def init_od_vaegmm(state_dict: Dict, vaegmm: tf.keras.Model) -> OutlierVAEGMM:
"""
Initialize OutlierVAEGMM.
Parameters
----------
state_dict
Dictionary containing the parameter values.
vaegmm
Loaded VAEGMM.
Returns
-------
Initialized OutlierVAEGMM instance.
"""
od = OutlierVAEGMM(threshold=state_dict['threshold'],
vaegmm=vaegmm,
samples=state_dict['samples'])
od.phi = state_dict['phi']
od.mu = state_dict['mu']
od.cov = state_dict['cov']
od.L = state_dict['L']
od.log_det_cov = state_dict['log_det_cov']
if not all(
tf.is_tensor(_)
for _ in [od.phi, od.mu, od.cov, od.L, od.log_det_cov]):
logger.warning('Loaded VAEGMM detector has not been fit.')
return od
detector = [
AdversarialAE(threshold=threshold, model=model, **kwargs),
IForest(threshold=threshold),
Mahalanobis(threshold=threshold),
OutlierAEGMM(threshold=threshold,
gmm_density_net=gmm_density_net,
n_gmm=n_gmm,
**kwargs),
OutlierVAE(threshold=threshold,
latent_dim=latent_dim,
samples=samples,
**kwargs),
OutlierAE(threshold=threshold, **kwargs),
OutlierVAEGMM(threshold=threshold,
gmm_density_net=gmm_density_net,
n_gmm=n_gmm,
latent_dim=latent_dim,
samples=samples,
**kwargs),
OutlierProphet(threshold=.7, growth='logistic'),
SpectralResidual(threshold=threshold, window_amp=10, window_local=10),
OutlierSeq2Seq(input_dim,
seq_len,
threshold=threshold,
threshold_net=threshold_net,
latent_dim=latent_dim)
]
n_tests = len(detector)
@pytest.fixture
def select_detector(request):
def test_vaegmm(vaegmm_params):
# OutlierVAEGMM parameters
threshold, n_gmm, w_energy, w_recon, samples, threshold_perc, return_instance_score = vaegmm_params
# define encoder, decoder and GMM density net
encoder_net = tf.keras.Sequential([
InputLayer(input_shape=(input_dim, )),
Dense(128, activation=tf.nn.relu),
Dense(latent_dim, activation=None)
])
decoder_net = tf.keras.Sequential([
InputLayer(input_shape=(latent_dim, )),
Dense(128, activation=tf.nn.relu),
Dense(input_dim, activation=tf.nn.sigmoid)
])
gmm_density_net = tf.keras.Sequential([
InputLayer(input_shape=(latent_dim + 2, )),
Dense(10, activation=tf.nn.relu),
Dense(n_gmm, activation=tf.nn.softmax)
])
# init OutlierAEGMM
vaegmm = OutlierVAEGMM(threshold=threshold,
encoder_net=encoder_net,
decoder_net=decoder_net,
gmm_density_net=gmm_density_net,
n_gmm=n_gmm,
latent_dim=latent_dim,
samples=samples)
assert vaegmm.threshold == threshold
assert vaegmm.meta == {
'name': 'OutlierVAEGMM',
'detector_type': 'offline',
'data_type': None
}
# fit OutlierAEGMM, infer threshold and compute scores
vaegmm.fit(X,
w_recon=w_recon,
w_energy=w_energy,
epochs=5,
batch_size=1000,
verbose=False)
vaegmm.infer_threshold(X, threshold_perc=threshold_perc)
energy = vaegmm.score(X)
perc_score = 100 * (energy <
vaegmm.threshold).astype(int).sum() / energy.shape[0]
assert threshold_perc + 5 > perc_score > threshold_perc - 5
# make and check predictions
od_preds = vaegmm.predict(X, return_instance_score=return_instance_score)
assert od_preds['meta'] == vaegmm.meta
assert od_preds['data']['is_outlier'].shape == (X.shape[0], )
if return_instance_score:
assert od_preds['data']['is_outlier'].sum() == (
od_preds['data']['instance_score'] >
vaegmm.threshold).astype(int).sum()
else:
assert od_preds['data']['instance_score'] is None