Occupational Data Graphs

Initial Setup

#including libs
library(dplyr)
library(ggplot2)

#importing data
occupation <- read.csv("occupation_data.csv")


occupation_complete <- occupation[complete.cases(occupation),]
#removing all null values
cleandata <- occupation[complete.cases(occupation),]

#filter data for office workers only
just_office <- cleandata %>% filter(occupation_category == "OFFICE")

Printout of Number of Categories

#print count of occ_category
table(occupation_complete$occupation_category)

           AGRICULTURAL                    ARTS                BUSINESS           COMPUTATIONAL 
                      1                       3                      12                       7 
               CULINARY               EDUCATION             ENGINEERING          GROUNDSKEEPING 
                      7                       4                       2                       3 
HEALTHCARE PROFESSIONAL      HEALTHCARE SUPPORT                   LEGAL              MANAGEMENT 
                      7                       1                       1                      16 
                 OFFICE              PRODUCTION      PROTECTIVE SERVICE                   SALES 
                     17                      11                       3                      11 
                SCIENCE                 SERVICE          SOCIAL SERVICE          TRANSPORTATION 
                      3                       3                       3                       4 

#using a frequency table to assess the number of categories 

Print Graph N1

this graph shows the distribution of earnings for each category

hist(occupation_complete$All_weekly, breaks = 40, col = "lightpink", main = "Distribution of Earnings - All Categories",
     xlab = "Weekly Earnings", ylab = "Frequency")

Print Histogram

#HISTOGRAM--visualizes the distribution of earnings within the category for both genders

management <- occupation_complete %>% filter(occupation_category %in% ("MANAGEMENT")) #filtering management occupations only
management_earnings <- management$All_weekly #saving the values in a vector as reference

hist(management$All_weekly, breaks = 10, col = "lightyellow", main = "Distribution of Earnings - Management",
     xlab = "Weekly Earnings", ylab = "Frequency")

#the data points all appear to fall into the same range of frequency!

#Bar Plot--investigates the gender balance across different occupations within the category

#sum the counts of females & males
female_count <- sum(management$F_workers) 
male_count <- sum(management$M_workers)

#create a data frame with gender counts
gender_data <- data.frame(Gender = c("Female", "Male"),
                          Count = c(female_count, male_count))

ggplot(data = gender_data, aes(x = Gender, y = Count, fill = Gender)) +
  geom_bar(stat = "identity", width = 0.6) +
  labs(title = "Gender Balance in Management",
       x = "Gender", y = "Count") +
  scale_fill_manual(values = c("pink", "skyblue")) +
  theme_minimal()