 984 LOC 0.1870 0.2086 0.1972 1951 PER 0.1685 0.0882 0.1158 884 micro avg 0.1384 0.1555 0.1465 3819 macro avg 0.1516 0.1555 0.1490 3819 >>> print(report) { 'f1-score': 0.14895159934887792, 'precision': 0.1516294012813676, 'recall': 0.15553809897879026, 'support': 3819, 'detail': {'LOC': {'f1-score': 0.19718992248062014, 'precision': 0.18695452457510336, 'recall': 0.20861096873398258, 'support': 1951}, 'ORG': {'f1-score': 0.08307926829268293, 'precision': 0.06646341463414634, 'recall': 0.11077235772357724, 'support': 984}, 'PER': {'f1-score': 0.11581291759465479, 'precision': 0.16846652267818574, 'recall': 0.08823529411764706, 'support': 884}}, }
-
fit
(x_train, y_train, x_validate=None, y_validate=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data set list.
- Parameters
x_train (List[List[str]]) – Array of train feature data (if the model has a single input), or tuple of train feature data array (if the model has multiple inputs)
y_train (List[List[str]]) – Array of train label data
x_validate (List[List[str]]) – Array of validation feature data (if the model has a single input), or tuple of validation feature data array (if the model has multiple inputs)
y_validate (List[List[str]]) – Array of validation label data
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tensorflow.python.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See
tf.keras.callbacks
.fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
fit_generator
(train_sample_gen, valid_sample_gen=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data generator.
Data generator must be the subclass of CorpusGenerator
- Parameters
train_sample_gen (kashgari.generators.CorpusGenerator) – train data generator.
valid_sample_gen (kashgari.generators.CorpusGenerator) – valid data generator.
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tf.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks.
fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
classmethod
load_model
(model_path, custom_objects=None, encoding='utf-8')¶
-
predict
(x_data, *, batch_size=32, truncating=False, predict_kwargs=None)¶ Generates output predictions for the input samples.
Computation is done in batches.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
array(s) of predictions.
- Return type
List[List[str]]
-
predict_entities
(x_data, batch_size=32, join_chunk=' ', truncating=False, predict_kwargs=None)¶ Gets entities from sequence.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
join_chunk (str) – str or False,
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
list of entity.
- Return type
-
Bidirectional CNN LSTM Model¶
-
class
kashgari.tasks.labeling.
CNN_LSTM_Model
(embedding=None, sequence_length=None, hyper_parameters=None)[source]¶ Bases:
kashgari.tasks.labeling.abc_model.ABCLabelingModel
-
__init__
(embedding=None, sequence_length=None, hyper_parameters=None)¶
-
build_model
(x_data, y_data)¶ Build Model with x_data and y_data
- This function will setup a
CorpusGenerator
, then call
ABCClassificationModel.build_model_gen()
for preparing processor and model
Returns:
- This function will setup a
-
build_model_generator
(generators)¶ - Parameters
generators (List[kashgari.generators.CorpusGenerator]) –
- Return type
-
compile_model
(loss=None, optimizer=None, metrics=None, **kwargs)¶ Configures the model for training. call
tf.keras.Model.predict()
to compile model with custom loss, optimizer and metricsExamples
>>> model = BiLSTM_Model() # Build model with corpus >>> model.build_model(train_x, train_y) # Compile model with custom loss, optimizer and metrics >>> model.compile(loss='categorical_crossentropy', optimizer='rsm', metrics = ['accuracy'])
- Parameters
loss (Any) – name of objective function, objective function or
tf.keras.losses.Loss
instance.optimizer (Any) – name of optimizer or optimizer instance.
metrics (object) – List of metrics to be evaluated by the model during training and testing.
kwargs (Any) – additional params passed to
tf.keras.Model.predict`()
.
- Return type
-
classmethod
default_hyper_parameters
()[source]¶ The default hyper parameters of the model dict, all models must implement this function.
You could easily change model’s hyper-parameters.
For example, change the LSTM unit in BiLSTM_Model from 128 to 32.
>>> from kashgari.tasks.classification import BiLSTM_Model >>> hyper = BiLSTM_Model.default_hyper_parameters() >>> print(hyper) {'layer_bi_lstm': {'units': 128, 'return_sequences': False}, 'layer_output': {}} >>> hyper['layer_bi_lstm']['units'] = 32 >>> model = BiLSTM_Model(hyper_parameters=hyper)
-
evaluate
(x_data, y_data, batch_size=32, digits=4, truncating=False)¶ Build a text report showing the main labeling metrics.
- Parameters
- Returns
A report dict
- Return type
Dict
Example
>>> from kashgari.tasks.labeling import BiGRU_Model >>> model = BiGRU_Model() >>> model.fit(train_x, train_y, valid_x, valid_y) >>> report = model.evaluate(test_x, test_y) precision recall f1-score support ORG 0.0665 0.1108 0.0831 984 LOC 0.1870 0.2086 0.1972 1951 PER 0.1685 0.0882 0.1158 884 micro avg 0.1384 0.1555 0.1465 3819 macro avg 0.1516 0.1555 0.1490 3819 >>> print(report) { 'f1-score': 0.14895159934887792, 'precision': 0.1516294012813676, 'recall': 0.15553809897879026, 'support': 3819, 'detail': {'LOC': {'f1-score': 0.19718992248062014, 'precision': 0.18695452457510336, 'recall': 0.20861096873398258, 'support': 1951}, 'ORG': {'f1-score': 0.08307926829268293, 'precision': 0.06646341463414634, 'recall': 0.11077235772357724, 'support': 984}, 'PER': {'f1-score': 0.11581291759465479, 'precision': 0.16846652267818574, 'recall': 0.08823529411764706, 'support': 884}}, }
-
fit
(x_train, y_train, x_validate=None, y_validate=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data set list.
- Parameters
x_train (List[List[str]]) – Array of train feature data (if the model has a single input), or tuple of train feature data array (if the model has multiple inputs)
y_train (List[List[str]]) – Array of train label data
x_validate (List[List[str]]) – Array of validation feature data (if the model has a single input), or tuple of validation feature data array (if the model has multiple inputs)
y_validate (List[List[str]]) – Array of validation label data
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tensorflow.python.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See
tf.keras.callbacks
.fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
fit_generator
(train_sample_gen, valid_sample_gen=None, batch_size=64, epochs=5, callbacks=None, fit_kwargs=None)¶ Trains the model for a given number of epochs with given data generator.
Data generator must be the subclass of CorpusGenerator
- Parameters
train_sample_gen (kashgari.generators.CorpusGenerator) – train data generator.
valid_sample_gen (kashgari.generators.CorpusGenerator) – valid data generator.
batch_size (int) – Number of samples per gradient update, default to 64.
epochs (int) – Number of epochs to train the model. An epoch is an iteration over the entire x and y data provided.
callbacks (List[tf.keras.callbacks.Callback]) – List of tf.keras.callbacks.Callback instances. List of callbacks to apply during training. See tf.keras.callbacks.
fit_kwargs (Dict) – fit_kwargs: additional arguments passed to
tf.keras.Model.fit()
- Returns
A
tf.keras.callback.History
object. Its History.history attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable).- Return type
tensorflow.python.keras.callbacks.History
-
classmethod
load_model
(model_path, custom_objects=None, encoding='utf-8')¶
-
predict
(x_data, *, batch_size=32, truncating=False, predict_kwargs=None)¶ Generates output predictions for the input samples.
Computation is done in batches.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
array(s) of predictions.
- Return type
List[List[str]]
-
predict_entities
(x_data, batch_size=32, join_chunk=' ', truncating=False, predict_kwargs=None)¶ Gets entities from sequence.
- Parameters
x_data (List[List[str]]) – The input data, as a Numpy array (or list of Numpy arrays if the model has multiple inputs).
batch_size (int) – Integer. If unspecified, it will default to 32.
truncating (bool) – remove values from sequences larger than model.embedding.sequence_length
join_chunk (str) – str or False,
predict_kwargs (Dict) – arguments passed to
tf.keras.Model.predict()
- Returns
list of entity.
- Return type
-