> ## Documentation Index
> Fetch the complete documentation index at: https://kumo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# COUNT_DISTINCT

#### `COUNT_DISTINCT(<table>.<column>, <start>, <end>, <unit>)`

## Description

Calculates the cardinality/count of distinct values in the specified `<table>.<column>` column starting from `<start>` days to `<end>` days. When used in the target field, the time period should be positive (in the future). When used in a temporal filter field, the time period should be negative (in the past).

This operator can be applied to columns of any type.

### Example

<CodeGroup>
  ```Text PQL theme={null}
  COUNT_DISTINCT(LOAN.AMOUNT, 0, 30)
  ```
</CodeGroup>

### Training Considerations

* Kumo runs your pQuery over many historic slices of data and across all entities that meet your filter criteria to generate training examples.
* If for a given entity and historic data slice there are no fact rows to aggregate over, the training example label is set to the value 0.
* For all aggregations, the start time is **excluded** from the calculation and the end time is **included** in the calculation.
* The units for the start and end times is `days` by default but can be specified as `months` or `hours`.