src.classification.watch package

Submodules

src.classification.watch.dense_classifier module

This file implements a Fully Connected classifier for the watch data.

class src.classification.watch.dense_classifier.WatchDenseClassifier(parameters: Optional[Dict] = None)

Bases: WatchNNBaseClassifier

Classifier consisting of Dense layers only.

initialize_model(parameters: Dict) → None

Initializes a new and pretrained version of the Watch-Dense model

Parameters:

parameters – Parameters for initializing the model.

src.classification.watch.lstm_classifier module

This file implements an LSTM based classifier for the watch data.

class src.classification.watch.lstm_classifier.WatchLSTMClassifier(parameters: Optional[Dict] = None)

Bases: WatchNNBaseClassifier

Classifier that uses LSTM layers and a Dense head for classification.

initialize_model(parameters: Dict) → None

Initializes a new and pretrained version of the Watch-LSTM model

Parameters:

parameters – Parameters for initializing the model.

src.classification.watch.nn_classifier module

This file defines an interface for classifiers for the watch data.

class src.classification.watch.nn_classifier.WatchNNBaseClassifier(name: str, parameters: Optional[Dict] = None)

Bases: WatchEmotionClassifier

Base class for all NN classifiers in tensorflow for watch data.

classify(parameters: Optional[Dict] = None, **kwargs) → array

Classification method used to classify emotions from watch data

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

abstract initialize_model(parameters: Dict) → None

Abstract method that creates self.model, a tf Model instance

Parameters:

parameters – Parameters for initializing the model

load(parameters: Optional[Dict] = None, **kwargs) → None

Loading method that loads a previously trained model from disk.

Parameters:

• parameters – Parameters required for loading the model

• kwargs – Additional kwargs parameters

save(parameters: Optional[Dict] = None, **kwargs) → None

Saving method that saves a previously trained model on disk.

Parameters:

• parameters – Parameters required for storing the model

• kwargs – Additional kwargs parameters

train(parameters: Optional[Dict] = None, **kwargs) → None

Training method for tensorflow watch models

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

src.classification.watch.random_forest_classifier module

This file defines a Random Forest classifier for the watch data.

class src.classification.watch.random_forest_classifier.WatchRandomForestClassifier(parameters: Optional[Dict] = None)

Bases: WatchEmotionClassifier

Random Forest classifier for watch data.

classify(parameters: Optional[Dict] = None, **kwargs) → array

Classification method used to classify emotions from watch data

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

load(parameters: Optional[Dict] = None, **kwargs) → None

Loading method that loads a previously trained model from disk.

Parameters:

• parameters – Parameters required for loading the model

• kwargs – Additional kwargs parameters

save(parameters: Optional[Dict] = None, **kwargs) → None

Saving method that saves a previously trained model on disk.

Parameters:

• parameters – Parameters required for storing the model

• kwargs – Additional kwargs parameters

train(parameters: Optional[Dict] = None, **kwargs) → None

Training method for Random Forest classifier

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

src.classification.watch.transformer_classifier module

This file implements an LSTM based classifier for the watch data.

class src.classification.watch.transformer_classifier.WatchTransformerClassifier(parameters: Optional[Dict] = None)

Bases: WatchNNBaseClassifier

Classifier that uses Transformer layers and a Dense head for classification.

initialize_model(parameters: Dict) → None

Initializes a new and pretrained version of the Watch-Transformer model

Parameters:

parameters – Parameters for initializing the model.

src.classification.watch.watch_emotion_classifier module

Base class for all watch emotion classifiers

class src.classification.watch.watch_emotion_classifier.WatchEmotionClassifier(name: str = 'watch', parameters: Optional[Dict] = None)

Bases: EmotionClassifier

Base class for all watch emotion classifiers. Contains common functions that concerns all smartwatch classifiers.

abstract classify(parameters: Optional[Dict] = None, **kwargs) → array

The virtual classification method for interfacing

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

abstract load(parameters: Optional[Dict] = None, **kwargs) → None

Loading method that loads a previously trained model from disk.

Parameters:

• parameters – Parameters required for loading the model

• kwargs – Additional kwargs parameters

prepare_data(parameters: Dict) → None

Function that prepares speech datasets for training and stores them inside the class.

Parameters:

parameters – Parameter dictionary that contains important params. including: which_set, batch_size, weighted

prepare_training(parameters: Dict) → None

Function that prepares the training by initializing optimizer, loss, metrics and callbacks for training.

Parameters:

parameters – Training parameters

abstract save(parameters: Optional[Dict] = None, **kwargs) → None

Saving method that saves a previously trained model on disk.

Parameters:

• parameters – Parameters required for storing the model

• kwargs – Additional kwargs parameters

abstract train(parameters: Optional[Dict] = None, **kwargs) → None

Virtual training method for interfacing

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

src.classification.watch.xgboost_classifier module

This file defines a XGBOOST classifier for the watch data.

class src.classification.watch.xgboost_classifier.WatchXGBoostClassifier(parameters: Optional[Dict] = None)

Bases: WatchEmotionClassifier

XGBoost classifier for watch data.

classify(parameters: Optional[Dict] = None, **kwargs) → array

Classification method used to classify emotions from watch data

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

load(parameters: Optional[Dict] = None, **kwargs) → None

Loading method that loads a previously trained model from disk.

Parameters:

• parameters – Parameters required for loading the model

• kwargs – Additional kwargs parameters

save(parameters: Optional[Dict] = None, **kwargs) → None

Saving method that saves a previously trained model on disk.

Parameters:

• parameters – Parameters required for storing the model

• kwargs – Additional kwargs parameters

train(parameters: Optional[Dict] = None, **kwargs) → None

Training method for XGBoost classifier

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

Module contents

Package for smartwatch based emotion classifiers