Data
employed <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-23/employed.csv")
employed_grouped <- employed %>%
filter(!is.na(employ_n)) %>%
group_by(occupation = paste(industry, minor_occupation), race_gender) %>%
summarise(n = sum(employ_n)) %>%
ungroup()
employed_tidy <- employed_grouped %>%
# Remove total category
filter(race_gender != "TOTAL") %>%
# Add total column
left_join(employed_grouped %>%
filter(race_gender == "TOTAL") %>%
select(occupation, total = n)) %>%
# Get pct in total
mutate(pct= n / total) %>%
# Remove outliers
filter(total > 1000) %>%
select(-n)
employed_tidy
## # A tibble: 1,160 × 4
## occupation race_gender total pct
## <chr> <chr> <dbl> <dbl>
## 1 Agriculture and related Construction and extractio… Asian 7.3 e4 0.0274
## 2 Agriculture and related Construction and extractio… Black or A… 7.3 e4 0.0822
## 3 Agriculture and related Construction and extractio… Men 7.3 e4 0.973
## 4 Agriculture and related Construction and extractio… White 7.3 e4 0.863
## 5 Agriculture and related Construction and extractio… Women 7.3 e4 0.0274
## 6 Agriculture and related Farming, fishing, and fore… Asian 5.74e6 0.0139
## 7 Agriculture and related Farming, fishing, and fore… Black or A… 5.74e6 0.0342
## 8 Agriculture and related Farming, fishing, and fore… Men 5.74e6 0.789
## 9 Agriculture and related Farming, fishing, and fore… White 5.74e6 0.911
## 10 Agriculture and related Farming, fishing, and fore… Women 5.74e6 0.211
## # ℹ 1,150 more rows
employed_standard <- employed_tidy %>%
# Standardize
group_by(race_gender) %>%
mutate(pct = pct %>% scale() %>% as.numeric()) %>%
ungroup() %>%
mutate(total = total %>% log() %>% scale() %>% as.numeric())
employed_standard
## # A tibble: 1,160 × 4
## occupation race_gender total pct
## <chr> <chr> <dbl> <dbl>
## 1 Agriculture and related Construction and extractio… Asian -1.30 -0.539
## 2 Agriculture and related Construction and extractio… Black or A… -1.30 -0.405
## 3 Agriculture and related Construction and extractio… Men -1.30 1.31
## 4 Agriculture and related Construction and extractio… White -1.30 0.725
## 5 Agriculture and related Construction and extractio… Women -1.30 -1.30
## 6 Agriculture and related Farming, fishing, and fore… Asian 0.819 -0.928
## 7 Agriculture and related Farming, fishing, and fore… Black or A… 0.819 -1.21
## 8 Agriculture and related Farming, fishing, and fore… Men 0.819 0.510
## 9 Agriculture and related Farming, fishing, and fore… White 0.819 1.38
## 10 Agriculture and related Farming, fishing, and fore… Women 0.819 -0.503
## # ℹ 1,150 more rows
occupation_demo_tb1 <- employed_tidy %>%
pivot_wider(names_from = race_gender, values_from = pct) %>%
janitor::clean_names()
occupation_demo_tb1
## # A tibble: 232 × 7
## occupation total asian black_or_african_ame…¹ men white women
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Agriculture and rel… 7.3 e4 0.0274 0.0822 0.973 0.863 0.0274
## 2 Agriculture and rel… 5.74e6 0.0139 0.0342 0.789 0.911 0.211
## 3 Agriculture and rel… 1.94e5 0.0155 0.0309 0.985 0.918 0.0103
## 4 Agriculture and rel… 1.01e6 0.00992 0.00794 0.739 0.967 0.261
## 5 Agriculture and rel… 5.22e6 0.00997 0.00882 0.741 0.962 0.259
## 6 Agriculture and rel… 5.15e5 0.0233 0.0155 0.159 0.938 0.841
## 7 Agriculture and rel… 2.11e5 0.0332 0.104 0.815 0.820 0.185
## 8 Agriculture and rel… 2.95e5 0.0339 0.0373 0.675 0.902 0.329
## 9 Agriculture and rel… 8.80e4 0 0.0682 0.864 0.875 0.136
## 10 Agriculture and rel… 9.40e4 0 0.0213 0.585 0.968 0.426
## # ℹ 222 more rows
## # ℹ abbreviated name: ¹black_or_african_american
occupation_cluster <- kmeans(occupation_demo_tb1 %>% select(-occupation), centers = 3, nstart = 20)
summary(occupation_cluster)
## Length Class Mode
## cluster 232 -none- numeric
## centers 18 -none- numeric
## totss 1 -none- numeric
## withinss 3 -none- numeric
## tot.withinss 1 -none- numeric
## betweenss 1 -none- numeric
## size 3 -none- numeric
## iter 1 -none- numeric
## ifault 1 -none- numeric
tidy(occupation_cluster)
## # A tibble: 3 × 9
## total asian black_or_african_ame…¹ men white women size withinss cluster
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <dbl> <fct>
## 1 1.80e6 0.0424 0.104 0.693 0.816 0.305 198 8.13e14 1
## 2 5.41e7 0.0654 0.124 0.533 0.774 0.467 8 4.86e15 2
## 3 1.47e7 0.0684 0.120 0.554 0.779 0.446 26 5.46e14 3
## # ℹ abbreviated name: ¹black_or_african_american
glance(occupation_cluster)
## # A tibble: 1 × 4
## totss tot.withinss betweenss iter
## <dbl> <dbl> <dbl> <int>
## 1 3.00e16 6.22e15 2.37e16 3
augment(occupation_cluster, occupation_demo_tb1) %>%
ggplot(aes(total, asian, color = .cluster)) +
geom_point()
kclusts <- tibble(k = 1:9) %>%
mutate(kclust = map(.x = k, .f = ~ kmeans(occupation_demo_tb1 %>% select(-occupation), centers = .x, nstart = 20)),
glanced = map(.x = kclust, .f = glance))
kclusts %>%
unnest(glanced) %>%
ggplot(aes(k, tot.withinss)) +
geom_point() +
geom_line()
final_cluster <- kmeans(occupation_demo_tb1 %>% select(-occupation), centers = 5, nstart = 20)
augment(final_cluster, occupation_demo_tb1) %>%
ggplot(aes(total, asian, color = .cluster)) +
geom_point()
umap_results <- occupation_demo_tb1 %>%
select(-occupation) %>%
umap()
umap_results_tb1 <- umap_results$layout %>%
as.tibble() %>%
bind_cols(occupation_demo_tb1 %>% select(occupation))
umap_results_tb1
## # A tibble: 232 × 3
## V1 V2 occupation
## <dbl> <dbl> <chr>
## 1 -5.24 -6.42 Agriculture and related Construction and extraction occupations
## 2 -2.64 6.30 Agriculture and related Farming, fishing, and forestry occupat…
## 3 -1.18 -3.52 Agriculture and related Installation, maintenance, and repair …
## 4 7.50 -0.648 Agriculture and related Manage-ment, business, and financial o…
## 5 -2.14 6.21 Agriculture and related Management, business, and financial op…
## 6 4.16 -3.78 Agriculture and related Office and administrative support occu…
## 7 -0.905 -3.56 Agriculture and related Production occupations
## 8 1.07 -3.68 Agriculture and related Professional and related occupations
## 9 -5.26 -6.24 Agriculture and related Protective service occupations
## 10 -5.21 -6.02 Agriculture and related Sales and related occupations
## # ℹ 222 more rows
umap_results_tb1 %>%
ggplot(aes(V1, V2)) +
geom_point()
kmeans_umap_tb1 <- final_cluster %>%
augment(occupation_demo_tb1) %>%
select(occupation, .cluster) %>%
# Add umap results
left_join(umap_results_tb1) %>%
# Add employment info
left_join(employed_tidy %>%
select(-total) %>%
pivot_wider(names_from = race_gender, values_from = pct) %>%
janitor::clean_names())
kmeans_umap_tb1
## # A tibble: 232 × 9
## occupation .cluster V1 V2 asian black_or_african_ame…¹ men white
## <chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Agricultur… 5 -5.24 -6.42 0.0274 0.0822 0.973 0.863
## 2 Agricultur… 4 -2.64 6.30 0.0139 0.0342 0.789 0.911
## 3 Agricultur… 5 -1.18 -3.52 0.0155 0.0309 0.985 0.918
## 4 Agricultur… 5 7.50 -0.648 0.00992 0.00794 0.739 0.967
## 5 Agricultur… 4 -2.14 6.21 0.00997 0.00882 0.741 0.962
## 6 Agricultur… 5 4.16 -3.78 0.0233 0.0155 0.159 0.938
## 7 Agricultur… 5 -0.905 -3.56 0.0332 0.104 0.815 0.820
## 8 Agricultur… 5 1.07 -3.68 0.0339 0.0373 0.675 0.902
## 9 Agricultur… 5 -5.26 -6.24 0 0.0682 0.864 0.875
## 10 Agricultur… 5 -5.21 -6.02 0 0.0213 0.585 0.968
## # ℹ 222 more rows
## # ℹ abbreviated name: ¹black_or_african_american
## # ℹ 1 more variable: women <dbl>
final <- kmeans_umap_tb1 %>%
# create text label
mutate(text_label = str_glue("Occupation: {occupation}
Cluster: {.cluster}
Asian: {asian %>% scales::percent(1)}
Women: {women %>% scales::percent(1)}")) %>%
#plot
ggplot(aes(V1, V2, color = .cluster, text = text_label)) +
geom_point()