def init_od_iforest(state_dict: Dict) -> IForest:
"""
Initialize isolation forest.
Parameters
----------
state_dict
Dictionary containing the parameter values.
Returns
-------
Initialized IForest instance.
"""
od = IForest(threshold=state_dict['threshold'])
od.isolationforest = state_dict['isolationforest']
return od
def train_detector(data, preprocessor, perc_outlier=5):
"""Train outliers detector."""
print("Initialize outlier detector.")
od = IForest(threshold=None, n_estimators=100)
print("Training on normal data.")
np.random.seed(0)
normal_batch = create_outlier_batch(data.data,
data.target,
n_samples=30000,
perc_outlier=0)
X_train = normal_batch.data.astype('float')
# y_train = normal_batch.target
od.fit(preprocessor.transform(X_train))
print("Train on threshold data.")
np.random.seed(0)
threshold_batch = create_outlier_batch(data.data,
data.target,
n_samples=1000,
perc_outlier=perc_outlier)
X_threshold = threshold_batch.data.astype('float')
# y_threshold = threshold_batch.target
od.infer_threshold(preprocessor.transform(X_threshold),
threshold_perc=100 - perc_outlier)
return od
def test_isolation_forest(iforest_params):
threshold, threshold_perc, return_instance_score = iforest_params
X, y = load_iris(return_X_y=True)
iforest = IForest(threshold)
assert iforest.threshold == threshold
assert iforest.meta == {
'name': 'IForest',
'detector_type': 'offline',
'data_type': 'tabular'
}
iforest.fit(X)
iforest.infer_threshold(X, threshold_perc=threshold_perc)
iscore = iforest.score(X)
perc_score = 100 * (iscore <
iforest.threshold).astype(int).sum() / iscore.shape[0]
assert threshold_perc + 5 > perc_score > threshold_perc - 5
od_preds = iforest.predict(X, return_instance_score=return_instance_score)
assert od_preds['meta'] == iforest.meta
assert od_preds['data']['is_outlier'].sum() == (
iscore > iforest.threshold).astype(int).sum()
if not return_instance_score:
assert od_preds['data']['instance_score'] is None
Dense(n_gmm, activation=tf.nn.softmax)
])
threshold_net = tf.keras.Sequential([
InputLayer(input_shape=(seq_len, latent_dim)),
Dense(5, activation=tf.nn.relu)
])
# define model
inputs = tf.keras.Input(shape=(input_dim, ))
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,