Skip to content

Remove unused update and merge implementations from Aggregates and supporting ScalarValue arithmetic #1550

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
Dandandan merged 2 commits into from
Jan 13, 2022
Merged

Remove unused update and merge implementations from Aggregates and supporting ScalarValue arithmetic #1550

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
23551d6
Remove Scalar::{add,mul,div}
alamb Jan 11, 2022
dac0e03
fixups
alamb Jan 11, 2022
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
23 changes: 4 additions & 19 deletions datafusion/src/physical_plan/expressions/average.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,13 +171,8 @@ impl Accumulator for AvgAccumulator {
Ok(vec![ScalarValue::from(self.count), self.sum.clone()])
}

fn update(&mut self, values: &[ScalarValue]) -> Result<()> {
let values = &values[0];

self.count += (!values.is_null()) as u64;
self.sum = sum::sum(&self.sum, values)?;

Ok(())
fn update(&mut self, _values: &[ScalarValue]) -> Result<()> {
unimplemented!("update_batch is implemented instead");
}

fn update_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
Expand All @@ -188,18 +183,8 @@ impl Accumulator for AvgAccumulator {
Ok(())
}

fn merge(&mut self, states: &[ScalarValue]) -> Result<()> {
let count = &states[0];
// counts are summed
if let ScalarValue::UInt64(Some(c)) = count {
self.count += c
} else {
unreachable!()
};

// sums are summed
self.sum = sum::sum(&self.sum, &states[1])?;
Ok(())
fn merge(&mut self, _states: &[ScalarValue]) -> Result<()> {
unimplemented!("merge_batch is implemented instead");
}

fn merge_batch(&mut self, states: &[ArrayRef]) -> Result<()> {
Expand Down
18 changes: 4 additions & 14 deletions datafusion/src/physical_plan/expressions/count.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,22 +112,12 @@ impl Accumulator for CountAccumulator {
Ok(())
}

fn update(&mut self, values: &[ScalarValue]) -> Result<()> {
let value = &values[0];
if !value.is_null() {
self.count += 1;
}
Ok(())
fn update(&mut self, _values: &[ScalarValue]) -> Result<()> {
unimplemented!("update_batch is implemented instead");
}

fn merge(&mut self, states: &[ScalarValue]) -> Result<()> {
let count = &states[0];
if let ScalarValue::UInt64(Some(delta)) = count {
self.count += *delta;
} else {
unreachable!()
}
Ok(())
fn merge(&mut self, _states: &[ScalarValue]) -> Result<()> {
unimplemented!("merge_batch is implemented instead");
}

fn merge_batch(&mut self, states: &[ArrayRef]) -> Result<()> {
Expand Down
11 changes: 4 additions & 7 deletions datafusion/src/physical_plan/expressions/sum.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,10 +353,8 @@ impl Accumulator for SumAccumulator {
Ok(vec![self.sum.clone()])
}

fn update(&mut self, values: &[ScalarValue]) -> Result<()> {
// sum(v1, v2, v3) = v1 + v2 + v3
self.sum = sum(&self.sum, &values[0])?;
Ok(())
fn update(&mut self, _values: &[ScalarValue]) -> Result<()> {
unimplemented!("update_batch is implemented instead");
}

fn update_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
Expand All @@ -365,9 +363,8 @@ impl Accumulator for SumAccumulator {
Ok(())
}

fn merge(&mut self, states: &[ScalarValue]) -> Result<()> {
// sum(sum1, sum2) = sum1 + sum2
self.update(states)
fn merge(&mut self, _states: &[ScalarValue]) -> Result<()> {
unimplemented!("merge_batch is implemented instead");
}

fn merge_batch(&mut self, states: &[ArrayRef]) -> Result<()> {
Expand Down
118 changes: 4 additions & 114 deletions datafusion/src/physical_plan/expressions/variance.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,122 +302,12 @@ impl Accumulator for VarianceAccumulator {
Ok(())
}

fn update(&mut self, values: &[ScalarValue]) -> Result<()> {
let values = &values[0];
let is_empty = values.is_null();
let mean = ScalarValue::from(self.mean);
let m2 = ScalarValue::from(self.m2);

if !is_empty {
let new_count = self.count + 1;
let delta1 = ScalarValue::add(values, &mean.arithmetic_negate())?;
let new_mean = ScalarValue::add(
&ScalarValue::div(&delta1, &ScalarValue::from(new_count as f64))?,
&mean,
)?;
let delta2 = ScalarValue::add(values, &new_mean.arithmetic_negate())?;
let tmp = ScalarValue::mul(&delta1, &delta2)?;

let new_m2 = ScalarValue::add(&m2, &tmp)?;
self.count += 1;

if let ScalarValue::Float64(Some(c)) = new_mean {
self.mean = c;
} else {
unreachable!()
};
if let ScalarValue::Float64(Some(m)) = new_m2 {
self.m2 = m;
} else {
unreachable!()
};
}

Ok(())
fn update(&mut self, _values: &[ScalarValue]) -> Result<()> {
unimplemented!("update_batch is implemented instead");
}

fn merge(&mut self, states: &[ScalarValue]) -> Result<()> {
let count;
let mean;
let m2;
let mut new_count: u64 = self.count;

if let ScalarValue::UInt64(Some(c)) = states[0] {
count = c;
} else {
unreachable!()
};

if count == 0_u64 {
return Ok(());
}

if let ScalarValue::Float64(Some(m)) = states[1] {
mean = m;
} else {
unreachable!()
};
if let ScalarValue::Float64(Some(n)) = states[2] {
m2 = n;
} else {
unreachable!()
};

if self.count == 0 {
self.count = count;
self.mean = mean;
self.m2 = m2;
return Ok(());
}

new_count += count;

let mean1 = ScalarValue::from(self.mean);
let mean2 = ScalarValue::from(mean);

let new_mean = ScalarValue::add(
&ScalarValue::div(
&ScalarValue::mul(&mean1, &ScalarValue::from(self.count))?,
&ScalarValue::from(new_count as f64),
)?,
&ScalarValue::div(
&ScalarValue::mul(&mean2, &ScalarValue::from(count))?,
&ScalarValue::from(new_count as f64),
)?,
)?;

let delta = ScalarValue::add(&mean2.arithmetic_negate(), &mean1)?;
let delta_sqrt = ScalarValue::mul(&delta, &delta)?;
let new_m2 = ScalarValue::add(
&ScalarValue::add(
&ScalarValue::mul(
&delta_sqrt,
&ScalarValue::div(
&ScalarValue::mul(
&ScalarValue::from(self.count),
&ScalarValue::from(count),
)?,
&ScalarValue::from(new_count as f64),
)?,
)?,
&ScalarValue::from(self.m2),
)?,
&ScalarValue::from(m2),
)?;

self.count = new_count;
if let ScalarValue::Float64(Some(c)) = new_mean {
self.mean = c;
} else {
unreachable!()
};
if let ScalarValue::Float64(Some(m)) = new_m2 {
self.m2 = m;
} else {
unreachable!()
};

Ok(())
fn merge(&mut self, _states: &[ScalarValue]) -> Result<()> {
unimplemented!("merge_batch is implemented instead");
}

fn evaluate(&self) -> Result<ScalarValue> {
Expand Down
Loading