library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.4.2
setwd("C:/Users/ahmetozmen/Desktop/Kaggle Data")
hr_data<-read.csv("HR_comma_sep.csv")

HR Data Analytics columns:

ls(hr_data)
##  [1] "average_montly_hours"  "last_evaluation"      
##  [3] "left"                  "number_project"       
##  [5] "promotion_last_5years" "salary"               
##  [7] "sales"                 "satisfaction_level"   
##  [9] "time_spend_company"    "Work_accident"

HR Data Analytics Summary:

summary(hr_data)  
##  satisfaction_level last_evaluation  number_project  average_montly_hours
##  Min.   :0.0900     Min.   :0.3600   Min.   :2.000   Min.   : 96.0       
##  1st Qu.:0.4400     1st Qu.:0.5600   1st Qu.:3.000   1st Qu.:156.0       
##  Median :0.6400     Median :0.7200   Median :4.000   Median :200.0       
##  Mean   :0.6128     Mean   :0.7161   Mean   :3.803   Mean   :201.1       
##  3rd Qu.:0.8200     3rd Qu.:0.8700   3rd Qu.:5.000   3rd Qu.:245.0       
##  Max.   :1.0000     Max.   :1.0000   Max.   :7.000   Max.   :310.0       
##                                                                          
##  time_spend_company Work_accident         left       
##  Min.   : 2.000     Min.   :0.0000   Min.   :0.0000  
##  1st Qu.: 3.000     1st Qu.:0.0000   1st Qu.:0.0000  
##  Median : 3.000     Median :0.0000   Median :0.0000  
##  Mean   : 3.498     Mean   :0.1446   Mean   :0.2381  
##  3rd Qu.: 4.000     3rd Qu.:0.0000   3rd Qu.:0.0000  
##  Max.   :10.000     Max.   :1.0000   Max.   :1.0000  
##                                                      
##  promotion_last_5years         sales         salary    
##  Min.   :0.00000       sales      :4140   high  :1237  
##  1st Qu.:0.00000       technical  :2720   low   :7316  
##  Median :0.00000       support    :2229   medium:6446  
##  Mean   :0.02127       IT         :1227                
##  3rd Qu.:0.00000       product_mng: 902                
##  Max.   :1.00000       marketing  : 858                
##                        (Other)    :2923

Satisfaction Histogram:

qplot(x=satisfaction_level,data=hr_data)  
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

average_montly_hours Histogram

qplot(x=average_montly_hours,data=hr_data) 
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

I wonder about relationship between salary and average_montly_hours

qplot(x=log10(average_montly_hours),data=hr_data) + facet_wrap(~salary)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

I wonder about relationship between average_montly_hours and satisfaction_level

ggplot(hr_data, aes(satisfaction_level, average_montly_hours)) + geom_point()

Satisfaction level by departmant

ggplot(hr_data, aes(x=factor(sales), y=satisfaction_level)) + stat_summary(fun.y="mean", geom="bar")

Satisfaction level by salary

ggplot(hr_data, aes(x=factor(salary), y=satisfaction_level)) + stat_summary(fun.y="mean", geom="bar")