# ACCA7022 Advanced Statistical Programming — R Function Reference Sheet
# 
# Each entry gives the function name and its purpose, followed by example R code.
# The examples are independent demonstrations, not one continuous analysis.
# Run individual lines or sections in R/RStudio.
#
# Requirements: base R; ggplot2 for the visualisation section.
# install.packages("ggplot2")  # Run once if ggplot2 is not installed.
# library(ggplot2)           # Uncomment before running ggplot2 examples.
#
# The read.csv() example requires a file named Results.csv in the working directory.
# The examples using mtcars use the dataset supplied with R.
# Some ggplot2 examples create plot components (layers or mappings), rather than
# complete plots; add these to a ggplot() expression to display them.

# ==========================================================================
# Workshop 1 – Introduction
# ==========================================================================

# c() — Combines values into a vector.
c(2, 4, 6)

# mean() — Calculates the arithmetic mean.
mean(c(2,4,6))

# hist() — Draws a histogram of numeric data.
hist(rnorm(100))

# sd() — Calculates sample standard deviation.
sd(c(2,4,6))

# runif() — Generates uniformly distributed random values.
runif(5, min=0, max=1)

# sample() — Randomly samples or rearranges values.
sample(1:10, 4)

# sum() — Adds values together.
sum(c(1,2,3))

# ==========================================================================
# Workshop 2 – Vectors I
# ==========================================================================

# typeof() — Returns an object's internal data type.
typeof(c(1,2,3))

# seq() — Creates a sequence of numbers.
seq(1, 3, by=0.4)

# ==========================================================================
# Workshop 3 – Vectors II
# ==========================================================================

# length() — Returns the number of elements.
length(c(4,5,6))

# is.na() — Identifies missing (NA) values.
is.na(c(1,NA,3))

# is.null() — Tests whether an object is NULL.
is.null(NULL)

# rep() — Repeats values or sequences.
rep(c(2,3,4), each=2)

# ==========================================================================
# Workshop 3F – Focus on Loops
# ==========================================================================

# print() — Displays an object in the console.
print("Hello")

# ==========================================================================
# Workshop 4 – Vectors III
# ==========================================================================

# subset() — Selects elements or rows meeting conditions.
subset(c(3,7,9), c(3,7,9)>5)

# all() — Tests whether all conditions are TRUE.
all(c(TRUE,TRUE))

# any() — Tests whether any condition is TRUE.
any(c(FALSE,TRUE))

# which() — Returns indices of TRUE values.
which(c(2,5,8)>4)

# ifelse() — Selects values according to a condition.
ifelse(c(2,7)>5,"high","low")

# identical() — Checks exact equality of two objects.
identical(1:3, c(1L,2L,3L))

# names() — Gets or sets element names.
names(c(a=1,b=2))

# barplot() — Draws a bar chart.
barplot(c(4,7,2))

# ==========================================================================
# Workshop 5 – Matrices and Arrays I
# ==========================================================================

# matrix() — Creates a two-dimensional matrix.
matrix(1:6,nrow=2)

# apply() — Applies a function across rows or columns.
apply(matrix(1:6,2), 1, sum)

# t() — Transposes a matrix.
t(matrix(1:6,nrow=2))

# ==========================================================================
# Workshop 6 – Matrices and Arrays II
# ==========================================================================

# rbind() — Joins objects by rows.
rbind(c(1,2),c(3,4))

# cbind() — Joins objects by columns.
cbind(c(1,2),c(3,4))

# colnames() — Gets or sets column names.
colnames(matrix(1:4,2)) <- c("A","B")

# rownames() — Gets or sets row names.
rownames(matrix(1:4,2)) <- c("X","Y")

# array() — Creates a multidimensional array.
array(1:8,dim=c(2,2,2))

# ==========================================================================
# Workshop 7 – Lists
# ==========================================================================

# list() — Creates a list of objects.
list(name="Jack",age=22)

# class() — Reports an object's class.
class(list(a=1))

# unlist() — Flattens a list into a vector.
unlist(list(a=1,b=2))

# unname() — Removes names from an object.
unname(c(a=3,b=4))

# lapply() — Applies a function to each list element.
lapply(list(1:3,4:6),sum)

# sapply() — Applies a function and simplifies results.
sapply(list(1:3,4:6),mean)

# ==========================================================================
# Workshop 8 – Data Frames
# ==========================================================================

# data.frame() — Creates a tabular data frame.
data.frame(name=c("A","B"),mark=c(70,65))

# read.csv() — Imports data from a CSV file.
read.csv("Results.csv",header=TRUE)

# complete.cases() — Identifies rows with no missing values.
complete.cases(data.frame(a=c(1,NA),b=2:3))

# ==========================================================================
# Workshop 9 – Frames, Factors & Tables
# ==========================================================================

# merge() — Joins data frames using common columns.
merge(data.frame(id=1:2,a=3:4),data.frame(id=1:2,b=5:6))

# order() — Returns indices that sort values.
order(c(5,1,3))

# tapply() — Applies a function to groups of values.
tapply(c(4,5,6),c("A","A","B"),mean)

# split() — Splits data into groups.
split(1:4,c("A","A","B","B"))

# as.data.frame() — Converts an object to a data frame.
as.data.frame(matrix(1:4,2))

# table() — Counts occurrences of values or combinations.
table(c("A","B","A"))

# factor() — Creates a categorical variable.
factor(c("urban","rural","urban"))

# ==========================================================================
# Workshop 19 – Simulation and Visualisation
# ==========================================================================

# Load ggplot2 before using the functions in this section.
library(ggplot2)

# set.seed() — Sets the random-number seed for reproducibility.
set.seed(42)

# aes() — Defines aesthetic mappings for a plot.
aes(x=wt,y=mpg)

# ggplot() — Initialises a ggplot2 visualisation.
ggplot(mtcars,aes(wt,mpg)) + geom_point()

# geom_histogram() — Adds a histogram layer.
ggplot(mtcars,aes(mpg)) + geom_histogram()

# labs() — Sets plot title and axis or legend labels.
labs(title="Mileage",x="Weight",y="MPG")

# geom_text() — Adds text labels to plotted data.
geom_text(aes(label=rownames(mtcars)))

# after_stat() — Maps a computed statistic to an aesthetic.
aes(y=after_stat(count))

# scale_x_continuous() — Controls a continuous x-axis scale.
scale_x_continuous(breaks=seq(1,5,1))

# theme() — Customises non-data plot appearance.
theme(legend.position="bottom")

# theme_minimal() — Applies a minimal plot theme.
theme_minimal()

# geom_line() — Adds lines connecting observations.
geom_line()

# geom_point() — Adds a scatterplot point layer.
geom_point()

# geom_tile() — Draws rectangular tiles, e.g. a heatmap.
geom_tile()

# geom_jitter() — Adds points with jitter to reduce overlap.
geom_jitter(width=0.1)

# ==========================================================================
# Workshop 10 – Control Statements I
# ==========================================================================

# numeric() — Creates a numeric vector, initially zero-filled.
numeric(5)

# ==========================================================================
# Workshop 12 – Functions I
# ==========================================================================

# paste() — Joins text values into strings.
paste("Mean:",mean(1:5))

# return() — Explicitly returns a value from a function.
f <- function(x) { return(x*2) }; f(3)

# ==========================================================================
# Workshop 13 – Functions II
# ==========================================================================

# unique() — Returns distinct values.
unique(c("A","B","A"))

# ==========================================================================
# Workshop 14 – Functions III
# ==========================================================================

# as.numeric() — Converts values to numeric form.
as.numeric("42")

# as.vector() — Converts an object to a vector.
as.vector(matrix(1:4,2))

# ==========================================================================
# Workshop 15 – Data Analysis I
# ==========================================================================

# substr() — Extracts or replaces part of a string.
substr("10:45",1,2)

# ==========================================================================
# Workshop 16 – Data Analysis II
# ==========================================================================

# nchar() — Counts characters in strings.
nchar("10:45")

# ==========================================================================
# Workshop 17 – Data Analysis III
# ==========================================================================

# median() — Finds the middle value of a distribution.
median(c(1,4,8))

# max() — Returns the largest value.
max(c(2,5,3))

# min() — Returns the smallest value.
min(c(2,5,3))

# range() — Returns the minimum and maximum.
range(c(2,5,3))

# which.max() — Returns the index of the first maximum.
which.max(c(3,9,4))

# quantile() — Calculates selected distribution quantiles.
quantile(1:20,probs=c(.25,.75))

# aggregate() — Summarises data by groups.
aggregate(mpg ~ cyl,data=mtcars,FUN=mean)

# summary() — Produces a statistical or structural summary.
summary(mtcars$mpg)

# switch() — Chooses among alternatives by key or position.
switch("b",a=1,b=2,c=3)

# ==========================================================================
# Workshop 18 – Data Analysis IV
# ==========================================================================

# plot() — Creates a base R plot.
plot(mtcars$wt,mtcars$mpg)

# cor() — Calculates a correlation coefficient.
cor(mtcars$wt,mtcars$mpg,method="pearson")

# shapiro.test() — Tests data for normality (Shapiro–Wilk).
shapiro.test(rnorm(30))

# boxplot() — Draws box-and-whisker plots.
boxplot(mpg ~ cyl,data=mtcars)

# t.test() — Performs a Student or Welch t-test.
t.test(mpg ~ am,data=mtcars)

# aov() — Fits an analysis-of-variance model.
aov(mpg ~ factor(cyl),data=mtcars)

# TukeyHSD() — Runs Tukey post-hoc pairwise comparisons.
TukeyHSD(aov(mpg ~ factor(cyl),data=mtcars))

# Scope and conventions
# The source cheat sheet excludes language keywords, operators and
# student-defined functions. Each listed function appears only once.
# ggplot2 geoms and themes can be added to a ggplot object with +.