Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix filtering function calls and introduce minor updates #9

Merged
merged 4 commits into from
Nov 8, 2023
Merged

Fix filtering function calls and introduce minor updates #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4fd82d8
Specify input and partition arguments in function calls
pranavanba Nov 1, 2023
8d4d09f
Minor fixes
pranavanba Nov 1, 2023
e1cdb3e
Ignore files and dirs whose names contain "pilot"
pranavanba Nov 7, 2023
1b2c2db
Use basename_template when writing parquet datasets
pranavanba Nov 8, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,3 +38,4 @@ dictionaries
dev*
misc*
*temp*
*pilot*
14 changes: 11 additions & 3 deletions filtering.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,13 +50,17 @@ drop_cols_datasets <- function(dataset, columns=c(), input = AWS_PARQUET_DOWNLOA
arrow::write_dataset(path = final_path,
max_rows_per_file = 100000,
partitioning = partitions,
existing_data_behavior = 'delete_matching')
existing_data_behavior = 'delete_matching',
basename_template = paste0("part-0000{i}.", as.character("parquet")))
}
}


# Filtering ---------------------------------------------------------------
dob2age("dataset_enrolledparticipants", "DateOfBirth")
dob2age(dataset = "dataset_enrolledparticipants",
column = "DateOfBirth",
input = AWS_PARQUET_DOWNLOAD_LOCATION,
partitions = "cohort")

unlink(PARQUET_FILTERED_LOCATION, recursive = T, force = T)

Expand All @@ -67,7 +71,11 @@ pii_to_drop <- synGet('syn52523394')$path %>% read.csv()
tmp <-
lapply(seq_len(nrow(pii_to_drop)), function(i) {
cat(i, "Dropping", pii_to_drop$column_to_be_dropped[[i]], "from", pii_to_drop$dataset[[i]], "\n")
drop_cols_datasets(dataset = pii_to_drop$dataset[[i]], columns = pii_to_drop$column_to_be_dropped[[i]])
drop_cols_datasets(dataset = pii_to_drop$dataset[[i]],
columns = pii_to_drop$column_to_be_dropped[[i]],
input = AWS_PARQUET_DOWNLOAD_LOCATION,
output = PARQUET_FILTERED_LOCATION,
partitions = "cohort")
})

rm(pii_to_drop)
8 changes: 4 additions & 4 deletions sts_synindex_external.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,14 +170,14 @@ system(manifest_cmd)

# Index files in Synapse --------------------------------------------------
# Get a list of all files to upload and their synapse locations (parentId)
STR_LEN_PARQUET_FINAL_LOCATION <- stringr::str_length(PARQUET_FINAL_LOCATION)
STR_LEN_PARQUET_FINAL_LOCATION <- stringr::str_length(AWS_ARCHIVE_DOWNLOAD_LOCATION)

## List all local files present (from manifest)
synapse_manifest <-
read.csv('./current_manifest.tsv', sep = '\t', stringsAsFactors = F) %>%
dplyr::filter(!grepl('owner.txt', path)) %>%
dplyr::rowwise() %>%
dplyr::mutate(file_key = stringr::str_sub(string = path, start = STR_LEN_PARQUET_FINAL_LOCATION)) %>%
dplyr::mutate(file_key = stringr::str_sub(string = path, start = STR_LEN_PARQUET_FINAL_LOCATION+2)) %>%
dplyr::mutate(s3_file_key = paste0(PARQUET_BUCKET_BASE_KEY_ARCHIVE, file_key)) %>%
dplyr::mutate(md5_hash = as.character(tools::md5sum(path))) %>%
dplyr::ungroup()
Expand Down Expand Up @@ -232,8 +232,8 @@ if(nrow(synapse_manifest_to_upload) > 0){
name = new_fileName)

f <- synStore(f,
activity = "Indexing",
activityDescription = "Indexing external parquet datasets",
activityName = "Indexing",
activityDescription = "Indexing external parquet datasets",
used = PARQUET_FOLDER_INTERNAL,
executed = latest_commit_tree_url)

Expand Down