Lab 1: Intro to R

library(tidyverse)
library(openintro)
arbuthnot

## # A tibble: 82 × 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
##  7  1635  5106  4928
##  8  1636  4917  4605
##  9  1637  4703  4457
## 10  1638  5359  4952
## # ℹ 72 more rows

data("arbuthnot")
glimpse(arbuthnot)

## Rows: 82
## Columns: 3
## $ year  <int> 1629, 1630, 1631, 1632, 1633, 1634, 1635, 1636, 1637, 1638, 1639…
## $ boys  <int> 5218, 4858, 4422, 4994, 5158, 5035, 5106, 4917, 4703, 5359, 5366…
## $ girls <int> 4683, 4457, 4102, 4590, 4839, 4820, 4928, 4605, 4457, 4952, 4784…

Exercise 1

arbuthnot$girls

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

From the plot, there is a clear upward trend in the number of girls baptized over the years from the early 1600s to the early 1700s. While there are some fluctuations (notably dips around the mid-1600s and early 1700s), the general pattern shows a steady increase. This suggests that over time, the population in London was growing, leading to more baptisms being recorded.

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

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

Exercise 3

Insert any text here.

arbuthnot$boys + arbuthnot$girls

##  [1]  9901  9315  8524  9584  9997  9855 10034  9522  9160 10311 10150 10850
## [13] 10670 10370  9410  8104  7966  7163  7332  6544  5825  5612  6071  6128
## [25]  6155  6620  7004  7050  6685  6170  5990  6971  8855 10019 10292 11722
## [37]  9972  8997 10938 11633 12335 11997 12510 12563 11895 11851 11775 12399
## [49] 12626 12601 12288 12847 13355 13653 14735 14702 14730 14694 14951 14588
## [61] 14771 15211 15054 14918 15159 13632 13976 14861 15829 16052 15363 14639
## [73] 15616 15687 15448 11851 16145 15369 16066 15862 15220 14928

arbuthnot <- arbuthnot %>%
  mutate(boy_to_girl_ratio = boys / girls)
5218/4683

## [1] 1.114243

arbuthnot <- arbuthnot %>%
  mutate(total = boys + girls)
arbuthnot <- arbuthnot %>%
  mutate(boy_ratio = boys / total)
ggplot(data = arbuthnot, aes(x = year, y = boy_ratio)) +
  geom_line(color = "darkgreen") +
  geom_hline(yintercept = 0.5, linetype = "dashed", color = "red") +
  labs(
    title = "Proportion of Boys Baptized in London (1629–1710)",
    x = "Year",
    y = "Proportion of Boys"
  )

Exercise 4

What years are included in this data set?-1940 to 2002 What are the dimensions of the data frame?-63row and 3 columns What are the variable (column) names?-“year” “boys” “girls”

arbuthnot <- arbuthnot %>%
  mutate(more_boys = boys > girls)
data(present)
head(present)

## # A tibble: 6 × 3
##    year    boys   girls
##   <dbl>   <dbl>   <dbl>
## 1  1940 1211684 1148715
## 2  1941 1289734 1223693
## 3  1942 1444365 1364631
## 4  1943 1508959 1427901
## 5  1944 1435301 1359499
## 6  1945 1404587 1330869

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

## # A tibble: 1 × 2
##     min   max
##   <int> <int>
## 1  2890  8426

present %>% 
  summarize(min_year = min(year),
            max_year = max(year))

## # A tibble: 1 × 2
##   min_year max_year
##      <dbl>    <dbl>
## 1     1940     2002

nrow(present)

## [1] 63

ncol(present)

## [1] 3

colnames(present)

## [1] "year"  "boys"  "girls"

Exercise 5

Arbuthnot’s data shows annual boy births ranging from 2,890 to 8,426, while the present dataset ranges from 121,166 to 2,186,274.The contrast is stark and this stark contrast highlights both population expansion and the evolution of data collection methods over centuries.

present %>%
  summarize(min_boys = min(boys),
            max_boys = max(boys))

## # A tibble: 1 × 2
##   min_boys max_boys
##      <dbl>    <dbl>
## 1  1211684  2186274

arbuthnot %>%
  summarize(min_boys = min(boys),
            max_boys = max(boys))

## # A tibble: 1 × 2
##   min_boys max_boys
##      <int>    <int>
## 1     2890     8426

arb_summary <- arbuthnot %>%
  summarize(min_boys_arb = min(boys),
            max_boys_arb = max(boys))
present_summary <- present %>%
  summarize(min_boys_present = min(boys),
            max_boys_present = max(boys))
comparison <- bind_cols(arb_summary, present_summary)
comparison <- comparison %>%
  mutate(min_ratio = min_boys_present / min_boys_arb,
         max_ratio = max_boys_present / max_boys_arb)

Exercise 6

Insert any text here.

present_prop <- present %>%
  mutate(total_births = boys + girls,
         prop_boys = boys / total_births)
ggplot(present_prop, aes(x = year, y = prop_boys)) +
  geom_line(color = "blue") +
  geom_hline(yintercept = 0.5, linetype = "dashed", color = "red") +
  labs(title = "Proportion of Boys Born in the U.S. Over Time",
       x = "Year",
       y = "Proportion of Boys") +
  theme_minimal()

Exercise 7

We see the most total number of births in the U.S in 1961. total number of births was 4268326.

present <- present %>%
  mutate(total = boys + girls)
present_sorted <- present %>%
  arrange(desc(total))
print(present_sorted)

## # A tibble: 63 × 4
##     year    boys   girls   total
##    <dbl>   <dbl>   <dbl>   <dbl>
##  1  1961 2186274 2082052 4268326
##  2  1960 2179708 2078142 4257850
##  3  1957 2179960 2074824 4254784
##  4  1959 2173638 2071158 4244796
##  5  1958 2152546 2051266 4203812
##  6  1962 2132466 2034896 4167362
##  7  1956 2133588 2029502 4163090
##  8  1990 2129495 2028717 4158212
##  9  1991 2101518 2009389 4110907
## 10  1963 2101632 1996388 4098020
## # ℹ 53 more rows