# Load the tidyverse and openintro packages, or libraries.
# Insert code for Exercise 0 here (already done for you)
library(tidyverse)
library(openintro)
Exercise 1
# Print the arbuthnot dataframe, available to us from the openintro package.
# Take a glimpse() of the arbuthnot dataframe.
# Print the girls column/feature/attribute of the arbuthnot dataframe.
# Insert code for Exercise 1 here
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…
arbuthnot$girls
## [1] 4683 4457 4102 4590 4839 4820 4928 4605 4457 4952 4784 5332 5200 4910 4617
## [16] 3997 3919 3395 3536 3181 2746 2722 2840 2908 2959 3179 3349 3382 3289 3013
## [31] 2781 3247 4107 4803 4881 5681 4858 4319 5322 5560 5829 5719 6061 6120 5822
## [46] 5738 5717 5847 6203 6033 6041 6299 6533 6744 7158 7127 7246 7119 7214 7101
## [61] 7167 7302 7392 7316 7483 6647 6713 7229 7767 7626 7452 7061 7514 7656 7683
## [76] 5738 7779 7417 7687 7623 7380 7288
Exercise 2
# Make a ggplot() using the arbuthnot dataframe, with year on the x-axis and girls on the y-axis.
# (Ensure the plot is a combined scatterplot and line graph.)
# Insert code for Exercise 2 here
# geom_point() -> scatterplots
# geom_line() -> line graph
ggplot((data=arbuthnot), aes(x=year, y=girls)) + geom_point()+ geom_line()
Exercise 3
# Mutate() the arbuthnot dataframe in memory such that it has 2 new columns/features/attributes,
# total (boys + girls) and boy_ratio (boys / total).
# Make a line graph plot using the arbuthnot dataframe, with year on the x-axis and total on the y-axis.
# Make a line graph plot using the arbuthnot dataframe, with year on the x-axis and boy_ratio on the y-axis.
# Insert code for Exercise 3 here
arbuthnot<-arbuthnot %>%
mutate(total = girls +boys)
arbuthnot<-arbuthnot %>%
mutate(boy_ratio=boys/total)
ggplot((data=arbuthnot), aes(x=year, y=total)) + geom_line()
ggplot (data=arbuthnot, aes(x=year, y=boy_ratio)) + geom_line()
Exercise 4
# Print the unique() values of the year column/feature/attribute of the present dataframe (e.g., present$year),
# available to us from the openintro package.
# Print the dimensions of the present dataframe.
# Print the column names of the present dataframe.
# Insert code for Exercise 4 here
unique(present$year)
## [1] 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954
## [16] 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969
## [31] 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984
## [46] 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999
## [61] 2000 2001 2002
dim(present)
## [1] 63 3
colnames(present)
## [1] "year" "boys" "girls"
Exercise 5
# Print the mean of the boys column/feature/attribute of the present dataframe, divided by
# the mean of the boys column/feature/attribute of the arbuthnot dataframe.
# Print the mean of the girls column/feature/attribute of the present dataframe, divided by
# the mean of the girls column/feature/attribute of the arbuthnot dataframe.
# Insert code for Exercise 5 here
mean(present$boys)/ mean(arbuthnot$boys)
## [1] 319.2092
mean(present$girls)/ mean(arbuthnot$girls)
## [1] 324.1246
Exercise 6
# Mutate() the present dataframe in memory such that it has 2 new columns/features/attributes,
# total (boys + girls) and boy_ratio (boys / total).
# Make a line graph plot using the present dataframe, with year on the x-axis and total on the y-axis.
# Make a line graph plot using the present dataframe, with year on the x-axis and boy_ratio on the y-axis.
# Insert code for Exercise 6 here
present<-present %>%
mutate(total = boys +girls)
present<-present %>%
mutate(boy_ratio= boys/total)
ggplot(data=present, aes(x=year, y=total)) + geom_line()
ggplot (data=present, aes(x=year, y=boy_ratio)) + geom_line()
Exercise 7
# Arrange() in descending order using desc() the total column/feature/attribute of the present dataframe,
# and print the result.
# Insert code for Exercise 7 here
present%>% arrange(desc(total))
# Knit (or generate) the R Markdown file into a PDF and submit both this .Rmd file and the PDF.