R Notebook

library(readxl)
library(tidyverse)
library(lubridate)
library(plotly)

# Import the three data files
Race_Ethnicity_2020 <- read_excel("./data/Race Ethnicity 2020.xlsx", skip=1) %>% select(-`Continued Claims`, -Area)
Age_Gender_2020 <- read_excel("./data/Age Gender 2020.xlsx", skip=1) %>% select(-`Continued Claims`, -Area)
Continued_Claims_by_Industry_2020 <- read_csv("./data/2020 Continued Claims by Industry.csv", skip=1) %>% select(-Total)

Parsed with column specification:
cols(
  .default = col_double(),
  month = col_character()
)
See spec(...) for full column specifications.

wrangle <- function(x, group) {
  r <- x %>% 
  mutate(
    group = group,
    month = as.Date(paste('01', month,'2020', sep='-'), format='%d-%b-%Y')
  ) %>%
  pivot_longer(cols = c(-group, -month) )
  return(r)
}

race <- wrangle(Race_Ethnicity_2020, 'race')
gender <- wrangle(Age_Gender_2020, 'gender') %>% filter(name %in% c("Male", "Female", "Gender N/A"))
age <- wrangle(Age_Gender_2020, 'age') %>% filter(!name %in% c("Male", "Female", "Gender N/A"))
industry <- wrangle(Continued_Claims_by_Industry_2020, 'industry')

---

Notes

Groups where the January 2020 value was under 100 people are remove to avoid misleading rates of change

---

Gender

Total

gender %>%
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  ggplot(
    aes(
      x = month,
      y = value,
      color = name
    )
  ) +
  geom_line()

Percent change from start of the year

gender %>% 
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  arrange(month) %>% 
  mutate(change = (value - first(value))/ first(value)) %>% 
  ggplot(
    aes(
      x = month,
      y = change,
      color = name
    )
  ) +
  geom_line()

NA
NA

---

Age

Total

age %>%
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  ggplot(
    aes(
      x = month,
      y = value,
      color = name
    )
  ) +
  geom_line()

NA
NA

Percent change from start of the year

age %>% 
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  arrange(month) %>% 
  mutate(change = (value - first(value))/ first(value)) %>% 
  ggplot(
    aes(
      x = month,
      y = change,
      color = name
    )
  ) +
  geom_line()

NA
NA

---

Race

Total

Percent change from start of the year

---

Industry

Total

industry %>% 
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  ggplot(
    aes(
      x = month,
      y = value,
      color = name
    )
  ) +
  geom_line()

NA
NA

Percent change from start of the year

industry %>% 
  group_by(name) %>% 
  filter(100 <= first(value)) %>%
  arrange(month) %>% 
  mutate(change = (value - first(value))/ first(value)) %>% 
  ggplot(
    aes(
      x = month,
      y = change,
      color = name
    )
  ) +
  geom_line()