Struct Evaluation 

pub struct Evaluation {
    pub labels: Summary,
    pub split: Split,
    pub numbers: Numbers,
    pub table: Meta,
    pub outside: BTreeMap<String, Numbers>,
    pub unseen: Option<Unseen>,
}

The table in place, tested on the newest 20 % of the corpus as it is now.

Fields

labels: Summary

split: Split

The test messages’ counts (train_* stay 0).

numbers: Numbers

table: Meta

When the table was trained (Unix seconds), and on how much.

outside: BTreeMap<String, Numbers>

Each outside source’s newest 20 %, the baseline, apart.

unseen: Option<Unseen>

The test messages that came after the table was trained: it never learned from them. The table a training writes learned from every message before it, the newest fifth included: on the others, it is judged on what it was taught. None when none came since.

Trait Implementations

impl Clone for Evaluation

fn clone(&self) -> Evaluation

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Evaluation

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

Formats the value using the given formatter.

impl PartialEq for Evaluation

fn eq(&self, other: &Evaluation) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for Evaluation