Project Part - 2

cat(“# Section 1: Data Loading and Exploration”)

library(rmarkdown)

level = c(1,2,3,4,5) title = c(‘Dataset Exploration’, ‘Plotting and Visualization’, ‘Model Creation’,‘PCA’,‘Conclusion’ )

for(i in 1:length(level)){ cat(“##”, rep(‘#’, level[i]), title[i],‘’) }

data_frame=read.csv('job.csv')
tail(data_frame)

NA

Dataset Summary

Rows: 215
Columns: 8
$ sl_no           <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14~
$ gender          <chr> "M", "M", "M", "M", "M", "M", "F", "M", "M", ~
$ ssc.grade       <dbl> 67.00, 79.33, 65.00, 56.00, 85.80, 55.00, 46.~
$ hsc.grade       <dbl> 91.00, 78.33, 68.00, 52.00, 73.60, 49.80, 49.~
$ Subject         <chr> "Commerce", "Science", "Arts", "Science", "Co~
$ bachelor.grade  <dbl> 58.00, 77.48, 64.00, 52.00, 73.30, 67.25, 79.~
$ work.experience <chr> "No", "Yes", "No", "No", "No", "Yes", "No", "~
$ status          <chr> "Placed", "Placed", "Placed", "Not Placed", "~

library(plotly)
library(ggplot2)
gg_box_plot=ggplot(data_frame,aes(y=hsc.grade,x=status))+
geom_boxplot(fill=c('red','green'),alpha=0.5)
gg_box_plot

ggplotly(gg_box_plot)