1 + 2
rnorm(100)
3 - 4
5 * 6
7 / 8
1 + 2 * 3
(1 + 2) * 3
17 %/% 4
17 %% 4
2 ^ 4
2 ^ 4.3
log(4)
log10(4)
log(4, 10)
sqrt(9)
abs(3-4)
exp(1)

us_population <- 3.31e8 # From Wolfram|Alpha, 2020 estimate
us_area <- 3719000      # From Wolfram|Alpha
us_pop_density <- us_population / us_area
us_pop_density
( us_pop_density <- us_population / us_area )
rm(us_pop_density) 

help(sqrt)
?sqrt
?"+"
example(sqrt)

has_diabetes    <- TRUE         # logical  (note case!)
patient_name    <- "Jane Doe"   # character
moms_age        <- NA           # used to represent an unknown ("missing") value
NY_socialite_iq <- NULL         # used to represent something that does not exist
is_enrolled  <- FALSE
is_candidate <- has_diabetes & ! is_enrolled
TRUE & FALSE
T | F
T & NA
F & NA
TRUE | NA
FALSE | NA
TRUE & ! FALSE & NA
as.numeric(has_diabetes)
as.numeric(is_enrolled)
as.character(us_population)
as.character(moms_age) 

x <- rnorm(100)
sum(x)
max(x)
summary(x)
plot(x)
hist(x)


my_colors <- c("red", "orange", "yellow", "green", "blue", "indigo", "violet")
my_colors <- c("infrared", my_colors, "ultraviolet")
length(my_colors)
my_colors[7]
my_colors[7] <- "purple"

a_numeric_vector <- vector(mode="numeric", length=1000)
a_numeric_vector[50] <- 5
a_numeric_vector[750] <- 10
plot(a_numeric_vector)

data()
state.name
state.area

indices <- 41:50
indices[1]
indices[2]
length(indices)
state.name[indices]

# state.name[c(1:10, (length(state.name)-9):length(state.name))]

summary(state.area)
cutoff <- 37317
# cutoff <- summary(state.area)[2]
state.area < cutoff
small_states <- state.name[state.area < cutoff]
"New York" %in% small_states
"Rhode Island" %in% state.name[state.area < cutoff]
which(state.area < cutoff)
state.name[which(state.area < cutoff)]
state.area[state.name == "Wyoming"]

names(state.area) <- state.name
state.area["Wyoming"]
state.area[c("Wyoming", "Alaska")]
state.area[small_states]
min(state.area)
state.area[which(state.area == min(state.area))]
state.area[which.min(state.area)]

seq(1, 10)
seq(1, 4, 0.5)
?seq
seq(0, 1, length.out = 10)
seq(from = 1, to = 4, by = 0.5)
seq(from = 0, to = 1, length.out = 10)
seq(to = 99)

rep(my_colors, 2)
rep(my_colors, times = 2) # same as above
rep(my_colors, each = 2)
rep(my_colors, each = 2, times = 2)
rep(my_colors, length.out = 10)

x <- 0:9
y <- seq(from = 0, to = 90, by = 10)
x + y
(1:5) + y
(1:4) + y
y * 2

sort(state.area)
order(state.area)
state.name[order(state.area)]
state.name[order(state.area, decreasing = TRUE)]

sample(state.name, 4)
sample(state.name)
sample(state.name, replace = TRUE)

rev(x)
sum(x)
cumsum(x)
diff(x)
max(x)
min(x)
range(x)
mean(x)

state.division
levels(state.division)
str(state.division)
class(state.division)

pony_colors <- sample(my_colors, size = 500, replace = TRUE)
str(pony_colors)
pony_colors_f <- factor(pony_colors)
str(pony_colors_f)
plot(pony_colors_f)
pony_colors_f <- factor(pony_colors, levels = my_colors)
str(pony_colors_f)
plot(pony_colors_f)

plot(state.division)
state.division <- factor(state.division, levels = sort(levels(state.division)))
plot(state.division)
levels(state.division)
levels(state.division) <- c("ENC", "ESC", "MA", "MT", "NE", "PAC", "SA", "WNC", "WSC")
plot(state.division)
state.name[state.division == "NE"]
mean(state.area[state.division == "NE"]) / mean(state.area[state.division == "WSC"])
t.test(state.area[state.division == "SA"], state.area[state.division == "MT"])

?USPersonalExpenditure
USPersonalExpenditure
rownames(USPersonalExpenditure)
colnames(USPersonalExpenditure)
dim(USPersonalExpenditure)
USPersonalExpenditure[1,3]
USPersonalExpenditure["Food and Tobacco", "1950"]
USPersonalExpenditure[1, "1950"]
USPersonalExpenditure[1, c(5, 3, 1)]
USPersonalExpenditure["Food and Tobacco", c("1960", "1950", "1940")]
USPersonalExpenditure[1, ]
USPersonalExpenditure["Food and Tobacco", ]
USPersonalExpenditure["Food and Tobacco", , drop = FALSE]
USPersonalExpenditure[, c("1940", "1950")]
USPersonalExpenditure[1:3, c("1940", "1950")]
sum(USPersonalExpenditure[, "1940"])
USPersonalExpenditure[1]
USPersonalExpenditure[2]
USPersonalExpenditure[7]
length(USPersonalExpenditure)
sum(USPersonalExpenditure)

game1 <- matrix(c("X", "", "O", "", "X", "O", "", "", ""), ncol = 3)
game2 <- matrix(c("X", "", "O", "", "X", "O", "", "", ""), ncol = 3, byrow = TRUE)
game1[3, 3] <- "X"

new_game <- matrix(data = "", ncol = 3, nrow = 3)

pieces <- c("rook", "knight", "bishop", "queen", "king", "bishop", "knight", "rook")
pawns <- rep("pawn", 8)
board <- rbind(rev(pieces), pawns, matrix("", nrow = 4, ncol = 8), pawns, pieces)
rownames(board) <- 8:1
colnames(board) <- letters[1:8]

USPersonalExpenditure["Personal Care", "1955"] <- "Unknown"
USPersonalExpenditure
rm(USPersonalExpenditure)


(edu_spend <- unname(USPersonalExpenditure["Private Education", ]))
(edu_yr <- seq(from = 0, to = 20, by = 5))
plot(edu_yr, edu_spend)
my_model <- lm(edu_spend ~ edu_yr)
my_model
summary(my_model)
abline(my_model)
plot(my_model)
str(my_model)

ad_mouse_colony <- list("9.1",  FALSE)
ad_mouse_colony <- list(room = "9.1",  bsl3 = FALSE)
ad_mouse_colony$conditions <- list(bedding = "straw", light_hrs = 12)
ad_mouse_colony$count <- c(male = 10, female = 0)
ad_mouse_colony[["variants"]] <- c("APP695swe", "PS1-dE9")

ad_mouse_colony[[1]]
ad_mouse_colony[["room"]]
ad_mouse_colony$room

names(ad_mouse_colony)
ad_mouse_colony[c(1,4)]
ad_mouse_colony $bsl3 <- NULL

x <- c(0, 1, 1, 2, 3, 5, 8, 13, 21)
attr(x, "description") <- "Fibonacci series"
attr(x, "description")
attributes(x)
str(attributes(x))

state_db <- data.frame(state.name, state.abb, state.area, state.center,
                       stringsAsFactors = FALSE)
state_db
summary(state_db)
head(state_db)

state_db$state.abb
state_db[[ "state.abb" ]]
state_db[[ 2 ]]
state_db[, 2]
state_db[ , 1:2]
state_db[41:50, 1:2]
state_db[c(50, 1), c("state.abb", "x", "y")]
state_db[order(state_db$state.area)[1:5], ]
state_db[order(state_db$state.area), ][1:5, ]
rownames(state_db) <- state.abb
state_db[c("NY", "NJ", "CT", "RI"), c("x", "y")]
names(state_db) <- c("name", "abb", "area", "long", "lat")
state_db$division <- state.division 
state_db$z.size <- (state_db$area - mean(state_db$area))/sd(state_db$area)
state_db[ , "z.size", drop = FALSE]
state_db[state_db$area < median(state_db$area), "name"]
state_db[state_db$area < median(state_db$area), "name", drop = FALSE]
coastal <- state_db[ state_db$division %in%
  c("New England", "Middle Atlantic", "South Atlantic", "Pacific"), ]
subset(state_db, area < median(area), select = name)
coastal <- subset(state_db, division %in%
  c("New England", "Middle Atlantic", "South Atlantic", "Pacific") )
subset(state_db, select = c(name, abb))
subset(state_db, select = -c(long, lat))
plot(area ~ division, data = state_db)
plot(log(area) ~ division, data = state_db)
plot(lat ~ long, data = state_db)
text(lat ~ long, data = state_db, rownames(state_db))

ablation <- read.csv("Ablation.csv", header = TRUE, stringsAsFactors = TRUE)
names(ablation)[names(ablation) == "SCORE"] <- "Score"

write.table(ablation, file = "ablation.txt",
               quote = FALSE, col.names = NA, sep = "\t")
write.table(ablation, file = "ablation.txt",
               quote = FALSE, row.names = FALSE, sep = "\t")

mySummary <- function(x) {
  my_mean <- mean(x)
  my_sd <- sd(x)
  list(mean = my_mean, sd = my_sd)
}
mySummary(rnorm(100))

raiseNumber <- function(x, power = 1) {
  x ^ power
}
raiseNumber(10)
raiseNumber(10, 3)

num_iterations <- 100
my_means <- numeric(length = num_iterations)
for (i in 1:num_iterations) {
  x <- rnorm(10000)
  my_means[i] <- mean(x)
}
hist(my_means)