ctesta01

# suppose we have two populations for which we'd like to infer the incidence rate ratio --
# 
# we could use a poisson, quasipoisson, or negative binomial model 
# 
# we'd like to know if we get the same estimates for incidence rate ratios using each of these models 

# dependencies
library(MASS)
library(broom)

ctesta01

Using Feature Branches and Pull Requests on GitHub

The following instructions walk through cloning a repository, creating a feature branch, and submitting a pull request.

You'll need to be ready to use git[^1] to follow along, and I suggest setting up ssh-key based authentication[^2] so you don't have to enter your username and password every time you are transferring code to and from GitHub.

ctesta01

library(dplyr)
library(lubridate)
library(stringr)

# let's say my data has some dates in it  -- these are just random dates for an example 
# and I want to code them to year and quarter

df <- data.frame(
  # random dates between 2020-01-01 and 2022-02-14
  date = lubridate::ymd('2020-01-01') + sample.int(775, 100, replace = TRUE))

ctesta01

library(ggforce)

tw <- -2:1 + .5 # triangle width points
th <- 0:3 + .5 # triangle height points

triangle <- rbind(c(-2,0), c(2,0), c(0,4))

nudge_factor <- 0.15

df <- tibble::tribble(

ctesta01

library(readr)
library(ggdist)
library(tidyverse)
library(magrittr)
library(cowplot)
library(ISOweek)

df <- readr::read_csv("https://github.com/nytimes/covid-19-data/raw/master/rolling-averages/us.csv")
df %<>% mutate(wday = lubridate::wday(lubridate::ymd(date)))
weekdays <- c('Sunday', 'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday')

ctesta01

library(ggplot2)
library(dplyr)
library(magrittr)

# generate fake data
total_N_obs <- 1000
example_data <- 
  data.frame(
    year = sample(2000:2020, replace = TRUE, size = total_N_obs),
    type = sample(c('a', 'b'), replace = TRUE, size = total_N_obs)

ctesta01

library(palmerpenguins)
library(purrr)
library(ggplot2)
library(dplyr)
library(patchwork)

# let's say I want to show bill_length_mm across different species (one plot for each species), 
# but each plot should have the same color scale

# one common issue is that if you just use scale_color_gradient() or scale_color_brewer(), each 

ctesta01

# Using Appropriate Color Names in R
#
# Often times the right color palette and color choices can greatly elevate the
# quality of a data visualization;  the colourlovers.com website has long been
# host to a great number of 5-color palettes which users can favorite and share.
# Moreover, there is now an R package to interface with the colourlovers to
# automatically pull the hex-codes of a specified palette into R.
#
# To take this to the next step of usability, there are times it's appropriate
# to identify and name individiaul colors (ideally with memorable names) to

ctesta01

library(ggplot2)
library(magrittr)
library(rvest)
library(dplyr)

# url to fetch html from
html_data <- "https://www.history.com/topics/black-history/black-history-milestones"

# parse html
html_text <- read_html(html_data)

ctesta01

library(tidyverse)
library(magrittr)
library(geomtextpath)

df_usa <- readr::read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/rolling-averages/us.csv")

ma <- function(x, n = 31){stats::filter(x, rep(1 / n, n), sides = 2)}

df_usa %<>% mutate(
  deaths_avg = as.numeric(ma(deaths_avg)),