berkaysynnada commented on code in PR #6982:
URL: https://github.com/apache/arrow-datafusion/pull/6982#discussion_r1268010003
##########
datafusion/physical-expr/src/intervals/interval_aritmetic.rs:
##########
@@ -451,6 +453,75 @@ impl Interval {
lower: IntervalBound::new(ScalarValue::Boolean(Some(true)), false),
upper: IntervalBound::new(ScalarValue::Boolean(Some(true)), false),
};
+
+ // Cardinality is the number of all points included by the interval,
considering its bounds.
+ pub fn cardinality(&self) -> Result<u64> {
+ match self.get_datatype() {
+ Ok(data_type) if data_type.is_integer() => {
+ if let Some(diff) =
self.upper.value.distance(&self.lower.value) {
+ Ok(calculate_cardinality_based_on_bounds(
+ self.lower.open,
+ self.upper.open,
+ diff as u64,
+ ))
+ } else {
+ Err(DataFusionError::Execution(format!(
+ "Cardinality cannot be calculated for {:?}",
+ self
+ )))
+ }
+ }
+ // Since the floating-point numbers are ordered in the same order
as their binary representation,
+ // we can consider their binary representations as "indices" and
subtract them.
+ //
https://stackoverflow.com/questions/8875064/how-many-distinct-floating-point-numbers-in-a-specific-range
+ Ok(data_type) if data_type.is_floating() => {
Review Comment:
ScalarValue's don't have it 😅
##########
datafusion/physical-expr/src/intervals/interval_aritmetic.rs:
##########
@@ -451,6 +453,75 @@ impl Interval {
lower: IntervalBound::new(ScalarValue::Boolean(Some(true)), false),
upper: IntervalBound::new(ScalarValue::Boolean(Some(true)), false),
};
+
+ // Cardinality is the number of all points included by the interval,
considering its bounds.
+ pub fn cardinality(&self) -> Result<u64> {
+ match self.get_datatype() {
+ Ok(data_type) if data_type.is_integer() => {
+ if let Some(diff) =
self.upper.value.distance(&self.lower.value) {
+ Ok(calculate_cardinality_based_on_bounds(
+ self.lower.open,
+ self.upper.open,
+ diff as u64,
+ ))
+ } else {
+ Err(DataFusionError::Execution(format!(
+ "Cardinality cannot be calculated for {:?}",
+ self
+ )))
+ }
+ }
+ // Since the floating-point numbers are ordered in the same order
as their binary representation,
+ // we can consider their binary representations as "indices" and
subtract them.
+ //
https://stackoverflow.com/questions/8875064/how-many-distinct-floating-point-numbers-in-a-specific-range
+ Ok(data_type) if data_type.is_floating() => {
Review Comment:
ScalarValue's don't have it 😅
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
