njtierney

library(lme4)

# broom tidies up model summaries
library(broom) # install.packages("broom")

# fit a mixed model
fm1 <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)

# print the model output
fm1

njtierney

library(plyr)
library(dplyr)
library(tidyr)
library(visdat)
library(ggplot2)
library(readr)

bible_quote <- read_csv("/Users/tierneyn/Downloads/public-bible-quotations.csv")
  # Parsed with column specification:
  #   cols(

njtierney

I think the two most important messages that people can get from a short course are:

a) the material is important and worthwhile to learn (even if it's challenging), and b) it's possible to learn it!

For those reasons, I usually start by diving as quickly as possible into visualisation. I think it's a bad idea to start by explicitly teaching programming concepts (like data structures), because the pay off isn't obvious. If you start with visualisation, the pay off is really obvious and people are more motivated to push past any initial teething problems. In stat405, I used to start with some very basic templates that got people up and running with scatterplots and histograms - they wouldn't necessary understand the code, but they'd know which bits could be varied for different effects.

Apart from visualisation, I think the two most important topics to cover are tidy data (i.e. http://www.jstatsoft.org/v59/i10/ + tidyr) and data manipulation (dplyr). These are both important for when people go off and apply

njtierney

ras_1 <- matrix(data = rep(NA, 100), 
                nrow = 10,
                ncol = 10,
                byrow = TRUE)

ras_1

ras_2 <- matrix(data = c(1,rep(NA, 99)), 
               nrow = 10,
               ncol = 10,

njtierney

iris_lm_fit_all <- lm(Sepal.Length ~ ., iris)

iris_lm_fit_all_step <- step(iris_lm_fit_all,
                             scope = Sepal.Length ~ .^2) 
#> Start:  AIC=-348.57
#> Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width + Species
#> 
#>                            Df Sum of Sq    RSS     AIC
#> + Petal.Length:Species      2    0.4883 13.068 -350.07
#> + Sepal.Width:Petal.Length  1    0.2754 13.281 -349.64

njtierney

####################
# Makefile
# Copyright Brian A. Fannin 2015
####################

RDIR = .
DATA_DIR = $(RDIR)/data

GATHER_DIR = $(DATA_DIR)/gather
GATHER_SOURCE = $(wildcard $(GATHER_DIR)/*.Rmd)

njtierney

# working out whether transactions have reciprocated

library(tibble)
library(dplyr)

# let's boil this example down

df_boil <- tribble(
    ~sender, ~receiver, ~transaction_id,
    1,        2,              "A",

njtierney

project
|- DESCRIPTION          # project metadata and dependencies
|- README.md            # top-level description of content and guide to users
|- NAMESPACE            # exports R functions in the package for repeated use
|- LICENSE              # specify the conditions of use and reuse of the code, data & text
|- data/                # raw data, not changed once created
|  +- my_data.csv       # data files in open formats such as TXT, CSV, TSV, etc.
|
|- analysis/            # Series of folders for each step of the analysis

njtierney

# install.packages("VineCopula")
# install.packages("copula")
# install.packages("tigerstats")

library(VineCopula)
library(copula)
library(tigerstats)
set.seed(123)
N=200
dim=dim

njtierney

ip <- as.data.frame(installed.packages()[,c(1,3:4)])
rownames(ip) <- NULL
ip <- ip[is.na(ip$Priority),1:2,drop=FALSE]
write.csv(ip, "package_list.csv")
print(ip, row.names=FALSE)