WOLFRAM

Wolfram Language & System Documentation Center

"NameAge" (Built-in Predictor)

Predict the age of a person in years, given their first name.

Classes

  • This classifier is based on the US census data. It will give poor performances for names that are rare in the US.

Examples

open all close all

Basic Examples  (2)

Use the built-in predictor "NameAge" to predict the age of a person from their first name:

Wolfram Language code: Predict["NameAge", "Tom"]

Obtain a PredictorFunction for this predictor:

Wolfram Language code: p = Predict["NameAge"]

Use the predictor function to predict the age of a person from their first name:

Wolfram Language code: p["Stacy"]

Predict many examples at once:

Wolfram Language code: p[ {"Tom", "Stacy", "Claire"}]

Scope  (2)

Visualize the distribution of the age for a given name:

Wolfram Language code: distribution = Predict["NameAge", "Claire", "Distribution"]
Wolfram Language code: Plot[PDF[distribution, x], {x, 0, 100}, Exclusions -> None, PlotRange -> All]

The most likely value of this distribution is the following:

Wolfram Language code: Predict["NameAge", "Claire"]

Load the PredictorFunction corresponding to the built-in predictor:

Wolfram Language code: p = Predict["NameAge"]

Obtain information about the predictor from Information:

Wolfram Language code: Information[p]

Options  (2)

IndeterminateThreshold  (1)

Use a custom IndeterminateThreshold after loading the PredictorFunction:

Wolfram Language code: p = Predict["NameAge"]
Wolfram Language code: p["Stacy", IndeterminateThreshold -> 0.6]

Update the value of the threshold in the predictor:

Wolfram Language code: p["Stacy", IndeterminateThreshold -> 0]

UtilityFunction  (1)

Obtain the utility function of the predictor that corresponds to a DiracDelta function:

Wolfram Language code: utility = Information[Predict["NameAge"], "UtilityFunction"]

This means by default, the value with the highest probability density is predicted:

Wolfram Language code: Predict["NameAge", "Claire"]

Change the utility function to predict the mean value instead of the most likely value:

Wolfram Language code: Predict["NameAge", "Claire", UtilityFunction -> Function[-(#2 - #1) ^ 2], IndeterminateThreshold -> 0]