USCOTS

Useful Models

geocode using geoapify

https://www.geoapify.com/tools/geocoding-online/

# A tibble: 6 × 11
  City       Address.x Zip   Institution Primary Affiliation.…¹ Position.x State
  <chr>      <chr>     <chr> <chr>       <chr>                  <chr>      <chr>
1 Northampt… 341 Pros… 1060  Amherst Co… 4-year College         Faculty    MA   
2 <NA>       <NA>      <NA>  Arizona St… 4-year College         Student    AZ   
3 <NA>       <NA>      <NA>  Arizona St… Research Institution   Faculty    AZ   
4 <NA>       <NA>      <NA>  Bucknell U… 4-year College         Faculty    PA   
5 <NA>       <NA>      <NA>  Bucknell U… 4-year College         Other      PA   
6 Los Osos   PO Box 7… 9341… Cal Poly a… 4-year College         Faculty    CA   
# ℹ abbreviated name: ¹​`Primary Affiliation.x`
# ℹ 4 more variables: `Work ZIP/Postal Code` <chr>, region <chr>, lat <dbl>,
#   lon <dbl>

Add regions and arrow end points

#registra <- registr |>
 # filter(Institution != "Other?(not?a?CAUSE?institutional?member")|>
  #rename(count = n) |>
  #mutate(
   # region = case_when(
    #  State %in% c("CT", "ME", "MA", "NH", "RI", "VT", "NJ", "NY", "PA") ~ "Northeast",
     # State %in% c("IL", "IN", "MI", "OH", "WI", "IA", "KS", "MN", "NE", "ND", "SD") ~ "Midwest",
      #State %in% c("DE", "FL", "GA", "MD", "NC", "SC", "VA", "DC", "WV", "AL", "KY", "MI", "TN", "AR", "LA", "OK", "TX", "PR") ~ "South",
      #State %in% c("AZ", "MO", "CO", "ID", "MT", "NV", "NM", "UT", "WY", "AK", "CA", "HI", "OR", "WA") ~ "West",
      #FALSE ~ "Other")
  #)|>
  #filter(!is.na(region))

cause1 <- cause |>
  filter(!is.na(region))

Jitter the points

#cause1$lat_jitter <- jitter(cause1$lat, factor = 0.00001)  # Adjust factor.
#cause1$lon_jitter <- jitter(cause1$lon, factor = 0.00001)

Create a color palette for the regions

library(wesanderson) wes_palette(“FantasticFox1”)

pal <- colorFactor(palette = c("#7538a1","#db8b12","#169bc7", "#c4313d"), 
  domain = cause1$region)

Set the default lat/long for the map

lat <-38.7946 
lon <- -97.5348 
popup = paste0(
        "<b>Institution:</b> ", cause1$Institution, "<br>",
        "<b>City:</b> ", cause1$City, "<br>",
        "<b>State:</b> ", cause1$State, "<br>")

m <- leaflet(data = cause1) |>
  addProviderTiles(providers$Thunderforest.Landscape) |>
  setView(lng = lon, lat = lat, zoom = 3.5) |>
  addTiles() |>
  addMarkers(
      lng = -93.6465, 
      lat = 42.0267,
      label = "ISU")|>
  addCircles(
    color = pal(cause1$region),
    popup = popup,
    radius = 1500,
    opacity = 0.6)|>
  addLegend("bottomright", pal = pal, values = cause1$region,
            title = "Region", opacity = 1) 

Assuming "lon" and "lat" are longitude and latitude, respectively

m

calculate distance from Iowa State U

library(sf)

Warning: package 'sf' was built under R version 4.5.1

Linking to GEOS 3.13.1, GDAL 3.11.0, PROJ 9.6.0; sf_use_s2() is TRUE

df_sf <- st_as_sf(cause1, coords = c("lat", "lon"), crs = 4326)

# 4326 is WGS 84, a common CRS for geographic coordinates
df_sf <- st_set_crs(df_sf, 4326)

Use Haversine formula

library(geosphere)

Warning: package 'geosphere' was built under R version 4.5.1

ames_lon <- -93.616669
ames_lat <- 42.034737
cause1$distance <- distHaversine(
  p1 = cbind(cause1$lon, cause1$lat),
  p2 = c(ames_lon, ames_lat)
)

cause2 <- cause1 |>
  filter(!is.na(distance)) |>
  mutate(distance_miles = distance/1609.344)

Distance Stats

dist <- cause2 |>
  arrange(desc(distance_miles))
dist

# A tibble: 231 × 13
   City      Address.x Zip   Institution Primary Affiliation.…¹ Position.x State
   <chr>     <chr>     <chr> <chr>       <chr>                  <chr>      <chr>
 1 <NA>      <NA>      <NA>  North Caro… Research Institution   Faculty    NC   
 2 <NA>      <NA>      <NA>  The Ohio S… Research Institution   Student    OH   
 3 <NA>      <NA>      <NA>  The Ohio S… Research Institution   Faculty    OH   
 4 <NA>      <NA>      <NA>  The Ohio S… Research Institution   Faculty    OH   
 5 <NA>      <NA>      <NA>  University… Research Institution   Faculty    GA   
 6 <NA>      <NA>      <NA>  University… Research Institution   Student    GA   
 7 <NA>      <NA>      <NA>  University… 4-year College         Faculty    GA   
 8 <NA>      <NA>      <NA>  University… 4-year College         Faculty    GA   
 9 <NA>      <NA>      <NA>  University… Research Institution   Faculty    GA   
10 San Fran… One Mont… 94104 Other (not… Exhibitor              Other      CA   
# ℹ 221 more rows
# ℹ abbreviated name: ¹​`Primary Affiliation.x`
# ℹ 6 more variables: `Work ZIP/Postal Code` <chr>, region <chr>, lat <dbl>,
#   lon <dbl>, distance <dbl>, distance_miles <dbl>

Proportion of Faculty to students for each Primary Affiliation

library(knitr)
library(kableExtra)

Attaching package: 'kableExtra'

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

    group_rows

cause_table <- cause1 |>
  filter(`Primary Affiliation.x` != "Other")|>
  mutate(type = case_when(`Primary Affiliation.x` %in% c("Research Institution", "4-year College") ~ "four-year",
                               `Primary Affiliation.x` == "2-year College" ~ "two-year",
                               TRUE ~ "Other"))|>
  select(type, Position.x) |>
  table()
kbl(cause_table, caption = "Two-Way Table") |> 
  kable_styling() |> 
  row_spec(row = 0, color = "#C41E3A")

Two-Way Table

	Faculty	Other	Student
four-year	183	5	30
Other	0	4	0
two-year	7	0	0

table of states

state_table <- cause1 |>
  group_by(State) |>
  tally() |>
  arrange(desc(n))
kbl(state_table, caption = "Two-Way Table") |> 
  kable_styling() |> 
  row_spec(row = 0, color = "#C41E3A")|>
   column_spec(1, width = "0.5in")

Two-Way Table

State	n
IA	33
CA	28
MN	28
MI	23
NY	19
PA	17
IL	15
NC	15
OH	9
MO	7
GA	5
KY	4
OR	4
MA	3
AZ	2
FL	2
MD	2
MT	2
NJ	2
WI	2
CO	1
IN	1
KS	1
NE	1
NM	1
TX	1
VA	1
VT	1
WA	1