Moved to read_tsv from read.table, and to inner_join from merge.

greenelab · Dec 19, 2017 · f96571d · f96571d
1 parent aac5bf5
commit f96571d
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 14 deletions.
diff --git a/evaluate_library_access_from_output_tsv/create_stratefied_sample_of_dois.R b/evaluate_library_access_from_output_tsv/create_stratefied_sample_of_dois.R
@@ -22,10 +22,8 @@ randomizer_seed_to_set <- 3  # Ensure that random sampling will always return
 
 # Read the dataset -------------------------------------------------------------
 
-library_access_data <- read.table(
+library_access_data <- readr::read_tsv(
   gzfile(lzma_compressed_library_access_data_location),
-  sep = '\t',
-  header = TRUE
 )
 # View(lzma_compressed_library_access_data)  # Check the dataset
 

diff --git a/evaluate_library_access_from_output_tsv/evaluate_library_access_from_output_tsv.Rmd b/evaluate_library_access_from_output_tsv/evaluate_library_access_from_output_tsv.Rmd
@@ -57,7 +57,7 @@ original_dataset_with_oa_color_column <- read.table(
 
 # Combine the datasets so that we have doi, full_text_indicator,
 # and oadoi_color
-merged_datasets <- merge(
+merged_datasets <- dplyr::inner_join(
   original_dataset_with_oa_color_column,
   lzma_compressed_library_access_tsv,
   by = "doi"

diff --git a/evaluate_library_access_from_output_tsv/facilitate_going_through_dois_manually.R b/evaluate_library_access_from_output_tsv/facilitate_going_through_dois_manually.R
@@ -7,22 +7,17 @@ manual_tsv_location <- file.path(
 
 # Open the tsv -----------------------------------------------------------------
 
-dataset_to_go_through <- read.table(
+dataset_to_go_through <- readr::read_tsv(
   manual_tsv_location,
-  sep = '\t',
-  na.strings = '',
-  header = TRUE,
-  colClasses = 'character'
+  na = ''
 )
 # View(dataset_to_go_through)
 
 # Facilitate going through the rows that haven't been filled in ----------------
 
-for (row_number in 
-  which(
-    is.na(dataset_to_go_through$full_text_indicator_manual)
-  )
-) {
+for (row_number in which(
+  is.na(dataset_to_go_through$full_text_indicator_manual)
+)) {
   doi_for_row <- dataset_to_go_through$doi[row_number]
 
   url_to_visit <- paste0(