Feedback:

fit LocalOutlierFactor

Use the LocalOutlierFactor algorithm when you want to identify anomalous data points using the scikit-learn Local Outlier Factor (LOF).

Syntax

fit LocalOutlierFactor [option_name]=[value] <fields> [into <model name>]

[option_name]=[value]

Specify model parameters. The following model parameters are supported:

  • n_neighbors=<integer>

  • algorithm={'auto', 'ball_tree', 'kd_tree', 'brute'}

  • leaf_size=<integer>

  • metric=<string>

  • pfloat=<float>

  • contamination={auto|<float>}

  • novelty={true|false}

For information on the model parameters, refer to scikit learn documentation:

https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.LocalOutlierFactor.html

<fields> Specify input fields used to train the model.
into Specify the into keyword to store the learned model in an artifact that can later be applied to new search results with the apply operator.
'<model_name>'

Specify the name of the model to save as an artifact, so that it can be used with the apply operator. The model name must be wrapped with single or double straight quotation marks.

Usage

You can use the LocalOutlierFactor algorithm to identify anomalous data points using the scikit-learn Local Outlier Factor (LOF). This algorithm measures the local density deviation of a data point with respect to its neighbors. In other words, the algorithm assesses how isolated or different a data point is compared to its local neighborhood. The key idea is that outliers often have a significantly lower density of neighboring points than the majority of the data. LocalOutlierFactor performs one-shot learning and is limited to fitting on training data and returning outliers.

Examples

Example 1: Detect anomalies using LocalOutlierFactor.

Copy 
|fields petal_length, petal_width, sepal_length,
sepal_width, species <br />|fit LocalOutlierFactor petal_length
petal_width sepal_length sepal_width species

Example 2: Identify outliers in multivariate data.

Copy 
|fields petal_length, petal_width, sepal_length,
sepal_width, species <br />|fit LocalOutlierFactor n_neighbors=10
with_std=true petal_length petal_width sepal_length sepal_width species

Example 3: Score observations for anomaly detection.

Copy 
|fields petal_length, petal_width, sepal_length,
sepal_width, species <br />|fit LocalOutlierFactor novelty=true wit