Department and Salaries Percentage

# Load ggplot2
library(ggplot2)
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)

## 
## 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

library(readr)

# Data

hr <- read_csv("~/Documents/UNH/Semester-2/Data_Visu_Comm/Assignments/Assignment1_4thFeb/HR_comma_sep.csv")

## Rows: 14999 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): sales, 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.

hr_ql <- hr %>% 
  group_by(sales) %>% 
  tally() %>% # summarized data
  ungroup() %>% 
  arrange(desc(sales)) %>%
  mutate(prop = n / sum(n) *100) %>% # Created variables for ploting and label
  mutate(ypos = cumsum(prop)- 0.5*prop ,
         label = paste0(sales , ' Department', '\n' ,round(prop , digits = 1) , '%') ,
         label_plotly = paste0('Department: ' , sales))

## 1. Using the HR_comma_sep dataset, create a pie chart for the variable sales.


ggplot(hr_ql, aes(x="", y=prop, fill=as.factor(sales))) +
  geom_bar(stat="identity", width=1) +
  coord_polar("y", start=0) + # Up to here: basic pie chart
  theme_void() + # White background
  theme(legend.position="none") + # position of labels
  geom_text(aes(y = ypos, label = as.factor(label)), 
            color = "black", 
            size=3) + # adding the labels
  scale_fill_brewer(palette="Set1") # color set

## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Set1 is 9
## Returning the palette you asked for with that many colors

## 2. Using the HR_comma_sep dataset, create a pie chart for the variable salary.

hr_q2 <- hr %>% 
  group_by(salary) %>% 
  tally() %>% # summarized data
  ungroup() %>% 
  arrange(desc(salary)) %>%
  mutate(prop = n / sum(n) *100) %>% # Created variables for ploting and label
  mutate(ypos = cumsum(prop)- 0.5*prop ,
         label = paste0(salary , ' salary', '\n' ,round(prop , digits = 1) , '%') ,
         label_plotly = paste0('salary: ' , salary))



ggplot(hr_q2, aes(x="", y=prop, fill=as.factor(salary))) +
  geom_bar(stat="identity", width=1) +
  coord_polar("y", start=0) + # Up to here: basic pie chart
  theme_void() + # White background
  theme(legend.position="none") + # position of labels
  geom_text(aes(y = ypos, label = as.factor(label)), 
            color = "white", 
            size=3) + # adding the labels
  scale_fill_brewer(palette="Set1") # color set