Enum SamplingStrategy 

pub enum SamplingStrategy {
    None,
    Random {
        size: usize,
    },
    Reservoir {
        size: usize,
    },
    Stratified {
        key_columns: Vec<String>,
        samples_per_stratum: usize,
    },
    Progressive {
        initial_size: usize,
        confidence_level: f64,
        max_size: usize,
    },
    Systematic {
        interval: usize,
    },
    Importance {
        weight_threshold: f64,
    },
    MultiStage {
        stages: Vec<SamplingStrategy>,
    },
}

Variants

None

No sampling - analyze all data

Random

Simple random sampling with fixed size

Fields

size: usize

Reservoir

Reservoir sampling for streaming data

Fields

size: usize

Stratified

Stratified sampling balanced by categories

Fields

key_columns: Vec<String>

samples_per_stratum: usize

Progressive

Progressive sampling - stop when confidence is reached

Fields

initial_size: usize

confidence_level: f64

max_size: usize

Systematic

Systematic sampling (every Nth row)

Fields

interval: usize

Importance

Importance sampling for anomaly detection

Fields

weight_threshold: f64

MultiStage

Multi-stage sampling (combination of strategies)

Fields

stages: Vec<SamplingStrategy>

Implementations

impl SamplingStrategy

pub fn adaptive(total_rows: Option<usize>, file_size_mb: f64) -> Self

Create adaptive strategy based on data characteristics

pub fn stratified(key_columns: Vec<String>, samples_per_stratum: usize) -> Self

Create stratified sampling strategy

pub fn importance(weight_threshold: f64) -> Self

Create importance sampling strategy

pub fn should_include(&self, row_index: usize, total_processed: usize) -> bool

Check if row should be included in sample

pub fn should_include_with_state( &self, row_index: usize, total_processed: usize, state: &mut SamplingState, row_data: Option<&HashMap<String, String>>, ) -> bool

Check if row should be included with state tracking

pub fn target_sample_size(&self) -> Option<usize>

pub fn description(&self) -> String

Get description of the sampling strategy

Trait Implementations

impl Clone for SamplingStrategy

fn clone(&self) -> SamplingStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SamplingStrategy

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

Formats the value using the given formatter.