Struct DataSketch 

pub struct DataSketch {
    pub sketch_type: SketchType,
    pub tdigests: HashMap<String, TDigest>,
    pub ddsketches: HashMap<String, DDSketch>,
    pub row_count: u64,
    pub source: Option<String>,
}

Serializable data sketch containing distribution summaries

Fields

sketch_type: SketchType

Sketch type used

tdigests: HashMap<String, TDigest>

Per-column T-Digest sketches

ddsketches: HashMap<String, DDSketch>

Per-column DDSketch sketches

row_count: u64

Total row count

source: Option<String>

Source identifier (e.g., node name)

Implementations

impl DataSketch

pub fn new(sketch_type: SketchType) -> Self

Create a new empty data sketch

pub fn with_source(self, source: impl Into<String>) -> Self

Set source identifier

pub fn from_dataset( dataset: &ArrowDataset, sketch_type: SketchType, ) -> Result<Self>

Create sketch from dataset

pub fn add_dataset(&mut self, dataset: &ArrowDataset) -> Result<()>

Add data from dataset to sketch

pub fn merge(sketches: &[Self]) -> Result<Self>

Merge multiple data sketches

pub fn quantile(&self, column: &str, q: f64) -> Option<f64>

Get quantile for a column

pub fn to_bytes(&self) -> Result<Vec<u8>>

Serialize to bytes

pub fn from_bytes(bytes: &[u8]) -> Result<Self>

Deserialize from bytes

Trait Implementations

impl Clone for DataSketch

fn clone(&self) -> DataSketch

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DataSketch

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DataSketch

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DataSketch

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.