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
## # … with 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…

arbuthnot$boys

##  [1] 5218 4858 4422 4994 5158 5035 5106 4917 4703 5359 5366 5518 5470 5460 4793
## [16] 4107 4047 3768 3796 3363 3079 2890 3231 3220 3196 3441 3655 3668 3396 3157
## [31] 3209 3724 4748 5216 5411 6041 5114 4678 5616 6073 6506 6278 6449 6443 6073
## [46] 6113 6058 6552 6423 6568 6247 6548 6822 6909 7577 7575 7484 7575 7737 7487
## [61] 7604 7909 7662 7602 7676 6985 7263 7632 8062 8426 7911 7578 8102 8031 7765
## [76] 6113 8366 7952 8379 8239 7840 7640

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.

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

#### the plot above shown there is an increase in the number of girls being baptized from 1629 to 1710

Exercise 3

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

#### it looks like propotions of boys baptized are dropping gradually overtime.

Exercise 4

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

## Rows: 63
## Columns: 3
## $ year  <dbl> 1940, 1941, 1942, 1943, 1944, 1945, 1946, 1947, 1948, 1949, 1950…
## $ boys  <dbl> 1211684, 1289734, 1444365, 1508959, 1435301, 1404587, 1691220, 1…
## $ girls <dbl> 1148715, 1223693, 1364631, 1427901, 1359499, 1330869, 1597452, 1…

Exercise 5

present<-present %>%
  mutate(total=boys+girls)
head(present)

## # A tibble: 6 × 4
##    year    boys   girls   total
##   <dbl>   <dbl>   <dbl>   <dbl>
## 1  1940 1211684 1148715 2360399
## 2  1941 1289734 1223693 2513427
## 3  1942 1444365 1364631 2808996
## 4  1943 1508959 1427901 2936860
## 5  1944 1435301 1359499 2794800
## 6  1945 1404587 1330869 2735456

head(arbuthnot)

## # A tibble: 6 × 6
##    year  boys girls total boys_to_girls_ratio boy_ratio
##   <int> <int> <int> <int>               <dbl>     <dbl>
## 1  1629  5218  4683  9901               0.527     0.527
## 2  1630  4858  4457  9315               0.522     0.522
## 3  1631  4422  4102  8524               0.519     0.519
## 4  1632  4994  4590  9584               0.521     0.521
## 5  1633  5158  4839  9997               0.516     0.516
## 6  1634  5035  4820  9855               0.511     0.511

The values in present dataset are much bigger than arbuthnot by 3 orders of magnitude

Exercise 6

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

#### the boy_ratio is decreasing over time for the present data, different from Arbuthnot’s observation.

Exercise 7

present %>%
  arrange(desc(total))

## # A tibble: 63 × 6
##     year    boys   girls   total boys_to_girls_ratio boys_ratio
##    <dbl>   <dbl>   <dbl>   <dbl>               <dbl>      <dbl>
##  1  1961 2186274 2082052 4268326                1.05      0.512
##  2  1960 2179708 2078142 4257850                1.05      0.512
##  3  1957 2179960 2074824 4254784                1.05      0.512
##  4  1959 2173638 2071158 4244796                1.05      0.512
##  5  1958 2152546 2051266 4203812                1.05      0.512
##  6  1962 2132466 2034896 4167362                1.05      0.512
##  7  1956 2133588 2029502 4163090                1.05      0.513
##  8  1990 2129495 2028717 4158212                1.05      0.512
##  9  1991 2101518 2009389 4110907                1.05      0.511
## 10  1963 2101632 1996388 4098020                1.05      0.513
## # … with 53 more rows