Trait linfa::metrics::MultiTargetRegression [−][src]
pub trait MultiTargetRegression<F: Float, T: AsTargets<Elem = F>>: AsTargets<Elem = F> {
fn max_error(&self, other: &T) -> Result<Array1<F>> { ... }
fn mean_absolute_error(&self, other: &T) -> Result<Array1<F>> { ... }
fn mean_squared_error(&self, other: &T) -> Result<Array1<F>> { ... }
fn mean_squared_log_error(&self, other: &T) -> Result<Array1<F>> { ... }
fn median_absolute_error(&self, other: &T) -> Result<Array1<F>> { ... }
fn r2(&self, other: &T) -> Result<Array1<F>> { ... }
fn explained_variance(&self, other: &T) -> Result<Array1<F>> { ... }
}
Expand description
Regression metrices trait for multiple targets.
It is possible to compute the listed mectrics between:
- bi-dimensional array - bi-dimensional array
- bi-dimensional array - dataset
- dataset - dataset
- dataset - one-dimensional array
- dataset - bi-dimensional array
The shape of the compared targets must match.
To compare single-dimensional arrays use SingleTargetRegression
Provided methods
Maximal error between two continuous variables
fn mean_absolute_error(&self, other: &T) -> Result<Array1<F>>
fn mean_absolute_error(&self, other: &T) -> Result<Array1<F>>
Mean error between two continuous variables
fn mean_squared_error(&self, other: &T) -> Result<Array1<F>>
fn mean_squared_error(&self, other: &T) -> Result<Array1<F>>
Mean squared error between two continuous variables
fn mean_squared_log_error(&self, other: &T) -> Result<Array1<F>>
fn mean_squared_log_error(&self, other: &T) -> Result<Array1<F>>
Mean squared log error between two continuous variables
fn median_absolute_error(&self, other: &T) -> Result<Array1<F>>
fn median_absolute_error(&self, other: &T) -> Result<Array1<F>>
Median absolute error between two continuous variables
R squared coefficient, is the proportion of the variance in the dependent variable that is predictable from the independent variable
fn explained_variance(&self, other: &T) -> Result<Array1<F>>
fn explained_variance(&self, other: &T) -> Result<Array1<F>>
Same as R-Squared but with biased variance