wrong structure for logistic regression confidence intervals #156
Description
library(tidymodels)
#> ── Attaching packages ───────────────────────────────────────────────────────────────── tidymodels 0.0.2 ──
#> ✔ broom 0.5.1 ✔ purrr 0.3.0
#> ✔ dials 0.0.2 ✔ recipes 0.1.4
#> ✔ dplyr 0.8.0.1 ✔ rsample 0.0.4
#> ✔ ggplot2 3.1.0 ✔ tibble 2.0.1
#> ✔ infer 0.4.0 ✔ yardstick 0.0.2
#> ✔ parsnip 0.0.1.9000
#> ── Conflicts ──────────────────────────────────────────────────────────────────── tidymodels_conflicts() ──
#> ✖ purrr::discard() masks scales::discard()
#> ✖ dplyr::filter() masks stats::filter()
#> ✖ dplyr::lag() masks stats::lag()
#> ✖ recipes::step() masks stats::step()
data("lending_club")
lending_club <-
lending_club %>%
slice(1:200)
log_reg <-
logistic_reg() %>%
set_engine("glm") %>%
fit(Class ~ log(funded_amnt) + int_rate, data = lending_club)
predict(log_reg, lending_club %>% slice(1:7) %>% dplyr::select(-Class), type = "prob")
#> # A tibble: 7 x 2
#> .pred_bad .pred_good
#> <dbl> <dbl>
#> 1 0.0511 0.949
#> 2 0.0706 0.929
#> 3 0.0500 0.950
#> 4 0.0499 0.950
#> 5 0.00185 0.998
#> 6 0.0166 0.983
#> 7 0.00441 0.996
predict(log_reg, lending_club %>% slice(1:7) %>% dplyr::select(-Class), type = "conf_int")
#> # A tibble: 7 x 2
#> .pred_lower .pred_upper
#> <dbl> <dbl>
#> 1 0.896 0.976
#> 2 0.813 0.975
#> 3 0.883 0.980
#> 4 0.897 0.976
#> 5 0.975 1.000
#> 6 0.944 0.995
#> 7 0.971 0.999Created on 2019-02-25 by the reprex package (v0.2.1)