# Q1.R

Oct 28th, 2021
903
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
1. library("openxlsx")
2. library("ggplot2")
3. library("stats")
4.
6. freq <- aggregate(df\$Employment.Status, by=list(df\$Employment.Status), FUN=length)
7. # plot this
8. g1 <- ggplot(freq, aes(x=Group.1, y=x)) + geom_bar(stat="identity") +
9.     scale_x_continuous(breaks=seq(min(freq\$Group.1), max(freq\$Group.1), 1), name="Employment Status") +
10.     scale_y_continuous(breaks=seq(0, max(freq\$x) + 1, 5), name="Frequncy Distribution of Employment Status", expand = c(0, 0))
11.
12.
13. ai <- df[c('AGE', 'Income', 'SEX')]
14. aim = ai[ai\$SEX == 1, ]
15. aif = ai[ai\$SEX == 2, ]
16.
17. aim_g <- aggregate(aim\$Income, by=list(aim\$AGE), FUN=mean)
18. aim_g <- aim_g[order(aim_g\$Group.1), ]
19. # plot this
20. gm <- ggplot(aim_g, aes(x=Group.1, y=x)) + geom_line(stat="identity") + geom_point(stat="identity") +
21.     scale_x_continuous(breaks=seq(min(aim_g\$Group.1), max(aim_g\$Group.1), 1), name="Age") +
22.     scale_y_continuous(breaks=seq(0, max(aim_g\$x) + 1, 100000), name="Income", expand = c(0, 0))
23.
24. aif_g <- aggregate(aif\$Income, by=list(aif\$AGE), FUN=mean)
25. aif_g <- aif_g[order(aif_g\$Group.1), ]
26. gf <- ggplot(aif_g, aes(x=Group.1, y=x)) + geom_line(stat="identity") + geom_point(stat="identity") +
27.     scale_x_continuous(breaks=seq(min(aif_g\$Group.1), max(aif_g\$Group.1), 1), name="Age") +
28.     scale_y_continuous(breaks=seq(0, max(aif_g\$x) + 1, 100000), name="Income", expand=c(0, 0))
29.
30. aix <- aggregate(ai\$Income, by=list(ai\$AGE), FUN=mean)
31. aix <- aix[order(aix\$Group.1), ]
32. gx <- ggplot(aix, aes(x=Group.1, y=x)) + geom_line(stat="identity") + geom_point(stat="identity") +
33.     scale_x_continuous(breaks=seq(min(aix\$Group.1), max(aix\$Group.1), 1), name="Age") +
34.     scale_y_continuous(breaks=seq(min(aix\$x), max(aix\$x) + 1, 5), name="Income", expand=c(0, 0))
35.
36. sd(df\$Hours.worked.per.week)
37. sd(df\$Income)
38.
39. gender_income <- aggregate(df\$Income, by=list(aim\$SEX), FUN=mean)
40. gender_worktime <- aggregate(df\$Length.of.time.at.job , by=list(aim\$SEX), FUN=mean)
41. gender_weeklyhours <- aggregate(df\$Hours.worked.per.week, by=list(aim\$SEX), FUN=mean)
42. gender_schooling <- aggregate(df\$Years.of.secondary.schooling, by=list(aim\$SEX), FUN=mean)
43.
44.
RAW Paste Data