eddjberry

# function to round a value to the nearest digit
# e.g. if nearest = 5 then 42 would round to 40
# and 47 would be rounded to 45
# source: http://r.789695.n4.nabble.com/Rounding-to-the-nearest-5-td863189.html

round_nearest <- function(x, nearest) {
  nearest * round(x / nearest)
}

eddjberry

group_prop <- function(df, ...) {
  # enquo the dots
  vars <- enquos(...)
  
  # count then calculate
  # proportions
  df_count <- df %>%
    count(!!!vars)
  
  if (length(vars) > 1) {

eddjberry

# a function to format strings
# to be in Proper case
str_proper <- function(string) {
  # get the first letter
  first_letter = substring(string, first = 1, last = 1)
  
  # get the other letters
  other_letters = substring(string, first = 2)
  
  # combine the first letter (upper case)

eddjberry

# create a tibble----------------------
tbl <- tibble::tibble(x = letters[1:5],
                      y = letters[5:1])

# returns a tibble --------------------
dplyr::select(tbl, x) 

tbl[1] 

tbl[, 1] 

eddjberry

library(scales)
library(viridis)

show_col(viridis(12))

eddjberry

# create some data
(df <- data_frame(x = 1:2,
                  y = c(NA, NA),
                  z = c(NA, 3)))

# remove rows where either col y or z contain NA
# i.e. keep rows where all variables are not NA
df %>% 
  filter_at(vars(y:z), all_vars(!is.na(.)))

eddjberry

library(tidyverse)

# Nest iris by Species
iris_nest <- iris %>%
  group_by(Species) %>%
  nest()

# Get the data list and set the names of the list to Species
# write_csv for each df in the data list with its name as the filename
iris_nest %>%

eddjberry

sim_binom <- function(n_samples = 1000, n_features = 2,
                      true_target_prob = 0.5, beta = NULL, seed = NULL) {

  if(!is.null(seed)) {
    set.seed(seed)
  }

  x = matrix(rnorm(n_samples * n_features),
             nrow = n_samples, ncol = n_features)

eddjberry

# Load packages
library(dplyr)
library(sparklyr)

# Set up connect
sc <- spark_connect(master = "local")

# Create a Spark DataFrame of mtcars
mtcars_sdf <- copy_to(sc, mtcars)