task 1 import the csv data set into r

salary= read.csv("C:\\Users\\69412\\Desktop\\R\\Professorial Salaries.csv")

task 2 exameine the overall relationship between varuables in the data set using “GGally” package

vars = salary[, c("Rank", "Discipline", "Yrs.since.phd","Yrs.service", "NPubs", "Ncits", "Sex", "Salary")]
library(GGally)
## 载入需要的程辑包：ggplot2
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
ggpairs(data = vars, mapping = aes(color = Sex))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

#### task 3 describe the study population

library(table1)
## 
## 载入程辑包：'table1'
## The following objects are masked from 'package:base':
## 
##     units, units<-
table1(~ Rank + Discipline + Yrs.since.phd +Yrs.service + NPubs + Ncits + Sex, data = salary)
Overall
(N=397)
Rank
AssocProf 64 (16.1%)
AsstProf 67 (16.9%)
Prof 266 (67.0%)
Discipline
A 181 (45.6%)
B 216 (54.4%)
Yrs.since.phd
Mean (SD) 22.3 (12.9)
Median [Min, Max] 21.0 [1.00, 56.0]
Yrs.service
Mean (SD) 17.6 (13.0)
Median [Min, Max] 16.0 [0, 60.0]
NPubs
Mean (SD) 18.2 (14.0)
Median [Min, Max] 13.0 [1.00, 69.0]
Ncits
Mean (SD) 40.2 (16.9)
Median [Min, Max] 35.0 [1.00, 90.0]
Sex
Female 39 (9.8%)
Male 358 (90.2%) 
table1(~ Rank + Discipline + Yrs.since.phd +Yrs.service + NPubs + Ncits | Sex, data = salary)
Female
(N=39)		 Male
(N=358)		 Overall
(N=397)
Rank
AssocProf 10 (25.6%) 54 (15.1%) 64 (16.1%)
AsstProf 11 (28.2%) 56 (15.6%) 67 (16.9%)
Prof 18 (46.2%) 248 (69.3%) 266 (67.0%)
Discipline
A 18 (46.2%) 163 (45.5%) 181 (45.6%)
B 21 (53.8%) 195 (54.5%) 216 (54.4%)
Yrs.since.phd
Mean (SD) 16.5 (9.78) 22.9 (13.0) 22.3 (12.9)
Median [Min, Max] 17.0 [2.00, 39.0] 22.0 [1.00, 56.0] 21.0 [1.00, 56.0]
Yrs.service
Mean (SD) 11.6 (8.81) 18.3 (13.2) 17.6 (13.0)
Median [Min, Max] 10.0 [0, 36.0] 18.0 [0, 60.0] 16.0 [0, 60.0]
NPubs
Mean (SD) 20.2 (14.4) 17.9 (13.9) 18.2 (14.0)
Median [Min, Max] 18.0 [1.00, 50.0] 13.0 [1.00, 69.0] 13.0 [1.00, 69.0]
Ncits
Mean (SD) 40.7 (16.2) 40.2 (17.0) 40.2 (16.9)
Median [Min, Max] 36.0 [14.0, 70.0] 35.0 [1.00, 90.0] 35.0 [1.00, 90.0]