library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(openintro)
## Loading required package: airports
## Loading required package: cherryblossom
## Loading required package: usdata
data('arbuthnot', package='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
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…

#E.1 What command would you use to extract just the counts of girls baptized? Try it!

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

?ggplot

#Is there an apparent trend in the number of girls baptized over the years? How would you describe it? (To ensure that your lab report is comprehensive, be sure to include the code needed to make the plot as well as your written interpretation.)

#The number of girls baptized over the years has Significantly increased after year 1660. this trend is gradual.

arbuthnot <- arbuthnot %>%
  mutate(total = boys + girls)
ggplot(data = arbuthnot, aes(x = year, y = total)) + 
  geom_line()

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

arbuthnot <- arbuthnot %>%
  mutate(boy_ratio = boys / total)

#E.3 Now, generate a plot of the proportion of boys born over time. What do you see?

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

#the trend shows the ratio is on avg .52. flactuate between .51 - .53

data('present', package='openintro')

#E.4 What years are included in this data set? What are the dimensions of the data frame? What are the variable (column) names?

summary(present)
##       year           boys             girls        
##  Min.   :1940   Min.   :1211684   Min.   :1148715  
##  1st Qu.:1956   1st Qu.:1799857   1st Qu.:1711405  
##  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
dim(present)
## [1] 63  3

E.5 How do these counts compare to Arbuthnot’s? Are they of a similar magnitude?

present %>%
  summarize(min = min(boys), max = max(boys))
## # A tibble: 1 × 2
##       min     max
##     <dbl>   <dbl>
## 1 1211684 2186274
arbuthnot %>%
  summarize(min = min(boys), max = max(boys))
## # A tibble: 1 × 2
##     min   max
##   <int> <int>
## 1  2890  8426
present %>%
  summarize(min = min(girls), max = max(girls))
## # A tibble: 1 × 2
##       min     max
##     <dbl>   <dbl>
## 1 1148715 2082052
arbuthnot %>%
  summarize(min = min(girls), max = max(girls))
## # A tibble: 1 × 2
##     min   max
##   <int> <int>
## 1  2722  7779

#No they are of different magnitude

#E.6 Make a plot that displays the proportion of boys born over time. What do you see? Does Arbuthnot’s observation about boys being born in greater proportion than girls hold up in the U.S.? Include the plot in your response. Hint: You should be able to reuse your code from Exercise 3 above, just replace the dataframe name.

present <- present %>%
  mutate(total = boys + girls)
present <- present %>%
  mutate(boy_ratio = boys / total)
ggplot(data = present, aes(x = year, y = boy_ratio)) + 
  geom_line()

#this ratio is between .512- .514

#E.7 In what year did we see the most total number of births in the U.S.? Hint: First calculate the totals and save it as a new variable. Then, sort your dataset in descending order based on the total column. You can do this interactively in the data viewer by clicking on the arrows next to the variable names. To include the sorted result in your report you will need to use two new functions: arrange (for sorting). We can arrange the data in a descending order with another function: desc (for descending order). The sample code is provided below.

present %>%
  arrange(desc(total))
## # A tibble: 63 × 5
##     year    boys   girls   total boy_ratio
##    <dbl>   <dbl>   <dbl>   <dbl>     <dbl>
##  1  1961 2186274 2082052 4268326     0.512
##  2  1960 2179708 2078142 4257850     0.512
##  3  1957 2179960 2074824 4254784     0.512
##  4  1959 2173638 2071158 4244796     0.512
##  5  1958 2152546 2051266 4203812     0.512
##  6  1962 2132466 2034896 4167362     0.512
##  7  1956 2133588 2029502 4163090     0.513
##  8  1990 2129495 2028717 4158212     0.512
##  9  1991 2101518 2009389 4110907     0.511
## 10  1963 2101632 1996388 4098020     0.513
## # ℹ 53 more rows

year 1961

?present