# Some vectors of numbers
percent_change  <- c(4, -1.91, 3.00, -5.002)
income <-  c(72.19, 1030.18, 10291.93, 1189192.18)
p_values <- c(0.12, 0.98, 0.0000191, 0.00000000002)

# Format c(0.0011, 0.011, 1) with digits = 1
format(c(0.0011, 0.011, 1), digits =1)

# Format c(1.0011, 2.011, 1) with digits = 1
format(c(1.0011, 2.011, 1), digits=1)

# Format percent_change to one place after the decimal point
format(percent_change, digits=2)

# Format income to whole numbers
format(income, digits=2)

# Format p_values in fixed format
format(p_values, scientific=FALSE)

## 2
formatted_income <- format(income, digits = 2)

# Print formatted_income
print(formatted_income)

# Call writeLines() on the formatted income
writeLines(formatted_income)

# Define trimmed_income
trimmed_income <- format(income, digits=2, trim=TRUE)

# Call writeLines() on the trimmed_income
writeLines(trimmed_income)

# Define pretty_income
pretty_income <- format(income, digits = 2, big.mark=",")

# Call writeLines() on the pretty_income
writeLines(pretty_income)


#Rather than a scientific argument, formatC() has a format argument that takes a code representing the required format. The most useful are:

#"f" for fixed,
#"e" for scientific, and
#"g" for fixed unless scientific saves space

# From the format() exercise
x <- c(0.0011, 0.011, 1)
y <- c(1.0011, 2.011, 1)

# formatC() on x with format = "f", digits = 1
formatC(x, format='f', digits=1)

# formatC() on y with format = "f", digits = 1
formatC(y, format ="f", digits=1)

# Format percent_change to one place after the decimal point
formatC(percent_change, format='f',digits=1)

# percent_change with flag = "+"
formatC(percent_change, format='f',digits=1, flag="+")

# Format p_values using format = "g" and digits = 2
formatC(p_values, format="g", digits=2)

# Add $ to pretty_income
paste("$",pretty_income,sep='' )

# Add % to pretty_percent
paste(pretty_percent, "%", sep="")

# Create vector with elements like 2010: +4.0%`
year_percent <- paste(years, ': ', pretty_percent, "%", sep="")

# Collapse all years into single string
paste(year_percent, collapse=', ')

## 3
# Define the names vector
income_names <- c("Year 0", "Year 1", "Year 2", "Project Lifetime")

# Create pretty_income
pretty_income <- format(income, digits=2, big.mark=",")

# Create dollar_income
dollar_income <- paste("$", pretty_income, sep="")

# Create formatted_names
formatted_names <- format(income_names, justify="right")

# Create rows
rows<-paste(formatted_names, dollar_income, sep="   ")

# Write rows
writeLines(rows)

## 3
# Randomly sample 3 toppings
my_toppings <- sample(toppings, size = 3)

# Print my_toppings
my_toppings

# Paste "and " to last element: my_toppings_and
my_toppings_and <- paste(c("", "", "and "), my_toppings, sep = "")

# Collapse with comma space: these_toppings
these_toppings <- paste(my_toppings_and, collapse = ", ")

# Add rest of sentence: my_order
my_order <- paste("I want to order a pizza with ", these_toppings, ".", sep = "")

# Order pizza with writeLines()
writeLines(my_order)

## stringr
library(stringr)

my_toppings <- c("cheese", NA, NA)
my_toppings_and <- paste(c("", "", "and "), my_toppings, sep = "")

# Print my_toppings_and
print(my_toppings_and)

# Use str_c() instead of paste(): my_toppings_str
my_toppings_str <- str_c(c("", "", "and "), my_toppings)

# Print my_toppings_str
print(my_toppings_str)

# paste() my_toppings_and with collapse = ", "
paste(my_toppings_and, collapse = ", ")

# str_c() my_toppings_str with collapse = ", "
str_c(my_toppings_str, collapse = ", ")

##
library(stringr)
library(babynames)
library(dplyr)

# Extracting vectors for boys' and girls' names
babynames_2014 <- filter(babynames, year == 2014)
boy_names <- filter(babynames_2014, sex == "M")$name
girl_names <- filter(babynames_2014, sex == "F")$name

# Take a look at a few boy_names
head(boy_names)

# Find the length of all boy_names
boy_length <- str_length(boy_names)

# Take a look at a few lengths
head(boy_length)

# Find the length of all girl_names
girl_length <- str_length(girl_names)

# Find the difference in mean length
mean(girl_length) - mean(boy_length)

# Confirm str_length() works with factors
head(str_length(factor(boy_names)))

#####
# Extract first letter from boy_names
boy_first_letter <- str_sub(boy_names, 1,1)

# Tabulate occurrences of boy_first_letter
table(boy_first_letter)

# Extract the last letter in boy_names, then tabulate
boy_last_letter <- str_sub(boy_names, -1,-1)
table(boy_last_letter)

# Extract the first letter in girl_names, then tabulate
girl_first_letter <- str_sub(girl_names, 1,1)
table(girl_first_letter)

# Extract the last letter in girl_names, then tabulate
girl_last_letter <- str_sub(girl_names, -1,-1)
table(girl_last_letter)


####
# Look for pattern "zz" in boy_names
contains_zz <- str_detect(boy_names, pattern="zz")

# Examine str() of contains_zz
str(contains_zz)

# How many names contain "zz"?
sum(contains_zz)

# Which names contain "zz"?
boy_names[contains_zz]

# Which rows in boy_df have names that contain "zz"?
boy_df[contains_zz,]