How deeply does Outlier Detection in Python cover one-dimensional outlier?

Defines column-wise unusualness and its limitation, but does not provide a general statistical scoring procedure.

One-dimensional outlier

As explained in Outlier Detection in Python

A univariate outlier is a data item with a value that is unusual when considered individually.

A one-dimensional outlier is a value that is unusual within its own column, considered independently of every other column. In numeric data, it is often unusually large or small. section 2.1

Use the distinction between single-value and combination-based unusualness:

A row can be flagged because it contains one or more one-dimensional outlier values. section 2.3.1
A one-dimensional check does not detect a combination that is ordinary in every individual feature but rare jointly; that requires multivariate analysis. section 2.3
Interpret flagged values cautiously: they may be errors, meaningful rare cases, or irrelevant to the investigation. section 8.3

Expense amounts

In an expense table, an Amount value of 643.99 may be unusual relative to the other amounts in that column. The row can therefore be flagged for containing a one-dimensional outlier, even before considering its account, time, or department. section 2.1 section 2.3

Table 2.2 Staff expenses (view table figure)

Row	Staff ID	Department	Account	Date of expense	Date submitted	Time submitted	Amount
1	9000483	Sales	Meals	02/03/2023	02/03/2023	09:10:21	12.44
2	9303332	Marketing	Travel	02/03/2023	02/03/2023	10:43:35	41.90
3	9847421	Engineering	Meals	02/03/2023	02/03/2023	10:56:04	643.99
4	9303332	Marketing	Supplies	02/03/2023	02/03/2023	21:12:09	212.00

Inspect the staff-expense table to compare an unusual amount with the other row features that may support multivariate analysis. section 2.3

How Outlier Detection in Python covers it

liveBook manning.com

Read Outlier Detection in Python on liveBook Get the book at manning.com

Related concepts

anomalykind of · An anomaly is an observation, behavior, or state that deviates from an expected or typical pattern or condition.
equal-width binningused by · Equal-width binning is a discretization technique that partitions a numerical range into intervals of identical width.
multivariate outliercontrasts with · A multivariate outlier is an observation whose unusualness depends on a combination of multiple feature values.
rare combinationcontrasts with · A rare combination is a combination of feature values that occurs relatively few times in a dataset.
signaluses · A signal is an observable value, event, or pattern that conveys information about a condition, state, or phenomenon.
quantitative datauses · Quantitative data is information represented numerically as quantities, measurements, counts, or other values suitable for numerical interpretation or analysis.

This explainer was generated by Manning's knowledge graph from the text of Outlier Detection in Python. The section links point to the parts of the book it draws on.