library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(plotly)
## Loading required package: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')
## Rows: 14999 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Department, salary
## dbl (8): satisfaction_level, last_evaluation, number_project, average_montly...
##
## 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.
chisq.test(hr$Work_accident, hr$left)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$Work_accident and hr$left
## X-squared = 357.56, df = 1, p-value < 2.2e-16
The p-value is a very small, that means that the probability of these results being random is very small. There is a dependence between work accidents and if the employee left or did not leave.
Those who did not have a work accident are more likely to leave.
prop_data <- hr %>%
group_by(Work_accident) %>%
summarise(
Not_left = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_data) %>%
add_bars(x = ~Work_accident, y = ~Not_left, name = "Not Left",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Work_accident, y = ~Left, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Work Accidents"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Those who did not have a work accident are more likely to leave."
)
chisq.test(hr$promotion_last_5years, hr$left)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$promotion_last_5years and hr$left
## X-squared = 56.262, df = 1, p-value = 6.344e-14
The p-value is a very small, that means that the probability of these results being random is very small. There is a dependence between promotions and if the employee left or did not leave.
Those who did not have a promotion are more likely to leave.
prop_data <- hr %>%
group_by(promotion_last_5years) %>%
summarise(
Not_left = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_data) %>%
add_bars(x = ~promotion_last_5years, y = ~Not_left, name = "Not Left",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~promotion_last_5years, y = ~Left, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Promotions Last 5 Years"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Those who did not have a promotion are more likely to leave."
)
chisq.test(hr$Department,hr$left)
##
## Pearson's Chi-squared test
##
## data: hr$Department and hr$left
## X-squared = 86.825, df = 9, p-value = 7.042e-15
The p-value is a very small, that means that the probability of these results being random is very small. There is a dependence between department and if the employee left or did not leave.
Those who work in HR are most likely to leave.
prop_data <- hr %>%
group_by(Department) %>%
summarise(
Not_left = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_data) %>%
add_bars(x = ~Department, y = ~Not_left, name = "Not Left",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Department, y = ~Left, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Those who work in HR are most likely to leave."
)
chisq.test(hr$salary, hr$left)
##
## Pearson's Chi-squared test
##
## data: hr$salary and hr$left
## X-squared = 381.23, df = 2, p-value < 2.2e-16
The p-value is a very small, that means that the probability of these results being random is very small. There is a dependence between salary and if the employee left or did not leave.
Those who have a low salary are most likely to leave.
prop_data <- hr %>%
group_by(salary) %>%
summarise(
Not_left = sum(left == 0) / n(),
Left = sum(left == 1) / n()
)
plot_ly(prop_data) %>%
add_bars(x = ~salary, y = ~Not_left, name = "Not Left",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~salary, y = ~Left, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Salary"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Those who have a low salary are most likely to leave."
)