Documentation v1.0.0

---

Documentation / @openassistant/geoda / standardizeVariable

Variable: standardizeVariable

const standardizeVariable: OpenAssistantTool<StandardizeVariableToolArgs, StandardizeVariableToolLlmResult, StandardizeVariableToolAdditionalData, StandardizeVariableToolContext>

Defined in: src/variable/tool.ts:98

standardizeVariable Tool

This tool standardizes a variable using various statistical methods. Standardization transforms data to have a mean of 0 and standard deviation of 1, making different variables comparable.

Standardization Methods

The tool supports various standardization methods:

• deviationFromMean: Standardizes to mean=0, std=1 (most common)
• standardizeMAD: Uses median and MAD instead of mean and std
• rangeAdjust: Scales to range [0,1]
• rangeStandardize: Scales using interquartile range
• standardize: Z-score standardization

Parameters

• datasetName: Name of the dataset containing the variable
• variableName: Name of the variable to standardize
• standardizationMethod: Standardization method to use (see above)
• saveData: Whether to save the standardized values (optional)

Example user prompts:

• "Standardize the population variable using z-score method"
• "Normalize the income data using min-max scaling"
• "Apply robust standardization to the housing prices"

Example

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

const standardizeTool = {
  ...standardizeVariable,
  context: {
    getValues: async (datasetName: string, variableName: string) => {
      // Implementation to retrieve values from your data source
      return [100, 200, 150, 300, 250, 180, 220, 190, 280, 210];
    },
  },
};

const result = await generateText({
  model: openai('gpt-4.1', { apiKey: key }),
  prompt: 'Standardize the population variable using z-score method',
  tools: { standardizeVariable: convertToVercelAiTool(standardizeTool) },
});