Assignment 5

Data Import

This data was acquired from https://data.london.gov.uk/dataset/jobs-by-age-and-gender and includes a notation that it has a UK Open Government Licence.

library(tidyverse)
jobs <- read_csv("jobs_by_age_and_gender.csv")
head(jobs)

## # A tibble: 6 x 6
##   date              age   gender     all_people full_time part_time
##   <chr>             <chr> <chr>           <dbl>     <dbl>     <dbl>
## 1 Apr 2004-Mar 2005 16-19 All People      86900     35800     51100
## 2 Apr 2004-Mar 2005 16-19 Female          45600     16300     29300
## 3 Apr 2004-Mar 2005 16-19 Male            41300     19400     21800
## 4 Apr 2004-Mar 2005 16-64 All People    3819100   3131700    684300
## 5 Apr 2004-Mar 2005 16-64 Female        1644900   1145300    497400
## 6 Apr 2004-Mar 2005 16-64 Male          2174200   1986300    187000

Tidy Data

Data was filtered to look at employment across all ages by gender over year long periods.

library(dplyr)

# Examine by gender 
gender_groups <- jobs %>% 
  filter(gender %in% c("Male", "Female"), age == "16-64", str_detect(date,"Jan."))

Employment by Age and Gender for 2019

age_groups <- jobs %>% 
  filter(gender %in% c("Male", "Female"), str_detect(date,"Jan."), str_detect(date,".2019"), age != "16-64") %>%
  group_by(gender, age) %>%
  mutate(gender = factor(gender)) %>%
  arrange(gender) 

names(age_groups) <- c("Date", "Age Group", "Gender", "Full-time", "Part-time")

Looking at the most recent year, grouped by gender, I noticed that males and females seems to have different patterns in whether greater numbers of people are employed in part-time or full-time work.

## 
## Attaching package: 'kableExtra'

## The following object is masked from 'package:dplyr':
## 
##     group_rows

Gender	Age Group	Full-time	Part-time
Female
Female	16-19	40100	13100
Female	20-24	183500	126600
Female	25-49	1513400	1099600
Female	50+	584800	340800
Male
Male	16-19	30800	9200
Male	20-24	190100	149500
Male	25-49	1927200	1793600
Male	50+	753500	620300

Examine Full-time Employment Trends Over Time

Given the observation from Table 1, plot one was created to look at full-time employment by gender of the last 10 years.

library(ggplot2)

  
# Plot
gender_groups %>%  tail(20) %>%
  ggplot( aes(x=date, y=full_time, group=gender, color=gender)) +
    geom_line() +
    ggtitle("Full Time Employment Trends by Gender") +
    theme_light() +
    ylab("Number Employed") + xlab("Time Period") + theme(axis.text.x = element_text(angle = 40))

Examine Part-time Employment Trends Over Time

Plot two was created to look at full-time employment by gender of the last 10 years.

options(scipen = 999) 
gender_groups %>%  tail(20) %>%
  ggplot( aes(x=date, y=part_time, group=gender, color=gender)) +
    geom_line() +
    ggtitle("Part-time Employment Trends by Gender") +
    theme_light() +
    ylab("Number Employed") + xlab ("Time Period") + theme(axis.text.x = element_text(angle = 40))

Observations

These two plots indicate that further investigation into the higher amounts of part-time work for those who identify as female versus those who identify as male and the reverse phenomenon in full-time work would be warranted.