Function calculate_selectivity

datafusion/physical-expr/src/analysis.rs:304–343

This function calculates the filter predicate's selectivity by comparing the initial and pruned column boundaries. Selectivity is defined as the ratio of rows in a table that satisfy the filter's predicate.

(
    target_boundaries: &[ExprBoundaries],
    initial_boundaries: &[ExprBoundaries],
)

/// the initial and pruned column boundaries. Selectivity is defined as the
/// ratio of rows in a table that satisfy the filter's predicate.
fn calculate_selectivity(
    target_boundaries: &[ExprBoundaries],
    initial_boundaries: &[ExprBoundaries],
) -> Result<f64> {
    // Since the intervals are assumed uniform and the values
    // are not correlated, we need to multiply the selectivities
    // of multiple columns to get the overall selectivity.
    if target_boundaries.len() != initial_boundaries.len() {
        return Err(internal_datafusion_err!(
            "The number of columns in the initial and target boundaries should be the same"
        ));
    }
    let mut acc: f64 = 1.0;
    for (initial, target) in initial_boundaries.iter().zip(target_boundaries) {
        match (initial.interval.as_ref(), target.interval.as_ref()) {
            (Some(initial_interval), Some(target_interval)) => {
                if let Precision::Exact(distinct_count)
                | Precision::Inexact(distinct_count) = target.distinct_count
                    && let Some(s) = singleton_selectivity(
                        initial_interval,
                        target_interval,
                        distinct_count,
                    )
                {
                    acc *= s;
                    continue;
                }
                acc *= cardinality_ratio(initial_interval, target_interval);
            }
            (None, Some(_)) => {
                return internal_err!(
                    "Initial boundary cannot be None while having a Some() target boundary"
                );
            }
            _ => return Ok(0.0),
        }
    }

    Ok(acc)
}

#[cfg(test)]
mod tests {