The Geo Tag model transforms your textual location, latitude and longitude, or IP address into geographical coordinates that you can display in a map visualization widget.
Use map visualizations to zoom in on specific locations and gain contextual insights as you drill down to finer levels of detail in your data.
Why use Geo Tag?
While the Unsupervised NLU model allows you to map Geo fields, if your volume of data is too low, the Unsupervised NLU model may fail. The machine learning (ML) portion of that model requires a certain amount of data in order to converge. Geo Tag allows you to use maps even with limited data.
For more information about how to use the Geo Tag model in widgets, see the Map visualization article.
How much data is required for the Unsupervised NLU model varies depending on the data that you have. For example, if your documents are long, like news articles, then you would need fewer documents. However, if the documents are very short, it might still fail even with a lot of documents.
One Geo field is required. You can map it to any of the following geographic field types. If your geographic field contains multiple types, you can select General.
- IP Address
- Phone Number
The following geographical fields are absolute, so if you specify one of them, you do not specify country, city, or any other geographical information.
- Lat/Long field
- Long/Lat field
- one Latitude and one Longitude field
- IP address and phone number
Street, city, state, and country are not absolute, so map as much information as possible if your geographical data takes this form.
The model returns the following fields for use in widget visualizations.
- locations: Geographical locations that produce a map visualization grouped by country or state/province.
- coordinates: Latitudinal and longitudinal coordinates that produce a heat map visualization.
- postcode: A list of postal or ZIP codes. This field does not produce a map visualization.
- Data: A table containing all of the original data from the data stream, plus all of the analyzed data from the model.
To create a Geo tag analysis
The data stream to which you apply the model must include location, latitude and longitude, or IP address information.
Here are the steps to create the analysis from within a dashboard.
1. Open the dashboard to which you want to add the model.
2. Click the Data icon and in the Data Ingestion panel, click the vertical ellipsis for the data stream that you want to use and select Edit.
3. In the Edit Data Streams dialog that appears, above the Deployed Models list, click Deploy Model.
4. In the Deploy Model dialog that appears, scroll down to Basic Analyses and click Geo Tag.
5. In the Deploy a New Model wizard that appears, in the Unassigned Fields column, click the plus sign of the location field to use and click General (or another type of geographical information in the list) to add it to the Assigned fields column, then click Next.
6. On the Complete and Submit page of the dialog, optionally change the Name, add Tags, and specify a Description for the model. These fields appear on the tile for the model both in the dashboard, and in the Models page.
7. Optionally scroll down and expand the Advanced section to set the option described in the table below.
You can set the following properties in the Advanced section of the Create a new model or Deploy a new model dialog.
- Custom Filters: Define a custom data training filter to refine the data returned.