metrax.RMSLE

class metrax.RMSLE(total: Array, count: Array)

Bases: MSLE

Computes the root mean squared logarithmic error for regression problems given predictions and labels.

The root mean squared logarithmic error is defined as:

\[RMSLE = \sqrt{\frac{1}{N} \sum_{i=1}^{N} (ln(y_i + 1) - ln(\hat{y}_i + 1))^2 }\]

where:

• \(y_i\) are true values

• \(\hat{y}_i\) are predictions

• \(N\) is the number of samples

__init__(total: Array, count: Array) → None

Methods

__init__(total, count)
compute()	Computes final metrics from intermediate values.
compute_value()	Wraps compute() and returns a values.Value.
empty()	Returns an empty instance (i.e. .merge(Metric.empty()) is a no-op).
from_fun(fun)	Calls cls.from_model_output with the return value from fun.
from_model_output(predictions, labels[, ...])	Updates the metric.
from_output(name)	Calls cls.from_model_output with model output named name.
merge(other)	Returns Metric that is the accumulation of self and other.
reduce()	Reduces the metric along it first axis by calling _reduce_merge().
replace(**updates)	Returns a new object replacing the specified fields with new values.

Attributes

total
count

compute() → Array

Computes final metrics from intermediate values.

__init__(total: Array, count: Array) → None

replace(**updates)

Returns a new object replacing the specified fields with new values.