Value Classifications
How to classify values using Lume
Value Classifications
Value classifications allow you to map data values through classification, independent of the property names. For example, you may want to create the following value mapping:
Source Data
{
"size": "Small"
},
{
"size": "Medium"
},
{
"size": "Large"
}
Mapped Data
// The property name can be different or the same.
// Lume will do the property mappings and value mapping together, if applicable.
{
"product_size": "S"
},
{
"product_size": "M"
},
{
"product_size": "L"
}
How to classify values
To map values via classification, use the enum property in your pipeline’s target schema. Enums allow AI to classify data into your internal enum definitions.
For example, if your internal models work with product sizes as “S”, “M”, “L”, and you want all incoming data to map to one of these values, define the target property as shown below. Any source data provided will be classified into this enum if the AI successfully maps the property.
"product_size": {
"description": "The size of the shirt product",
"type": "string",
"enum": ["S", "M", "L"]
}
Classification rate limiting
Classification tasks require heavier AI compute and hit global rate limits faster. For each job, keep the number of classifications (calculated by number of records x number of enum target properties) below 500. For example, the above scenario triggers 3 classifications (3 records x 1 enum target property).
Editing Classifications
Users can now edit classifications and generated lookup tables via the API and the Lume Webapp. See Edit Mapper Guide to learn more.