Gender Classifier
Estimates the likelihood of a name historically being associated with men or women.
Estimates the likelihood of a name historically being associated with men or women.
Important
The Gender Classifier tool is deprecated and will no longer be supported. For tasks involving this tool in an existing pipeline, you will receive an alert to the deprecation, and the tool will be bypassed during future builds.
Input and output
To use this tool, you need a text column.
The tool adds two columns to your data: a binary gender estimate ("male" or "female") and a probability column. The probability columns shows the likelihood of the estimate being correct.
When to use this tool
You can use this tool when you need demographic information and have no other way to get that data. For example, let's say you want to use the Gender Pay app but don't have gender information in your data source. You can use this tool to get an approximate idea of gender distribution, which you can use to help you determine pay equity in your organization. Be careful when using this tool since it's only an estimate.
Tip
This training data used by this tool comes from these sources: Dbpedia Person Data (direct download); Popular baby names in the US; and Names data set curated by Milos Bejda. It was last updated with data from 2017. You could use the Text Classifier tool instead to train your own model to estimate this type of information using historic data that is more appropriate to your use case.
Usage example
In this example, we start with a data set that looks like this:
Name |
|---|
Liam Gonzalez |
Alejandro Hernandez |
Earl Cooley |
Isis Roberts |
Imogen Eaton |
Herbert Rees |
Ava-Rose Floyd |
George Carty |
Geoffrey Robinson |
Travis Stephenson |
After running the tool, there are two new columns in the data set:
Name | Gender | Probability |
|---|---|---|
Liam Gonzalez | Male | 0.984 215 795 993 804 9 |
Alejandro Hernandez | Male | 0.998 553 931 713 104 2 |
Earl Cooley | Male | 0.937 227 010 726 928 7 |
Isis Roberts | Female | 0.984 409 387 223 422 5 |
Imogen Eaton | Female | 0.808 390 051 126 480 1 |
Herbert Rees | Male | 0.999 955 415 725 708 |
Ava-Rose Floyd | Female | 0.999 999 992 828 745 3 |
George Carty | Male | 0.986 132 025 718 689 |
Geoffrey Robinson | Male | 0.997 940 957 546 234 1 |
Travis Stephenson | Male | 0.989 474 117 755 889 9 |
Configuration
Use the following configuration options to configure the Gender predictor tool.
Go to the Pipes module from the side navigation bar.
On the Pipes tab, find the pipe you want to work with. Click the pipe to open. For more information about pipes, see the Creating a pipe documentation.
In your Pipe builder, add your data source.
Click
+ Tool.In the Tools modal search bar, type Gender predictor.
Tip
You can also find the Predict Gender tool in the Learn section.
Click + Add tool.
Connect the tool to your data set.
In the configuration pane, enter the following information:
Table 67. Gender predictor configurationField
Description
Name
Select a text column to use from your data set.
New gender column
Enter the name for the new gender column.
New probability column
Enter the name for the new probability column.