Task 1

library(readr)
salary<- read_csv("C:/Users/24928614/Downloads/Professorial Salaries.csv")
## Rows: 397 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Rank, Discipline, Sex
## dbl (6): ID, Yrs.since.phd, Yrs.service, NPubs, Ncits, Salary
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
head(salary)
## # A tibble: 6 × 9
##      ID Rank      Discipline Yrs.since.phd Yrs.service Sex   NPubs Ncits Salary
##   <dbl> <chr>     <chr>              <dbl>       <dbl> <chr> <dbl> <dbl>  <dbl>
## 1     1 Prof      B                     19          18 Male     18    50 139750
## 2     2 Prof      B                     20          16 Male      3    26 173200
## 3     3 AsstProf  B                      4           3 Male      2    50  79750
## 4     4 Prof      B                     45          39 Male     17    34 115000
## 5     5 Prof      B                     40          41 Male     11    41 141500
## 6     6 AssocProf B                      6           6 Male      6    37  97000

##Task2

library(ggplot2)
p = ggplot(data = salary, aes(x = Salary))
p1 = p + geom_histogram(color = "white", fill = "blue")
p1
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

p = ggplot(data = salary, aes(x = Salary))
p1 = p + geom_histogram(color = "white", fill = "blue")
p2 = p + geom_histogram(aes(y = ..density..), color = "white", fill = "blue")
p2 = p2 + geom_density(col="red")
library(gridExtra)
library(grid)
grid.arrange(p1, p2, nrow = 2, top = textGrob("Distribution of professors' salaries by sex", gp = gpar(fontsize = 20, font = 1)))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

p = ggplot(data = salary, aes(x = Salary, fill = Sex))
p1 = p + geom_histogram(position = "dodge") 
p2 = ggplot(data = salary, aes(x = Salary, fill = Sex, color = Sex)) + geom_density(alpha = 0.1)

grid.arrange(p1, p2, nrow = 2, top = textGrob("Distribution of professors' salaries by sex", gp = gpar(fontsize = 20, font = 1)))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Task 3

p = ggplot(data = salary, aes(x = Rank, fill = Rank, col = Rank))
p1 = p + geom_bar(position = "dodge")

salary$Prof.Rank = factor(salary$Rank, levels = c("AsstProf", "AssocProf", "Prof"))
p = ggplot(data = salary, aes(x = Prof.Rank, fill = Prof.Rank, col = Prof.Rank))
p2 = p + geom_bar(position = "dodge")

grid.arrange(p1, p2, nrow = 2, top = textGrob("Distribution of professors' rank", gp = gpar(fontsize = 20, font = 1)))

p = ggplot(data = salary, aes(x = Prof.Rank, fill = Sex, col = Sex))
p1 = p + geom_bar(position = "dodge")
p1 + ggtitle("Distribution of professors' rank by sex")

library(dplyr)
## 
## Attaching package: 'dplyr'
## The following object is masked from 'package:gridExtra':
## 
##     combine
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
p = ggplot(salary %>% count(Prof.Rank, Sex) %>% mutate(pct = n/sum(n)), aes(factor(Prof.Rank), n, fill = Sex))
p = p + geom_bar(stat ="identity")
p = p + geom_text(aes(label = paste0(sprintf("%1.1f", pct*100),"%")), position = position_stack(vjust=0.5))
p + labs(x = "Professors' ranks", y = "Number of cases") + ggtitle("Professors' rank by sex")

Task 4

p = ggplot(data = salary, aes(x = Sex,  y = Salary, fill = Sex, col = Sex))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) 
p1 + labs(x = "Sex", y = "Salaries (USD)") + ggtitle("Professors' salaries by sex") + theme_bw()

p = ggplot(data = salary, aes(x = Prof.Rank,  y = Salary, fill = Prof.Rank, col = Prof.Rank))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) 
p1 + labs(x = "Rank", y = "Salaries (USD)") + ggtitle("Professors' salaries by rank") + theme_bw()

p = ggplot(data = salary, aes(x = Prof.Rank,  y = Salary, fill = Sex, col = Sex))
p1 = p + geom_boxplot(col = "black") + geom_jitter(alpha = 0.05) 
p1 + labs(x = "Professors' Ranks", y = "Salaries (USD)") + ggtitle("Professors' salaries by rank and sex") + theme_bw()

Task 5

p = ggplot(data = salary, aes(x = Yrs.service, y = Salary))
p1 = p + geom_point() + geom_smooth() + labs(x = "Time in service (years)", y = "Professors' salaries (USD)") + ggtitle("Correlation between professors' salaries and time in service") + theme_bw()
p1
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'

p = ggplot(data = salary, aes(x = Yrs.service, y = Salary, fill = Sex, col = Sex))
p2 = p + geom_point() + geom_smooth(method = "lm", formula = y ~ x + I(x^2) + I(x^3)) + labs(x = "Time in service (years)", y = "Professors' salaries (USD)") + ggtitle("Correlation between professors' salaries and time in service by sex") + theme_bw()
p2