Parsing SpeciationLib in R
Read google form into R
library(readr)
sheet_id <- "1ryhAjK0FtUys6bOXMtbTDeVjWZ597FcmzyFj9F0b_o0"
gid <- "81549752"
csv_url <- paste0( "https://docs.google.com/spreadsheets/d/", sheet_id, "/export?format=csv&gid=", gid )
speciationlib <- read_csv(csv_url)
Display number of articles associated with each key word
library(dplyr)
library(tidyr)
library(stringr) ​
speciationlib %>% separate_rows(Keywords, sep = ",") %>% mutate(Keywords = str_trim(Keywords)) %>%
count(Keywords, sort = TRUE)
Find all papers by James Mallet.
speciationlib %>% filter(str_detect(Reference, regex("mallet, j", ignore_case = TRUE))) %>% arrange(desc(Publication_year))
produce a date-soted list of all papers associated with keyword
"Speciation genomics" and save to .csv
library(dplyr)
library(tidyr)
library(stringr)
speciation_genomics_papers <- speciationlib %>%
mutate(row_id = row_number()) %>%
separate_rows(Keywords, sep = ",") %>%
mutate(Keywords = str_trim(Keywords)) %>%
filter(Keywords == "Speciation genomics") %>%
distinct(row_id) %>%
left_join(speciationlib %>% mutate(row_id = row_number()),
by = "row_id") %>%
select(-row_id) %>%
arrange(desc(Publication_year))
write.csv(speciation_genomics_papers,"speciation_genomics_papers.csv",row.names = FALSE)
As above, but only Review/perspective papers
library(dplyr)
library(tidyr)
library(stringr)
speciation_genomics_papers <- speciationlib %>%
mutate(row_id = row_number()) %>%
separate_rows(Keywords, sep = ",") %>%
mutate(Keywords = str_trim(Keywords)) %>%
filter(Keywords == "Speciation genomics",`Paper type` == "Review/perspective") %>%
distinct(row_id) %>%
left_join(speciationlib %>% mutate(row_id = row_number()),
by = "row_id") %>%
select(-row_id) %>%
arrange(desc(Publication_year))
write.csv(speciation_genomics_papers,"speciation_genomics_papers.csv",row.names = FALSE)