Hands-On Data Analysis with Pandas

Local outlier factor

The local outlier factor (LOF) algorithm scores all points based on the ratio of the density around each point to that of its nearest neighbors. Points that are considered normal will have similar densities to their neighbors; those with few others nearby will be considered abnormal.

More information on this algorithm can be found at https://scikit-learn.org/stable/modules/outlier_detection.html#local-outlier-factor.

Let's build another pipeline, but swap out the isolation forest for LOF:

>>> from sklearn.neighbors import LocalOutlierFactor>>> from sklearn.pipeline import Pipeline>>> from sklearn.preprocessing import StandardScaler>>> lof_pipeline = Pipeline([...     ('scale', StandardScaler()),...     ('lof', LocalOutlierFactor() ...