Merge pull request #10 from trias-project/craete-new-cubes-with-kingdom

Craete new cubes with kingdom

Author: damianooldoni

data/raw/gbif_downloads.tsv

@@ -1,10 +1,13 @@
 gbif_download_key	input_checklist	gbif_download_created	gbif_download_status	gbif_download_doi
-0003809-190415153152247	NA	2019-04-24 17:52:31	SUCCEEDED	https://doi.org/10.15468/dl.7gwm6j
-0008507-190621201848488	NA	2019-07-09 08:31:24	SUCCEEDED	https://doi.org/10.15468/dl.1eycss
-0030713-190918142434337	NA	2019-10-28 09:05:48	SUCCEEDED	https://doi.org/10.15468/dl.g1z7y7
-0000537-200127171203522	NA	2020-01-28 14:23:32	SUCCEEDED	https://doi.org/10.15468/dl.apwtzv
-0002883-200127171203522	NA	2020-02-01 18:40:05	SUCCEEDED	https://doi.org/10.15468/dl.oztfun
-0003154-200613084148143	NA	2020-06-17 08:36:35	SUCCEEDED	https://doi.org/10.15468/dl.97jyjt
-0003160-200613084148143	NA	2020-06-17 08:52:20	SUCCEEDED	https://doi.org/10.15468/dl.as99qq
-0123848-200613084148143	NA	2020-11-27 14:29:15	SUCCEEDED	https://doi.org/10.15468/dl.49ksep
-0124676-200613084148143	NA	2020-11-28 19:34:08	SUCCEEDED	https://doi.org/10.15468/dl.v5xe9r
+0003809-190415153152247	NA	2019-04-24T17:52:31Z	SUCCEEDED	https://doi.org/10.15468/dl.7gwm6j
+0008507-190621201848488	NA	2019-07-09T08:31:24Z	SUCCEEDED	https://doi.org/10.15468/dl.1eycss
+0030713-190918142434337	NA	2019-10-28T09:05:48Z	SUCCEEDED	https://doi.org/10.15468/dl.g1z7y7
+0000537-200127171203522	NA	2020-01-28T14:23:32Z	SUCCEEDED	https://doi.org/10.15468/dl.apwtzv
+0002883-200127171203522	NA	2020-02-01T18:40:05Z	SUCCEEDED	https://doi.org/10.15468/dl.oztfun
+0003154-200613084148143	NA	2020-06-17T08:36:35Z	SUCCEEDED	https://doi.org/10.15468/dl.97jyjt
+0003160-200613084148143	NA	2020-06-17T08:52:20Z	SUCCEEDED	https://doi.org/10.15468/dl.as99qq
+0123848-200613084148143	NA	2020-11-27T14:29:15Z	SUCCEEDED	https://doi.org/10.15468/dl.49ksep
+0124676-200613084148143	NA	2020-11-28T19:34:08Z	SUCCEEDED	https://doi.org/10.15468/dl.v5xe9r
+0173465-210914110416597		2022-03-05T15:42:33Z	SUCCEEDED	https://doi.org/10.15468/dl.8aasr6
+0174724-210914110416597		2022-03-07T14:46:49Z	SUCCEEDED	https://doi.org/10.15468/dl.kmh5hs
+0174958-210914110416597		2022-03-07T17:10:00Z	SUCCEEDED	https://doi.org/10.15468/dl.b22yu3

src/1_download.Rmd

@@ -37,7 +37,7 @@ library(lubridate)      # To work with dates
 We define country we want to get data cube:
 
 ```{r define_countries}
-countries <- c("LT")
+countries <- c("IT")
 ```
 
 ## Basis of record
@@ -83,15 +83,15 @@ Trigger download:
 
 ```{r trigger_gbif_download}
 # Reuse existing download (comment to trigger new download)
-# gbif_download_key <- "0124676-200613084148143"
+gbif_download_key <- "0173465-210914110416597"
 
 # Trigger new download (commented by default)
-gbif_download_key <- occ_download(
-  pred_in("country", countries),
-  pred_in("basisOfRecord", basis_of_record),
-  pred_gte("year", year_begin),
-  pred_lte("year", year_end),
-  pred("hasCoordinate", hasCoordinate))
+# gbif_download_key <- occ_download(
+#   pred_in("country", countries),
+#   pred_in("basisOfRecord", basis_of_record),
+#   pred_gte("year", year_begin),
+#   pred_lte("year", year_end),
+#   pred("hasCoordinate", hasCoordinate),
 #   user = rstudioapi::askForPassword("GBIF username"),
 #   pwd = rstudioapi::askForPassword("GBIF password"),
 #   email = rstudioapi::askForPassword("Email address for notification")

src/2_create_db.Rmd

@@ -37,8 +37,8 @@ library(RSQLite)        # To interact with SQlite databases
 Define key returned in `1_download.Rmd` and country:
 
 ```{r define_key_countries}
-key <- "0003154-200613084148143"
-countries <- c("BE")
+key <- "0173465-210914110416597"
+countries <- c("IT")
 ```
 
 Download the occurrences from GBIF:

src/3_assign_grid.Rmd

@@ -35,8 +35,8 @@ library(RSQLite)        # To interact with SQlite databases
 Define key returned in `1_download.Rmd` and country:
 
 ```{r define_key_countries}
-key <- "0003154-200613084148143"
-countries <- c("BE")
+key <- "0173465-210914110416597"
+countries <- c("IT")
 ```
 
 Name and path of `.sqlite` file:

src/4_aggregate.Rmd

@@ -33,8 +33,8 @@ library(RSQLite)        # To interact with SQlite databases
 Define key returned in `1_download.Rmd` and country:
 
 ```{r define_key_countries}
-key <- "0003154-200613084148143"
-countries <- c("BE")
+key <- "0173465-210914110416597"
+countries <- c("IT")
 ```
 
 Name and path of `.sqlite` file:
@@ -62,7 +62,7 @@ sqlite_occ <- dbConnect(SQLite(), dbname = sqlite_path)
 
 Species, synonyms of that species and infraspecific taxa of that species all share the same `speciesKey`.
 
-For speeding up the aggregation, we create an index on  `year`,  `eea_cell_code` and `speciesKey` if not present:
+For speeding up the aggregation, we create an index on `year`, `eea_cell_code` and `speciesKey` if not present:
 
 ```{r create_idx_speciesKey}
 idx_species_year_cell <- "idx_species_year_cell"
@@ -106,8 +106,8 @@ occ_cube_species <-
   dbGetQuery(sqlite_occ, query) %>%
   rename(
     n = "COUNT(_ROWID_)",
-    min_coord_uncertainty = "MIN(`coordinateUncertaintyInMeters`)"
-)
+    min_coord_uncertainty = "MIN(`coordinateUncertaintyInMeters`)") %>%
+  mutate(speciesKey = as.numeric(speciesKey))
 ```
 
 Preview:
@@ -120,7 +120,7 @@ Number of occurrences linked to taxa with higher rank than species:
 
 ```{r occs_higher_rank_than_species}
 occ_cube_species %>%
-  filter(speciesKey == 0) %>%
+  filter(speciesKey == 0 | is.na(speciesKey)) %>%
   select(n) %>%
   colSums()
 ```
@@ -130,14 +130,14 @@ We will discard them:
 ```{r remove_occs_with_higher_rank}
 occ_cube_species <-
   occ_cube_species %>%
-  filter(speciesKey != 0)
+  filter(speciesKey != 0 & !is.na(speciesKey))
 ```
 
 ## Map taxa
 
-Grouping by `speciesKey`, we loose informations about which taxa share the same  `speciesKey`. This information could be sometimes helpful. We extract it in a separate data.frame, `taxa_species`.
+Grouping by `speciesKey`, we loose informations about which taxa share the same `speciesKey`. This information could be sometimes helpful. We extract it in a separate data.frame, `taxa_species`.
 
-For speeding up the extraction, we create an index on  `speciesKey`,  `taxonKey` and `scientificName` if not present:
+For speeding up the extraction, we create an index on `speciesKey`, `taxonKey` and `scientificName` if not present:
 
 ```{r create_idx_speciesKey}
 idx_species_taxon_name <- "idx_species_taxon_name"
@@ -227,7 +227,7 @@ occ_cube_species_taxa %>%
   arrange(speciesKey, taxonKey)
 ```
 
-We create `taxa_species` by adding the taxonomic rank, `SPECIES`, and the taxonomic status of the species, one of `ACCEPTED` or  `DOUBTFUL`, and create a column called `include` which contains all taxa whose occurrences are linked to the species:
+We create `taxa_species` by adding the taxonomic rank, `SPECIES`, and the taxonomic status of the species, one of `ACCEPTED` or `DOUBTFUL`, and create a column called `include` which contains all taxa whose occurrences are linked to the species:
 
 ```{r make_taxa_species}
 taxa_species <- 
@@ -249,7 +249,7 @@ taxa_species <-
   reduce(full_join) %>%
 
   # select columns of interest
-  select(speciesKey, scientificName, rank, taxonomicStatus) %>%
+  select(speciesKey, scientificName, rank, taxonomicStatus, kingdom) %>%
   
   # rename 'scientificName' to 'species_scientificName'
   rename(species_scientificName = scientificName) %>%
@@ -261,7 +261,8 @@ taxa_species <-
   group_by(speciesKey,
            species_scientificName,
            rank,
-           taxonomicStatus) %>%
+           taxonomicStatus,
+           kingdom) %>%
   
   # create 'includes' column
   summarize(includes = paste(
@@ -304,11 +305,11 @@ taxa_species_filename <- paste0(
   ".csv"
 )
 write_csv(taxa_species,
-          path = here::here("data",
+          file = here::here("data",
                             "processed",
                             taxa_species_filename),
           na = "", 
-          quote_escape = FALSE
+          escape = "none"
 )
 ```