From f73d26da5adb5dc8aacbd9f127c76bbd5b4036b9 Mon Sep 17 00:00:00 2001 From: Pranav Anbarasu Date: Fri, 14 Jun 2024 16:49:17 +0000 Subject: [PATCH] Trim whitespace from column values before using in subsequent steps --- scripts/filtering/filtering.R | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/scripts/filtering/filtering.R b/scripts/filtering/filtering.R index 1b20dba..cd3c002 100644 --- a/scripts/filtering/filtering.R +++ b/scripts/filtering/filtering.R @@ -71,7 +71,10 @@ unlink(PARQUET_FILTERED_LOCATION, recursive = T, force = T) synLogin() -pii_to_drop <- synGet(PII_COLS_TO_DROP)$path %>% read.csv() +pii_to_drop <- + synGet(PII_COLS_TO_DROP)$path %>% + read.csv() %>% + dplyr::mutate(column_to_be_dropped = trimws(column_to_be_dropped)) datasets_to_filter <- pii_to_drop$dataset %>% unique() cols_to_drop <- lapply(datasets_to_filter, function(x) {