H1B Visa Application Trends Analysis

Introduction

This report analyzes H1B visa application trends, focusing on gender differences, total applicant trends, and geographic distribution across U.S. states.

Load and Prepare Data

country <- read.csv("/Users/yii/Desktop/H1bTableau/FromTableau/TRK_13139_FY2021.csv++ (Multiple Connections)_Country Codes.csv") %>%
  clean_names()

job <- read.csv("/Users/yii/Desktop/H1bTableau/FromTableau/TRK_13139_FY2021.csv++ (Multiple Connections)_I-129 H1B Job Codes.csv") %>%
  clean_names()

trk <- read.csv("/Users/yii/Desktop/H1bTableau/FromTableau/TRK_13139_FY2021.csv++ (Multiple Connections)_TRK_13139_FY2021.csv") %>%
  clean_names()

Graph 1: Trends by Gender

p1 <- trk %>% 
  filter(gender %in% c("female", "male")) %>%
  group_by(lottery_year, gender) %>%
  summarise(num_of_emp_in_us_sum = sum(num_of_emp_in_us, na.rm = TRUE), .groups = "drop") %>% 
  ggplot(aes(x = lottery_year, y = num_of_emp_in_us_sum, color = gender)) +
  geom_line(linewidth = 1) +
  geom_point(size = 3, shape = 21, fill = "white", stroke = 1) +
  labs(title = "Trends in Applicants of Different Genders", 
       x = "Year of Lottery", 
       y = "Number of Employees in US") +
  theme_classic(base_family = "Arial") +
  theme(
    plot.background = element_rect(fill = "black"),
    panel.background = element_rect(fill = "black"),
    text = element_text(color = "white"),
    axis.text = element_text(color = "white"),
    axis.title = element_text(color = "white"),
    plot.title = element_text(color = "white", size = 16, face = "bold"),
    legend.background = element_rect(fill = "black"),
    legend.text = element_text(color = "white"),
    legend.title = element_text(color = "white")
  )

ggplotly(p1)

Graph 2: Geographic Distribution of Beneficiaries

world_map <- map_data("world")
us_states <- st_read("/Users/yii/Desktop/H1bTableau/us-state-boundaries/us-state-boundaries.shp")

## Reading layer `us-state-boundaries' from data source 
##   `/Users/yii/Desktop/H1bTableau/us-state-boundaries/us-state-boundaries.shp' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 56 features and 20 fields
## Geometry type: MULTIPOLYGON
## Dimension:     XY
## Bounding box:  xmin: -179.2311 ymin: -14.60181 xmax: 179.8597 ymax: 71.44069
## Geodetic CRS:  WGS 84

state_table <- read.csv("/Users/yii/Desktop/H1bTableau/state_abb.csv")

state_abb <- state_table %>%
  filter(Status.of.region %in% c("State","Federal district",
                                 "Insular area (Commonwealth)",
                                 "Insular area (Territory)",
                                 "US military mail code")) %>%
  mutate(pet_state = ANSI, name = Name) %>%
  select(pet_state, name)

trk_map <- trk %>%
  filter(gender %in% c("female", "male")) %>%
  filter(pet_state != "") %>%
  group_by(pet_state) %>%
  summarise(number_of_beneficiaries_sum = sum(number_of_beneficiaries, na.rm = TRUE), .groups = "drop")

merged_map <- trk_map %>%
  left_join(state_abb, by = "pet_state") %>%
  left_join(us_states, by = "name") %>%
  drop_na() %>%
  st_as_sf() %>%
  mutate(centroid = st_centroid(geometry))

p3 <- ggplot() +
  geom_polygon(data = world_map, aes(x = long, y = lat, group = group), fill = "lightgray", color = "white") +
  geom_sf(data = merged_map, aes(fill = number_of_beneficiaries_sum), color = "lightgray") +
  scale_fill_gradient(low = "#bfa554", high = "#994926") +
  labs(title = "H1B Applications in Different States", fill = "Number of Beneficiaries") +
  geom_text(aes(x = st_coordinates(merged_map$centroid)[,1],
                y = st_coordinates(merged_map$centroid)[,2],
                label = merged_map$pet_state), size = 3, color = "white") +
  coord_sf(xlim = c(-170, -65), ylim = c(20, 70)) +
  theme_void(base_family = "Arial") +
  theme(
    plot.background = element_rect(fill = "black", color = NA),
    panel.background = element_rect(fill = "black", color = NA),
    plot.title = element_text(size = 16, color = "white", face = "bold"),
    axis.ticks = element_blank(), 
    axis.line = element_blank(),  
    legend.position = "right",
    legend.title = element_text(size = 10, face = "bold", color = "white"),
    legend.text = element_text(size = 8, color = "white"),
    legend.key.size = unit(0.2, "cm"),
    legend.key.width = unit(0.5, "cm"),
    legend.key.height = unit(0.5, "cm"),
    legend.spacing.y = unit(0.1, "cm")
  ) +
  theme(
    plot.background = element_rect(fill = "black"),
    panel.background = element_rect(fill = "black"),
    plot.title = element_text(size = 16, color = "white", face = "bold"),
    legend.position = "right",
    legend.title = element_text(size = 10, color = "white", face = "bold"),
    legend.text = element_text(size = 8, color = "white"),
    legend.key.size = unit(0.2, "cm"),
    legend.key.width = unit(0.5, "cm"),
    legend.key.height = unit(0.5, "cm")
  )

ggplotly(p3)

Conclusion

This analysis provides insights into H1B application trends by gender, application volume, and geographic distribution across the United States. Future work could include analysis by occupation or salary levels.