Documentation v1.0.0

---

Documentation / @openassistant/geoda / rate

Variable: rate

const rate: OpenAssistantTool<RateFunctionArgs, RateLlmResult, RateAdditionalData, RateContext>

Defined in: src/rate/tool.ts:67

rate Tool

This tool calculates rates from a base variable and an event variable using various statistical methods. It's commonly used in epidemiology and spatial analysis to standardize rates across different populations.

Rate Methods

The rate calculation method can be one of the following types:

• Raw Rates: Simple division of events by base population
• Excess Risk: Measures excess risk compared to expected values
• Empirical Bayes: Uses Bayesian smoothing to stabilize rates
• Spatial Rates: Incorporates spatial information in rate calculation
• Spatial Empirical Bayes: Combines spatial and Bayesian smoothing
• EB Rate Standardization: Empirical Bayes with rate standardization

Parameters

• datasetName: Name of the dataset containing the variables
• baseVariableName: Name of the base population variable (denominator)
• eventVariableName: Name of the event variable (numerator)
• rateMethod: Rate calculation method (see above)
• weightsID: ID of spatial weights matrix (required for spatial methods)
• saveData: Whether to save the calculated rates (optional)
• outputRateVariableName: Custom name for the output rate variable (optional)

Example user prompts:

• "Calculate the excess risk rates from the base variable 'population' and the event variable 'crimes'"
• "Compute spatial empirical Bayes rates for disease incidence"
• "Calculate raw crime rates per capita"

Example

import { rate } from "@openassistant/geoda";
import { convertToVercelAiTool } from "@openassistant/utils";

const rateTool = {
  ...rate,
  context: {
    getValues: async (datasetName: string, variableName: string) => {
      // Implementation to retrieve values from your data source
      return [1000, 2000, 1500, 3000, 2500, 1800, 2200, 1900, 2800, 2100];
    },
  },
};

const result = await generateText({
  model: openai('gpt-4.1', { apiKey: key }),
  prompt: 'Calculate the excess risk rates from the base variable "population" and the event variable "crimes"',
  tools: { rate: convertToVercelAiTool(rateTool) },
});