Alter Fit Convention - Githubissues

vc1492a / PyNomaly

Anomaly detection using LoOP: Local Outlier Probabilities, a local density based outlier detection method providing an outlier score in the range of [0,1].

Other

305 stars 36 forks source link

Alter Fit Convention #7

Open vc1492a opened 6 years ago

vc1492a commented 6 years ago

Provide parameters in LocalOutlierProbability() and provide data in fit() as opposed to providing data in LocalOutlierProbability() along with params. This is s.t. PyNomaly is more in line with scikit-learn and other popular libraries.

vc1492a commented 4 years ago

More specifically and as an update, the following parameters could stay in the LocalOutlierProbability() method:

extent
n_neighbors

And any data-related parameters that may change from execution to execution (such in the case of inference) could instead be passed to the fit() method:

data
distance_matrix
neighbor_matrix
use_numba
progress_bar

vc1492a commented 3 years ago

See NetworkX implementation.