alexhallam

library(modelr)
library(tidyverse)
library(gapminder)

# nest data by continent and label test/train data
nested_gap <- gapminder %>% 
  mutate(test_train = ifelse(year < 1992, "train", "test")) %>% 
  group_by(continent) %>% 
  nest()

alexhallam

# Test/Train split
set.seed(2018)  # for reproducability
daily %>% 
  mutate(test_train = ifelse(rbinom(n=n(), size = 1, prob = .75) == 1,
                             "train","test")) %>% 
  count(test_train)

alexhallam

library(purrr)
library(broom)
library(modelr)

#data set up
my_iris <- iris %>% 
  mutate(train_test = ifelse(rbinom(n=n(), size = 1, prob = .85) == 1,
"train","test")) 

#set up model function

alexhallam

#https://purrple.cat/blog/2018/03/02/multiple-lags-with-tidy-evaluation/
lags <- function(var, n=10){
  var <- enquo(var)
  
  indices <- seq_len(n)
  map( indices, ~quo(lag(!!var, !!.x)) ) %>% 
    set_names(sprintf("lag_%s_%02d", quo_text(var), indices))
  
}

alexhallam

  ggthemes::geom_tufteboxplot(aes(color = pre_post), size = 2)+
  scale_color_viridis(discrete=TRUE, option = "magma", end = .8)

alexhallam

library(tidyverse)
library(gumballthemes)
dat <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2018-09-11/cats_vs_dogs.csv")

dat <- dat %>% 
  mutate(household_label = ifelse(n_dog_households > n_cat_households, "more dog households", "more cat households"))

p <- ggplot(dat, aes(x = percent_cat_owners, y = percent_dog_owners, color = household_label)) +
  geom_point() +
  ylab("% Dog Owners") +

alexhallam

sudo docker run -dit --restart unless-stopped -v $PWD/share:/home/rstudio/share -p 8787:8787 -e PASSWORD=*** --name rstudio rocker/rstudio

alexhallam

library(tidyverse)
library(tidymodels)
Sacramento %>% str()
y <- Sacramento %>% select(price) %>% as.matrix()
x <- Sacramento  %>% as.matrix() %>% scale()
fit <- glmnet::glmnet(x, y, lambda = 4192.847)
str(fit)

tidy_glmnet <- function(fit){
lasso_coeffs <- tibble(index = seq(1:fit$dim[1]) - 1, terms = row.names(fit$beta)) %>% 

alexhallam

library(tidyverse)
# naive forecast method example
sales <- tibble(g = c(rep("insample", 23), rep("outsample", 12)),
       y = c(0,2,0,1,0,10,0,0,0,2,0,6,3,0,0,0,0,0,7,0,0,0,0, 0, 0, 0, 3, 1, 0, 0, 1, 0, 1, 0, 0),
       y_hat = ifelse(g == "insample", lag(y), last(y)),
       error = abs(y - y_hat))

sales

sales %>%

alexhallam

taskscheduleR::taskscheduler_create(taskname = "myfancyscript_5min", rscript = myscript,
                     schedule = "MINUTE", starttime = "11:19", modifier = 1, startdate = format(as.Date("2019-01-19"), "%m/%d/%Y"))