Coerce objects to exponential fits

This is used to sanitize input for pb210_cic() and pb210_crs(), where fit objects are required but where it is anticipated that numeric constants will be common as input.

pb210_as_fit(x, ...)

# S3 method for default
pb210_as_fit(x, ...)

# S3 method for numeric
pb210_as_fit(x, ...)

pb210_fit_lazy(x)

# S3 method for `function`
pb210_as_fit(x, ...)

# S3 method for formula
pb210_as_fit(x, ...)

# S3 method for pb210_fit_lazy
pb210_as_fit(x, data = NULL, ...)

Arguments

x	An object
...	Unused.
data	For lazy fits, this object is a tibble with cumulative_dry_mass and excess.

Value

An object with a stats::predict() method.

Examples

fake_depth <- 0:10
fake_pb210 <- exp(5 - fake_depth) + rnorm(11, sd = 0.005)

pb210_as_fit(pb210_fit_exponential(fake_depth, fake_pb210))
#> Nonlinear regression model
#>   model: y ~ exp(m * x + b)
#>    data: data
#>  b  m 
#>  5 -1 
#>  residual sum-of-squares: 0.0002726
#> 
#> Number of iterations to convergence: 3 
#> Achieved convergence tolerance: 5.184e-07
pb210_as_fit(1)
#> $coef
#> b m 
#> 0 0 
#> 
#> attr(,"class")
#> [1] "exponential_manual"
pb210_as_fit(0)
#> $coef
#>    b    m 
#> -Inf    1 
#> 
#> attr(,"class")
#> [1] "exponential_manual"