topepo

## -----------------------------------------------------------------------------
# Simple demonstration of stacking using three models with the Ames housing data

## -----------------------------------------------------------------------------

library(tidymodels)
library(rules)
library(doMC)
library(AmesHousing)
library(ggforce)

topepo

library(tidymodels)
library(Matrix)
library(lobstr)


# ------------------------------------------------------------------------------

rand_values <- function (prefix = "step", len = 3, num_vals = Inf) {
  candidates <- c(letters, LETTERS, paste(0:9))
  candidates <- candidates[1:min(length(candidates), num_vals)]

topepo

library(tidyverse)
library(janitor)
library(tidymodels)
library(plotly)

theme_set(theme_bw())

body <- 
  read_csv("http://staff.pubhealth.ku.dk/~tag/Teaching/share/data/Bodyfat.csv") %>% 
  janitor::clean_names() %>% 

topepo

library(tidyverse)
library(lubridate)

# ------------------------------------------------------------------------------

set.seed(2427)
hotels <- 
  readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-02-11/hotels.csv') %>%
  filter(is_canceled == 0) %>%
  mutate(

topepo

# devtools::install_dev("rsample")
library(tidymodels)

set.seed(252)
first_split <- initial_split(iris, p = 8/10)
test <- testing(first_split)
nrow(test)

others <- training(first_split)

topepo

library(tidyverse)
library(lubridate)

theme_set(theme_bw())

dat <-
  read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-counties.csv")

dat %>%
  group_by(state) %>%

topepo

library(tidymodels)
library(modeldata)

data(attrition)

ord_rec <- 
  recipe(Attrition ~ JobInvolvement + JobSatisfaction, data = attrition) %>% 
  step_dummy(all_nominal()) %>% 
  prep() %>% 
  juice() %>% 

topepo

library(tidymodels)
library(rlang)


get_arg <- function(ns, f, arg) {
  args <- formals(getFromNamespace(f, ns))
  args <- args %>% as.list() 
  as.character(args[[arg]])
}

topepo

replicates <- tibble::tribble(
           ~id,  ~rep_1,  ~rep_2,
  "sample_001",  2.4061,  1.8369,
  "sample_002", -0.6736,  -0.102,
  "sample_003",  1.0801,  0.7717,
  "sample_004",   1.071,  1.5332,
  "sample_005",  0.0674,  0.5275,
  "sample_006",  1.6322,  1.8619,
  "sample_007", -0.5528,  -0.373,
  "sample_008",  1.6413,  1.9207,

topepo

library(tidymodels)
library(nycflights13)

set.seed(25213)
flight_data <- 
  flights %>% 
  mutate(
    delay = ifelse(arr_delay >= 30, "late", "on_time"),
    delay = factor(delay),
    date = as.Date(time_hour)