Created
August 30, 2019 00:35
-
-
Save tmastny/15fbace489c28822026261012b92dd57 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(recipes) | |
library(embed) | |
library(dplyr) | |
library(mlbench) | |
set.seed(124) | |
data(PimaIndiansDiabetes) | |
d <- PimaIndiansDiabetes | |
d <- d %>% | |
as_tibble() %>% | |
select(diabetes, everything()) | |
# make factor variables | |
d <- d %>% | |
mutate(mass_fct = factor(ifelse(mass > 30, "large", "small"))) %>% | |
mutate(pregnant_fct = as.factor(pregnant)) %>% | |
mutate(pressure_fct = factor(case_when( | |
pressure < 30 ~ "low", | |
between(pressure, 30, 50) ~ "medium", | |
pressure > 50 ~ "high" | |
))) %>% | |
mutate(triceps_fct = factor(ifelse(triceps > 0, "has", "none"))) %>% | |
mutate(insulin_fct = factor(insulin)) %>% | |
mutate(age_fct = factor(age)) | |
# steps in `embed` | |
embed_rec <- recipe(diabetes ~ ., d) %>% | |
embed::step_woe(mass_fct, outcome = diabetes) %>% | |
embed::step_lencode_bayes(pregnant_fct, outcome = vars(diabetes)) %>% | |
embed::step_lencode_glm(pressure_fct, outcome = vars(diabetes)) %>% | |
embed::step_lencode_mixed(triceps_fct, outcome = vars(diabetes)) %>% | |
embed::step_embed( | |
insulin_fct, | |
outcome = vars(diabetes), | |
options = embed_control(epochs = 1) | |
) %>% | |
embed::step_umap(age_fct, outcome = vars(diabetes)) | |
embed_rec_prepped <- prep(embed_rec, d) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment