Lab 1: Intro to R

library(tidyverse)
library(openintro)

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

Plotting baptism data of girls over years using line graph

qplot(x = year, y = girls, data = arbuthnot, geom = "line")

print("We see a decline in between 1650 to 1660 and then afterwards there is an increase in number of girls baptized.")

## [1] "We see a decline in between 1650 to 1660 and then afterwards there is an increase in number of girls baptized."

Exercise 3

Boys proportion

prop_boys = arbuthnot$boys / (arbuthnot$boys + arbuthnot$girls)
plot(arbuthnot$year, prop_boys, type = "l")

print("From the graph we can see the proportion of boys getting baptized over years is almost steady.")

## [1] "From the graph we can see the proportion of boys getting baptized over years is almost steady."

Exercise 4

Analyse present dataframe

#Years present in the frame
print("Years present in the frame are : ")

## [1] "Years present in the frame are : "

range(present$year)

## [1] 1940 2002

#dimension of the frame
print("Dimension of the frame are : ")

## [1] "Dimension of the frame are : "

dim(present)

## [1] 63  3

#Column names of the frame
print("Column names of the frame are :")

## [1] "Column names of the frame are :"

names(present)

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

Exercise 5

Arbuthnot and present dataframe - count compare

mean(arbuthnot$boys + arbuthnot$girls)

## [1] 11441.74

mean(present$boys + present$girls)

## [1] 3679515

print("We see from the mean of both dataframes that they are not on same magnitude")

## [1] "We see from the mean of both dataframes that they are not on same magnitude"

Exercise 6

Boys proportion in present dataframe

prop_boys = present$boys / (present$boys + present$girls)
plot(present$year, prop_boys, type = "l")

print("Arbuthnot’s observation about boys being born in greater proportion than girls doesnt hold up in the U.S. as per this plot.")

## [1] "Arbuthnot’s observation about boys being born in greater proportion than girls doesnt hold up in the U.S. as per this plot."

Exercise 7

Highest birh rate year

present <- present %>%
        mutate(total = boys + girls)
present <- present %>%
        arrange(desc(total))
plot( present$year,present$total,type = "l")

paste("Highest bith rate was recorded in ", present$year[(present$boys + present$girls) == max(present$boys + present$girls)])

## [1] "Highest bith rate was recorded in  1961"