implement more trending_model_fit accessors

[TimTaylor]

No description provided.

[thibautjombart]

library(trending)
x = rnorm(100, mean = 0)
y = rpois(n = 100, lambda = exp(1.5 + 0.5*x))
dat <- data.frame(x = x, y = y)

poisson_model <- glm_model(y ~ x , family = "poisson")

get_formula(poisson_model) # works
#> y ~ x
get_response(poisson_model) # works
#> [1] "y"

f <- fit(poisson_model, dat)

get_model(f) # works
#> 
#> Call:  glm(formula = y ~ x, family = "poisson", data = data)
#> 
#> Coefficients:
#> (Intercept)            x  
#>      1.5167       0.5064  
#> 
#> Degrees of Freedom: 99 Total (i.e. Null);  98 Residual
#> Null Deviance:       237.5 
#> Residual Deviance: 104.7     AIC: 426.2
get_formula(f) # missing
#> Error in UseMethod("get_formula", x): no applicable method for 'get_formula' applied to an object of class "c('trending_model_fit', 'list')"
get_response(f) # missing
#> Error in UseMethod("get_response", x): no applicable method for 'get_response' applied to an object of class "c('trending_model_fit', 'list')"

^{Created on 2021-02-22 by the reprex package (v1.0.0)}