Skip to content

Update variance/stddev to work with single values #4847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
alamb merged 4 commits into from
Jan 8, 2023
Merged

Update variance/stddev to work with single values #4847

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ea06312
Update variance/stddev to work with single values
jonmmease Jan 7, 2023
319a115
Fix tests
jonmmease Jan 7, 2023
bc65eeb
matches! to if let
jonmmease Jan 7, 2023
6f7d67e
fix test_stddev_1_input test
jonmmease Jan 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions datafusion/core/tests/sqllogictests/test_files/aggregate.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1091,3 +1091,15 @@ query U
SELECT ARRAY_AGG([1]);
----
[[1]]

# variance_single_value
query RRRR
select var(sq.column1), var_pop(sq.column1), stddev(sq.column1), stddev_pop(sq.column1) from (values (1.0)) as sq;
----
NULL 0 NULL 0

# variance_two_values
query RRRR
select var(sq.column1), var_pop(sq.column1), stddev(sq.column1), stddev_pop(sq.column1) from (values (1.0), (3.0)) as sq;
----
2 1 1.4142135623730951 1
9 changes: 4 additions & 5 deletions datafusion/physical-expr/src/aggregate/stddev.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,8 +307,8 @@ mod tests {
"bla".to_string(),
DataType::Float64,
));
let actual = aggregate(&batch, agg);
assert!(actual.is_err());
let actual = aggregate(&batch, agg).unwrap();
assert_eq!(actual, ScalarValue::Float64(None));

Ok(())
}
Expand Down Expand Up @@ -341,9 +341,8 @@ mod tests {
"bla".to_string(),
DataType::Float64,
));
let actual = aggregate(&batch, agg);
assert!(actual.is_err());

let actual = aggregate(&batch, agg).unwrap();
assert_eq!(actual, ScalarValue::Float64(None));
Ok(())
}

Expand Down
30 changes: 15 additions & 15 deletions datafusion/physical-expr/src/aggregate/variance.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,17 +286,17 @@ impl Accumulator for VarianceAccumulator {
}
};

if count <= 1 {
return Err(DataFusionError::Internal(
"At least two values are needed to calculate variance".to_string(),
));
}

if self.count == 0 {
Ok(ScalarValue::Float64(None))
} else {
Ok(ScalarValue::Float64(Some(self.m2 / count as f64)))
}
Ok(ScalarValue::Float64(match self.count {
0 => None,
1 => {
if let StatsType::Population = self.stats_type {
Some(0.0)
} else {
None
}
}
_ => Some(self.m2 / count as f64),
}))
}

fn size(&self) -> usize {
Expand Down Expand Up @@ -382,8 +382,8 @@ mod tests {
"bla".to_string(),
DataType::Float64,
));
let actual = aggregate(&batch, agg);
assert!(actual.is_err());
let actual = aggregate(&batch, agg).unwrap();
assert_eq!(actual, ScalarValue::Float64(None));

Ok(())
}
Expand Down Expand Up @@ -416,8 +416,8 @@ mod tests {
"bla".to_string(),
DataType::Float64,
));
let actual = aggregate(&batch, agg);
assert!(actual.is_err());
let actual = aggregate(&batch, agg).unwrap();
assert_eq!(actual, ScalarValue::Float64(None));

Ok(())
}
Expand Down