Lab 1: Intro to R

# library(tidyverse)
library(openintro)

## Warning: package 'openintro' was built under R version 4.3.3

## Warning: package 'usdata' was built under R version 4.3.3

Exercise 1

arbuthnot$girls

##  [1] 4683 4457 4102 4590 4839 4820 4928 4605 4457 4952 4784 5332 5200 4910 4617
## [16] 3997 3919 3395 3536 3181 2746 2722 2840 2908 2959 3179 3349 3382 3289 3013
## [31] 2781 3247 4107 4803 4881 5681 4858 4319 5322 5560 5829 5719 6061 6120 5822
## [46] 5738 5717 5847 6203 6033 6041 6299 6533 6744 7158 7127 7246 7119 7214 7101
## [61] 7167 7302 7392 7316 7483 6647 6713 7229 7767 7626 7452 7061 7514 7656 7683
## [76] 5738 7779 7417 7687 7623 7380 7288

Exercise 2

Insert any text here.

# Insert code for Exercise 2 here

# Plotting the number of girls over time
library(ggplot2)
ggplot(arbuthnot, aes(x = year, y = girls)) +
  geom_line() +
  labs(title = "Number of Girls Over Time",
       x = "Year",
       y = "Number of Girls")

# 

Exercise 3

Insert any text here.

# Insert code for Exercise 3 here

# Add a new column for the proportion of boys
arbuthnot$prop_boys <- arbuthnot$boys / (arbuthnot$boys + arbuthnot$girls)

# Plot the proportion of boys over time
ggplot(arbuthnot, aes(x = year, y = prop_boys)) +
  geom_line() +
  labs(title = "Proportion of Boys Over Time",
       x = "Year",
       y = "Proportion of Boys")

Exercise 4

Insert any text here.

# Insert code for Exercise 4 here
# showing the dimensions of the Arbuthnot dataset
dim(arbuthnot)

## [1] 82  4

Exercise 5

Insert any text here.

# Insert code for Exercise 5 here

# Summing up the total number of boys and girls
total_boys <- sum(arbuthnot$boys)
total_girls <- sum(arbuthnot$girls)

# Comparing the counts
cat("Total number of boys:", total_boys, "\n")

## Total number of boys: 484382

cat("Total number of girls:", total_girls, "\n")

## Total number of girls: 453841

Exercise 6

Insert any text here.

# Insert code for Exercise 6 here
# Assuming using the same Arbuthnot dataset, we can re-plot the same proportion
ggplot(arbuthnot, aes(x = year, y = prop_boys)) +
  geom_line() +
  labs(title = "Proportion of Boys Over Time",
       x = "Year",
       y = "Proportion of Boys")

Exercise 7

Insert any text here.

# Insert code for Exercise 7 here

# Add a new column for total births (boys + girls)
arbuthnot$total <- arbuthnot$boys + arbuthnot$girls

# Find the year with the maximum total births
max_total_year <- arbuthnot[which.max(arbuthnot$total), "year"][[1]]

# Print the year with the maximum total births
cat("Year with the maximum total births:", max_total_year)

## Year with the maximum total births: 1705