perform data validation on dates-as-strings

Author: nmdefries

backfill_corrections/delphiBackfillCorrection/R/main.R

@@ -309,12 +309,9 @@ main <- function(params,
     input_data <- lapply(
       files_list,
       function(file) {
-        df <- read_data(file) %>%
+        # refd_col and issued_col read in as strings
+        read_data(file) %>%
           fips_to_geovalue()
-        df[[refd_col]] <- as.Date(df[[refd_col]], "%Y-%m-%d")
-        df[[issued_col]] <- as.Date(df[[issued_col]], "%Y-%m-%d")
-
-        return(df)
       }
     ) %>%
       bind_rows()
@@ -336,6 +333,9 @@ main <- function(params,
       )
       input_data <- result[["df"]]
     }
+
+    input_data[[refd_col]] <- as.Date(input_data[[refd_col]], "%Y-%m-%d")
+    input_data[[issued_col]] <- as.Date(input_data[[issued_col]], "%Y-%m-%d")
 
     # Check available training days
     training_days_check(input_data[[issued_col]], params$training_days)

backfill_corrections/delphiBackfillCorrection/R/utils.R

@@ -156,19 +156,11 @@ validity_checks <- function(df, value_type, num_col, denom_col, signal_suffixes,
     stop("No reference date column detected for the reference date!")
   }
 
-  if (!(inherits(df[[refd_col]], "Date"))) {
-    stop("Reference date column must be of `Date` type")
-  }
-  
   # issue_date and lag should exist in the dataset
   if ( !(lag_col %in% colnames(df)) || !(issued_col %in% colnames(df)) ) {
     stop("Issue date and lag fields must exist in the input data")
   }
 
-  if (!(inherits(df[[issued_col]], "Date"))) {
-    stop("Issue date column must be of `Date` type")
-  }
-
   if ( any(is.na(df[[lag_col]])) || any(is.na(df[[issued_col]])) ||
     any(is.na(df[[refd_col]])) ) {
     stop("Issue date, lag, or reference date fields contain missing values")