tomhopper

library(qcc)
#' The data, from sample published by Donald Wheeler
my.xmr.raw <- c(5045,4350,4350,3975,4290,4430,4485,4285,3980,3925,3645,3760,3300,3685,3463,5200)
#' Create the individuals chart and qcc object
my.xmr.x <- qcc(my.xmr.raw, type = "xbar.one", plot = TRUE)
#' Create the moving range chart and qcc object. qcc takes a two-column matrix
#' that is used to calculate the moving range.
my.xmr.raw.r <- matrix(cbind(my.xmr.raw[1:length(my.xmr.raw)-1], my.xmr.raw[2:length(my.xmr.raw)]), ncol=2)
my.xmr.mr <- qcc(my.xmr.raw.r, type="R", plot = TRUE)

tomhopper

library(qcc)
library(ggplot2)
library(grid)

#' The data, from sample data provided by Donald Wheeler
my.xmr.raw <- c(5045,4350,4350,3975,4290,4430,4485,4285,3980,3925,3645,3760,3300,3685,3463,5200)

#' Create the individuals qcc object
my.xmr.x <- qcc(my.xmr.raw, type = "xbar.one", plot = FALSE)

tomhopper

library(ggplot2)
#' create a data frame with test data.
my.df <- data.frame(index = 1:10, value = rnorm(10))

#' create the ggplot object
my.ggp <- ggplot(data = my.df, aes(x = index, y = value)) + geom_point() + geom_line()

#' get the x- and y-axis ranges actually used in the graph

# This worked in early versions of ggplot2 (probably <2.2)

tomhopper

#' Example Cleveland-style dot plot.
#' Two variables plotted on an facet plot.
#' Ordering of the data in the first facet.
#' Error bars plotted with each dot.

library(ggplot2)
library(reshape2)
library(plyr)

#' Create some data for the demonstration

tomhopper

ggplot(NULL, aes(x=x, colour = distribution)) + 
  stat_function(fun=dnorm, data = data.frame(x = c(-6,6), distribution = factor(1)), size = 1) + 
  stat_function(fun=dt, args = list( df = 20), data = data.frame(x = c(-6,6), distribution = factor(2)), linetype = "dashed", size = 1) + 
  scale_colour_manual(values = c("blue","red"), labels = c("Normal","T-Distribution")) +
  theme(text = element_text(size = 12),
        legend.position = c(0.85, 0.75)) +
  xlim(-4, 4) +
  xlab(NULL) +
  ylab(NULL)

tomhopper

#' @title PRESS
#' @author Thomas Hopper
#' @description Returns the PRESS statistic (predictive residual sum of squares).
#'              Useful for evaluating predictive power of regression models.
#' @param linear.model A linear regression model (class 'lm'). Required.
#' 
PRESS <- function(linear.model) {
  #' calculate the predictive residuals
  pr <- residuals(linear.model)/(1-lm.influence(linear.model)$hat)
  #' calculate the PRESS

tomhopper

library(data.table)

# See \link{http://stackoverflow.com/questions/11792527/filtering-out-duplicated-non-unique-rows-in-data-table}
# for a discussion of how to eliminate duplicate rows.
# The problem is that the \code{unique()} function will use a key, if it exists. We need to
# eliminate the key.

# Create one column of data
temp1 <- data.table(sample(letters,size = 15, replace = FALSE))
temp2 <- data.table(sample(letters,size = 15, replace = FALSE))

tomhopper

#' When plotting multiple data series that share a common x axis but different y axes,
#' we can just plot each graph separately. This suffers from the drawback that the shared axis will typically
#' not align across graphs due to different plot margins.
#' One easy solution is to reshape2::melt() the data and use ggplot2's facet_grid() mapping. However, there is
#' no way to label individual y axes.
#' facet_grid() and facet_wrap() were designed to plot small multiples, where both x- and y-axis ranges are
#' shared acros all plots in the facetting. While the facet_ calls allow us to use different scales with
#' the \code{scales = "free"} argument, they should not be used this way.
#' A more robust approach is to the grid package grid.draw(), rbind() and ggplotGrob() to create a grid of 
#' individual plots where the plot axes are properly aligned within the grid.

tomhopper

#' Data frame column names are rarely human-readable, concise and clear, but are usually meaningful. Rather
#' than trying to modify the data, we can provide custom labels for facets.
library(data.table)
library(lubridate)
library(reshape2)
library(ggplot2)

#' Download raw data from "Weather Data" at \link{http://datamonitoring.marec.gvsu.edu/DataDownload.aspx},
#' rename the file to "Marec_weather.csv" and save it to /data/ in the current working directory.

tomhopper

#' @title Returns a normally distributed vector within the 99.7% tolerance interval defined by minimum and maximum
#' @param n (required) The number of random numbers to generate
#' @param minimum (optional) The lower 99.9% tolerance limit
#' @param maximum (optional) The upper 99.9% tolerance limit
#' @return numeric vector with n elements randomly distributed so that approximately 99.7% of values will fall between minimum and maximum
#' @examples
#'  rnorm.within(10)
#'  rnorm.within(10, 10, 20)
#'  summary(rnorm.within(10000, 10, 20))
rnorm.within <- function(n, minimum=0, maximum=1)