filter-missing-size-md5.R

library(tidyr)
library(dplyr)
library(readr)
library(synapser)
synLogin()

id <- 'syn19034850'

obj <- synGet(id)
d <- readr::read_csv(obj$path)
d <- d %>% mutate(missing_size = (size == 0),
                          missing_md5 = (md5sum == "None"))
d_missing <- d %>% filter(missing_size | missing_md5)

d_summary <- d_missing %>% 
  group_by(submission_id) %>% 
  summarize(n_missing_size=sum(missing_size), 
            n_missing_md5=sum(missing_md5)) %>% 
  arrange(submission_id)

readr::write_csv(d_missing, path = "/tmp/missing-file-info.csv")
readr::write_csv(d_summary, path = "/tmp/summary-missing-file-info.csv")