Lab 1: Intro to R

library(tidyverse)
library(openintro)

load/look at data

#load data
data('arbuthnot', package = 'openintro')

#peak at data
head (arbuthnot)

## # A tibble: 6 x 3
##    year  boys girls
##   <int> <int> <int>
## 1  1629  5218  4683
## 2  1630  4858  4457
## 3  1631  4422  4102
## 4  1632  4994  4590
## 5  1633  5158  4839
## 6  1634  5035  4820

Exercise 1

colSums(arbuthnot[ , "girls"])

##  girls 
## 453841

print ("There were 453,841 girls baptized during the years 1629 to 1710")

## [1] "There were 453,841 girls baptized during the years 1629 to 1710"

Exercise 2

By plotting the data we can visually see that the least number of girls baptizes occurred in 1649 through 1651

ggplot(data = arbuthnot, aes(x = year, y = girls) ) +
  geom_line()

Exercise 3

Let’s see the proportion of boys baptized over time for arbuthnot , this time using a bar_plot. Here we see that there were more boys than girls baptised every year during this period.

arbuthnot_prop <- arbuthnot %>%
  mutate(more_boys = boys > girls)

summary(arbuthnot_prop)

##       year           boys          girls      more_boys     
##  Min.   :1629   Min.   :2890   Min.   :2722   Mode:logical  
##  1st Qu.:1649   1st Qu.:4759   1st Qu.:4457   TRUE:82       
##  Median :1670   Median :6073   Median :5718                 
##  Mean   :1670   Mean   :5907   Mean   :5535                 
##  3rd Qu.:1690   3rd Qu.:7576   3rd Qu.:7150                 
##  Max.   :1710   Max.   :8426   Max.   :7779

ggplot(data = arbuthnot_prop, aes( x = more_boys))+
  geom_bar()

Exercise 4

What does present data frame look like. Using the dim function, we see the data frame has 63 rows and 3 columns

data(present)
dim(present)

## [1] 63  3

Exercise 5

colSums(arbuthnot[ , c(2,3)])

##   boys  girls 
## 484382 453841

print ("Between the years 1629 to 1710, there were 484,382 boys baptized and 453,841 girls baptized")

## [1] "Between the years 1629 to 1710, there were 484,382 boys baptized and 453,841 girls baptized"

Exercise 6

what is the proportioon of boys to girls baptized in the present?

present_prop <- present %>%
  mutate(more_boys = boys > girls)

summary(present_prop)

##       year           boys             girls         more_boys     
##  Min.   :1940   Min.   :1211684   Min.   :1148715   Mode:logical  
##  1st Qu.:1956   1st Qu.:1799857   1st Qu.:1711405   TRUE:63       
##  Median :1971   Median :1924868   Median :1831679                 
##  Mean   :1971   Mean   :1885600   Mean   :1793915                 
##  3rd Qu.:1986   3rd Qu.:2058524   3rd Qu.:1965538                 
##  Max.   :2002   Max.   :2186274   Max.   :2082052

ggplot(data = present_prop, aes( x = more_boys))+
  geom_bar()

Exercise 7

Find the maximum number in the boys column

arbuthnot %>%
  summarize (max = max(boys) )

## # A tibble: 1 x 1
##     max
##   <int>
## 1  8426

print("The maximumn number of boys is 8,426")

## [1] "The maximumn number of boys is 8,426"