How to read an occurrence.txt GBIF download and do a basic analysis at species level (n occs, min/max eventDate). Data used in example have been retrieved via https://gist.github.com/damianooldoni/b16608eef989aa17a296adcaa71537e5. GBIF download: https://www.gbif.org/occurrence/download/0104018-230224095556074

gbif_occurrences_basic_analysis.R

library(readr)
library(dplyr)
library(purrr)

# specify your path
occs <- read_tsv("../../0104018-230224095556074_eu_ias_occs.txt",
                 guess_max = 100000, 
                 na = ""
)

occs_info_summary <- occs %>%
  group_by(speciesKey) %>%
  summarise(nObs = n(),
            sumIndividualCount = sum(individualCount),
            firstObs = min(eventDate, na.rm = TRUE),
            lastObs = max(eventDate, na.rm = TRUE)) %>%
  left_join(occs %>%
              distinct(species, speciesKey),
            join_by(speciesKey)) %>%
  # add scientific name of the species as it could be that all occurrences come from subtaxa
  mutate(scientificName = map_chr(.data$speciesKey,
                                  function(x) {
                                    name_usage(x)$data %>% 
                                      pull(scientificName)
                                    })) %>%
  rename(gbifTaxonKey = speciesKey) %>%
  select(gbifTaxonKey, scientificName, 
         nObs, sumIndividualCount, 
         firstObs, lastObs) %>%
  arrange(scientificName)

# save as csv file
occs_info_summary %>% write_csv(file = "eu_ias_info_from_gbif.csv", na = "")