def test_ae(ae_params):
# OutlierAE parameters
threshold, threshold_perc, return_instance_score, return_feature_score, outlier_perc, outlier_type = ae_params
# define encoder and decoder
encoder_net = tf.keras.Sequential(
[
InputLayer(input_shape=(input_dim,)),
Dense(5, activation=tf.nn.relu),
Dense(encoding_dim, activation=None)
]
)
decoder_net = tf.keras.Sequential(
[
InputLayer(input_shape=(encoding_dim,)),
Dense(5, activation=tf.nn.relu),
Dense(input_dim, activation=tf.nn.sigmoid)
]
)
# init OutlierAE
ae = OutlierAE(
threshold=threshold,
encoder_net=encoder_net,
decoder_net=decoder_net
)
assert ae.threshold == threshold
assert ae.meta == {'name': 'OutlierAE', 'detector_type': 'offline', 'data_type': None, 'version': __version__}
# fit OutlierAE, infer threshold and compute scores
ae.fit(X, epochs=5, verbose=False)
ae.infer_threshold(X, threshold_perc=threshold_perc)
fscore, iscore = ae.score(X)
perc_score = 100 * (iscore < ae.threshold).astype(int).sum() / iscore.shape[0]
assert threshold_perc + 5 > perc_score > threshold_perc - 5
# make and check predictions
od_preds = ae.predict(X,
return_instance_score=return_instance_score,
return_feature_score=return_feature_score,
outlier_type=outlier_type,
outlier_perc=outlier_perc
)
assert od_preds['meta'] == ae.meta
if outlier_type == 'instance':
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']
> ae.threshold).astype(int).sum()
elif outlier_type == 'feature':
assert od_preds['data']['is_outlier'].shape == X.shape
if return_feature_score:
assert od_preds['data']['is_outlier'].sum() == (od_preds['data']['feature_score']
> ae.threshold).astype(int).sum()
if return_feature_score:
assert od_preds['data']['feature_score'].shape == X.shape
else:
assert od_preds['data']['feature_score'] is None
if return_instance_score:
assert od_preds['data']['instance_score'].shape == (X.shape[0],)
else:
assert od_preds['data']['instance_score'] is None
outputs = tf.keras.layers.Dense(2, activation=tf.nn.softmax)(inputs)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
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)
InputLayer(input_shape=(encoding_dim,)),
Dense(np.prod(dense_dim)),
Reshape(target_shape=dense_dim),
Conv2D(1024, 4, strides=2, padding='same', activation=tf.nn.relu),
Conv2D(512, 4, strides=2, padding='same', activation=tf.nn.relu),
Conv2DTranspose(256, 4, strides=2, padding='same', activation=tf.nn.relu),
Conv2DTranspose(64, 4, strides=2, padding='same', activation=tf.nn.relu),
Conv2DTranspose(3, 4, strides=2, padding='same', activation='sigmoid')
])
# In[32]:
od = OutlierAE( threshold = 0.01,
encoder_net=encoder_net,
decoder_net=decoder_net)
# In[33]:
adam = tf.keras.optimizers.Adam(lr=1e-4)
model = od.fit(train, epochs=100, verbose=True, optimizer = adam)
od.infer_threshold(test, threshold_perc=95)
preds = od.predict(test, outlier_type='instance',
return_instance_score=True,