Models¶

class best.sleep_classification.models.KDEBayesianCausalModel(*args, **kwargs)¶

fit(X, y)¶

scores(X)¶

class best.sleep_classification.models.KDEBayesianModel(fbands=[[0.5, 5], [4, 9], [8, 14], [11, 16], [14, 20], [20, 30]], segm_size=30, fs=200, bands_to_erase=[], filter_bands=True, nfft=12000, window_smooth_n=3, window_std=1, cat_bias={'AWAKE': 1, 'N2': 1, 'N3': 1, 'REM': 1}, Selector2=True)¶

extract_features(signal, return_names=False)¶

extract_features_bulk(list_of_signals, fsamp_list, return_names=False)¶

fit(X, y)¶

fit_transform(X, y)¶

predict(X)¶

predict_signal(signal, fs, datarate_threshold=0.85)¶

predict_signal_scores(signal, fs, datarate_threshold=0.85)¶

preprocess_signal(signal, fs, datarate_threshold=0.85)¶

scores(X)¶

transform(X)¶

class best.sleep_classification.models.KDEBayesianModelNC(fbands=[[0.5, 5], [4, 9], [8, 14], [11, 16], [14, 20], [20, 30]], segm_size=30, fs=200, bands_to_erase=[], filter_bands=True, filter_order=5001, nfft=12000, window_smooth_n=3, window_std=1, cat_bias={'AWAKE': 1, 'N2': 1, 'N3': 1, 'REM': 1}, Selector2=True)¶

extract_features(signal, return_names=False)¶

extract_features_bulk(list_of_signals, fsamp_list, return_names=False)¶

fit(X, y)¶

fit_transform(X, y)¶

predict(X)¶

predict_signal(signal, fs, datarate_threshold=0.85)¶

predict_signal_scores(signal, fs, datarate_threshold=0.85)¶

preprocess_signal(signal, fs, datarate_threshold=0.85)¶

scores(X)¶

transform(X)¶

class best.sleep_classification.models.MVGaussBayesianCausalModel(*args, **kwargs)¶

class best.sleep_classification.models.MVGaussBayesianModel(fbands=[[0.5, 5], [4, 9], [8, 14], [11, 16], [14, 20], [20, 30]], segm_size=30, fs=200, bands_to_erase=[], filter_bands=True, nfft=12000, window_smooth_n=3, window_std=1, cat_bias={'AWAKE': 1, 'N2': 1, 'N3': 1, 'REM': 1}, Selector2=True)¶

class best.sleep_classification.models.Mapper¶

create_template(x, y=None, name='Template')¶

fit_genetic(x, y=None, popsize=15)¶

fit_genetic_likelihood(x, y=None, popsize=15, model=None)¶

fit_map(x, y=None, bias={'REM': 2})¶

get_probabilities(x)¶

map(x, name, model=None)¶

class best.sleep_classification.models.MultiChannelMVGaussBayesClassifier(fbands=[[0.5, 5], [4, 9], [8, 14], [11, 16], [14, 20], [20, 30]], segm_size=30, fs=200, bands_to_erase=[], filter_bands=True, nfft=12000, window_smooth_n=3, window_std=1, cat_bias={'AWAKE': 1, 'N2': 1, 'N3': 1, 'REM': 1}, Selector2=True)¶

extract_features(signal, return_names=False)¶

extract_features_bulk(list_of_signals, fsamp_list, return_names=False)¶

fit(X, y)¶

fit_transform(X, y)¶

predict(X)¶

predict_signal(signal, fs, datarate_threshold=0.85)¶

predict_signal_scores(signal, fs, datarate_threshold=0.85)¶

preprocess_signal(signal, fs, datarate_threshold=0.85)¶

scores(X)¶

class best.sleep_classification.models.SleepClassifierWrapper¶

predict_signal(X, fs, stim_freq)¶

train(X, df)¶

class best.sleep_classification.models.SleepStageProbabilityMarkovChainFilter¶

correct_certainty(certainty: dict)¶

fit(scores, y)¶

fit_optimize(scores, y, Niter=200, popsize=10)¶

get_changing_state_posteriors(state, x_prob)¶

get_changing_state_priors(state)¶

get_changing_state_probabilities(state, x_prob)¶

get_prob_to_change(state, x_prob)¶

get_state_change_posterior(state, x_prob)¶

get_state_change_prior(state)¶

get_state_idx(state)¶

get_state_priors(state)¶

predict(scores, state='AWAKE')¶

remove_class(class_name)¶

reset_probabilities()¶

weight_probabilities(stability: numpy.ndarray)¶

class best.sleep_classification.models.SleepStructureClassifier(states=['WAKE', 'N1', 'N2', 'N3', 'REM'])¶

fit(x, y)¶

scores(x)¶