Struct ObservationalData 

pub struct ObservationalData { /* private fields */ }

Container for observational (non-interventional) data.

Data is stored as a matrix: samples[i] is the i-th observation, with one entry per variable in the same order as variables.

Implementations

impl ObservationalData

pub fn new(variables: Vec<String>) -> Self

Create an empty dataset with the given variable names.

pub fn add_sample(&mut self, sample: Vec<f64>) -> Result<(), CausalError>

Add a single observation. Returns an error if the dimension does not match.

pub fn n_samples(&self) -> usize

Number of observations.

pub fn n_variables(&self) -> usize

Number of variables.

pub fn column(&self, var: &str) -> Option<Vec<f64>>

Extract all values for a single variable.

pub fn mean(&self, var: &str) -> Option<f64>

Compute the marginal mean of a variable.

pub fn conditional_mean( &self, outcome: &str, condition_var: &str, condition_val: f64, ) -> Option<f64>

Compute the mean of outcome conditioned on condition_var == condition_val.

Equality is checked with a small tolerance (1e-9) to handle floating-point values.

pub fn variables(&self) -> &[String]

Return a reference to the variable names.

pub fn samples(&self) -> &[Vec<f64>]

Return all samples as a slice of rows.

Trait Implementations

impl Clone for ObservationalData

fn clone(&self) -> ObservationalData

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ObservationalData

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

Formats the value using the given formatter.