count species by lake combinations

aggregate.R

# ================================
# helper script for species counts (lakes for Leana)
# ================================
library(data.table)

# read data
lake_data <- fread("links_extract_dt.csv")

# count unique species by combination of `Pond Name`, Town, County
# skip or add column in the "by" section if needed
lake_data[, Species_Num := uniqueN(Names), by = .(`Pond Name`, Town, County)]

# if "Caughts" is zero, then should be no species, so Species_Num = 0 in that case
lake_data[, Species_Num := ifelse(Caughts == 0, yes = 0, no = Species_Num)]

# save results to csv file
write.csv(lake_data, "lake_data.csv", row.names = FALSE)